diff --git a/examples/amazon-google/AmazonGoogle.py b/examples/amazon-google/AmazonGoogle.py index 26e006900..54f210e17 100644 --- a/examples/amazon-google/AmazonGoogle.py +++ b/examples/amazon-google/AmazonGoogle.py @@ -33,7 +33,7 @@ args.setOutput(outputPipe) -options = ClientOptions([ClientOptions.PHASE,"link"]) +options = ClientOptions([ClientOptions.PHASE,"match"]) #Zingg execution for the given phase zingg = Zingg(args, options) diff --git a/examples/amazon-google/configWithStopWords.json b/examples/amazon-google/configWithStopWords.json index c47478fed..cb38f1f10 100644 --- a/examples/amazon-google/configWithStopWords.json +++ b/examples/amazon-google/configWithStopWords.json @@ -48,16 +48,7 @@ "delimiter": ",", "header":true }, - "schema": - "{\"type\" : \"struct\", - \"fields\" : [ - {\"name\":\"id\", \"type\":\"string\", \"nullable\":false}, - {\"name\":\"title\", \"type\":\"string\", \"nullable\":true}, - {\"name\":\"description\", \"type\":\"string\", \"nullable\":true}, - {\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} , - {\"name\":\"price\", \"type\":\"double\", \"nullable\":true} - ] - }" + "schema": "id string, title string, description string, manufacturer string, price double" }, { "name":"google", @@ -67,16 +58,7 @@ "delimiter": ",", "header":true }, - "schema": - "{\"type\" : \"struct\", - \"fields\" : [ - {\"name\":\"id\", \"type\":\"string\", \"nullable\":false}, - {\"name\":\"title\", \"type\":\"string\", \"nullable\":true}, - {\"name\":\"description\", \"type\":\"string\", \"nullable\":true}, - {\"name\":\"manufacturer\",\"type\":\"string\",\"nullable\":true} , - {\"name\":\"price\", \"type\":\"double\", \"nullable\":true} - ] - }" + "schema": "id string, title string, description string, manufacturer string, price double" } ], "labelDataSampleSize" : 0.4, diff --git a/examples/febrl/FebrlExample.py b/examples/febrl/FebrlExample.py index 705c703a4..c2bc11d01 100644 --- a/examples/febrl/FebrlExample.py +++ b/examples/febrl/FebrlExample.py @@ -37,7 +37,7 @@ args.setOutput(outputPipe) -options = ClientOptions([ClientOptions.PHASE,"label"]) +options = ClientOptions([ClientOptions.PHASE,"match"]) #Zingg execution for the given phase zingg = Zingg(args, options) diff --git a/examples/iTunes-amazon/iTunesAmazon.py b/examples/iTunes-amazon/iTunesAmazon.py index 6d3e743f0..d700c1f64 100644 --- a/examples/iTunes-amazon/iTunesAmazon.py +++ b/examples/iTunes-amazon/iTunesAmazon.py @@ -37,7 +37,7 @@ outputPipe = CsvPipe("iTunesAmazonresult", "/tmp/iTunesAmazonOutput") args.setOutput(outputPipe) -options = ClientOptions([ClientOptions.PHASE,"link"]) +options = ClientOptions([ClientOptions.PHASE,"match"]) #Zingg execution for the given phase zingg = Zingg(args, options) diff --git a/examples/ncVoters5M/ncVoters.py b/examples/ncVoters5M/ncVoters.py index 357c51b76..c4b6fc34b 100644 --- a/examples/ncVoters5M/ncVoters.py +++ b/examples/ncVoters5M/ncVoters.py @@ -8,7 +8,7 @@ givenname = FieldDefinition("givenname", "string", MatchType.FUZZY) surname = FieldDefinition("surname", "string", MatchType.EXACT) suburb = FieldDefinition("suburb","string", MatchType.FUZZY) -postcode = FieldDefinition("postcode", "double", MatchType.EXACT) +postcode = FieldDefinition("postcode", "string", MatchType.EXACT) fieldDefs = [recid, givenname, surname, suburb, postcode] args.setFieldDefinition(fieldDefs) @@ -21,7 +21,7 @@ #reading dataset into inputPipe and settint it up in 'args' #below line should not be required if you are reading from in memory dataset #in that case, replace df with input df -schema = "recid string, givenname string, surname string, suburb string, postcode double " +schema = "recid string, givenname string, surname string, suburb string, postcode string " inputPipe = CsvPipe("ncVotersTest", "examples/ncVoters5M/5Party-ocp20/", schema) args.setData(inputPipe) @@ -30,7 +30,7 @@ args.setOutput(outputPipe) -options = ClientOptions([ClientOptions.PHASE,"trainMatch"]) +options = ClientOptions([ClientOptions.PHASE,"match"]) #Zingg execution for the given phase zingg = Zingg(args, options) diff --git a/models/100/model/block/zingg.block/.part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet.crc b/models/100/model/block/zingg.block/.part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet.crc new file mode 100644 index 000000000..d63731903 Binary files /dev/null and b/models/100/model/block/zingg.block/.part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet.crc differ diff --git a/models/100/model/block/zingg.block/.part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet.crc b/models/100/model/block/zingg.block/.part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet.crc deleted file mode 100644 index e84c34c2e..000000000 Binary files a/models/100/model/block/zingg.block/.part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/100/model/block/zingg.block/part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet b/models/100/model/block/zingg.block/part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet new file mode 100644 index 000000000..682dd2918 Binary files /dev/null and b/models/100/model/block/zingg.block/part-00000-07541197-25f5-49a0-a765-1118752066d5-c000.snappy.parquet differ diff --git a/models/100/model/block/zingg.block/part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet b/models/100/model/block/zingg.block/part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet deleted file mode 100644 index 48335b55b..000000000 Binary files a/models/100/model/block/zingg.block/part-00000-3585cf25-210b-42e5-8f66-fce8d46290f1-c000.snappy.parquet and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/metadata/.part-00000.crc index b4ee3d48c..6638f63e2 100644 Binary files a/models/100/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/100/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/bestModel/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/metadata/part-00000 index eb6352b69..1b827b765 100644 --- a/models/100/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/100/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1679653593791,"sparkVersion":"3.1.2","uid":"pipeline_37bd53de1842","paramMap":{"stageUids":["vecAssembler_ab6a72b9ff3a","poly_5441bacea924","logreg_8bb21326b817"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680262758849,"sparkVersion":"3.1.2","uid":"pipeline_7af7179ee2c9","paramMap":{"stageUids":["vecAssembler_d9c5b06776d6","poly_9e0e03752d9e","logreg_c64f720bac8d"]},"defaultParamMap":{}} diff --git a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc deleted file mode 100644 index 72654ca71..000000000 Binary files a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc new file mode 100644 index 000000000..1adf81258 Binary files /dev/null and b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/_SUCCESS b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/_SUCCESS rename to models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 similarity index 59% rename from models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 rename to models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 index 93cb6167a..53c07be8e 100644 --- a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 +++ b/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1679653593336,"sparkVersion":"3.1.2","uid":"vecAssembler_ab6a72b9ff3a","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17","z_sim18","z_sim19"]},"defaultParamMap":{"outputCol":"vecAssembler_ab6a72b9ff3a__output","handleInvalid":"error"}} +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680262758941,"sparkVersion":"3.1.2","uid":"vecAssembler_d9c5b06776d6","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17","z_sim18","z_sim19"]},"defaultParamMap":{"outputCol":"vecAssembler_d9c5b06776d6__output","handleInvalid":"error"}} diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/.part-00000.crc deleted file mode 100644 index cb964f9d2..000000000 Binary files a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/part-00000 deleted file mode 100644 index 0369df742..000000000 --- a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1679653593986,"sparkVersion":"3.1.2","uid":"poly_5441bacea924","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_5441bacea924__output"}} diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc new file mode 100644 index 000000000..453c2fde0 Binary files /dev/null and b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/_SUCCESS b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/1_poly_5441bacea924/metadata/_SUCCESS rename to models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/part-00000 new file mode 100644 index 000000000..de20cb032 --- /dev/null +++ b/models/100/model/classifier/best.model/bestModel/stages/1_poly_9e0e03752d9e/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680262759042,"sparkVersion":"3.1.2","uid":"poly_9e0e03752d9e","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_9e0e03752d9e__output"}} diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/.part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/.part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet.crc deleted file mode 100644 index cf075ec32..000000000 Binary files a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/.part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet deleted file mode 100644 index 34c8f375b..000000000 Binary files a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/part-00000-0be162b4-2dc5-4539-b471-1e19b42426e8-c000.snappy.parquet and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc deleted file mode 100644 index 0f871061e..000000000 Binary files a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/part-00000 deleted file mode 100644 index 5ffe6ff5c..000000000 --- a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1679653594084,"sparkVersion":"3.1.2","uid":"logreg_8bb21326b817","paramMap":{"fitIntercept":true,"predictionCol":"z_prediction","regParam":1.0E-4,"probabilityCol":"z_probability","maxIter":100,"threshold":0.4,"featuresCol":"z_feature","labelCol":"z_isMatch"},"defaultParamMap":{"fitIntercept":true,"predictionCol":"prediction","regParam":0.0,"tol":1.0E-6,"probabilityCol":"probability","standardization":true,"family":"auto","elasticNetParam":0.0,"maxIter":100,"threshold":0.5,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"featuresCol":"features","aggregationDepth":2,"labelCol":"label"}} diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/._SUCCESS.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/._SUCCESS.crc rename to models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/.part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/.part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet.crc new file mode 100644 index 000000000..b36df29d1 Binary files /dev/null and b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/.part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet.crc differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/_SUCCESS b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/data/_SUCCESS rename to models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/_SUCCESS diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet new file mode 100644 index 000000000..813579462 Binary files /dev/null and b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/data/part-00000-0faf943f-3ad3-4fff-b133-467678fdf77d-c000.snappy.parquet differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc new file mode 100644 index 000000000..e40fabf3e Binary files /dev/null and b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/_SUCCESS b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/bestModel/stages/2_logreg_8bb21326b817/metadata/_SUCCESS rename to models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/part-00000 b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/part-00000 new file mode 100644 index 000000000..d22b94770 --- /dev/null +++ b/models/100/model/classifier/best.model/bestModel/stages/2_logreg_c64f720bac8d/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680262759138,"sparkVersion":"3.1.2","uid":"logreg_c64f720bac8d","paramMap":{"maxIter":100,"featuresCol":"z_feature","labelCol":"z_isMatch","fitIntercept":true,"regParam":1.0E-4,"probabilityCol":"z_probability","threshold":0.4,"predictionCol":"z_prediction"},"defaultParamMap":{"maxIter":100,"featuresCol":"features","elasticNetParam":0.0,"labelCol":"label","fitIntercept":true,"regParam":0.0,"maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","probabilityCol":"probability","aggregationDepth":2,"tol":1.0E-6,"family":"auto","threshold":0.5,"predictionCol":"prediction","standardization":true}} diff --git a/models/100/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/metadata/.part-00000.crc index f4c2e12eb..c34955de0 100644 Binary files a/models/100/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/100/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/estimator/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/metadata/part-00000 index fe3ebec01..f68a4abc1 100644 --- a/models/100/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/100/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1679653593142,"sparkVersion":"3.1.2","uid":"pipeline_37bd53de1842","paramMap":{"stageUids":["vecAssembler_ab6a72b9ff3a","poly_5441bacea924","logreg_8bb21326b817"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680262758290,"sparkVersion":"3.1.2","uid":"pipeline_7af7179ee2c9","paramMap":{"stageUids":["vecAssembler_d9c5b06776d6","poly_9e0e03752d9e","logreg_c64f720bac8d"]},"defaultParamMap":{}} diff --git a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc deleted file mode 100644 index 29349c26c..000000000 Binary files a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc new file mode 100644 index 000000000..ec099e8d0 Binary files /dev/null and b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/_SUCCESS b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_ab6a72b9ff3a/metadata/_SUCCESS rename to models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 similarity index 59% rename from models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 rename to models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 index e248cacdf..4927b6a3d 100644 --- a/models/100/model/classifier/best.model/bestModel/stages/0_vecAssembler_ab6a72b9ff3a/metadata/part-00000 +++ b/models/100/model/classifier/best.model/estimator/stages/0_vecAssembler_d9c5b06776d6/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1679653593881,"sparkVersion":"3.1.2","uid":"vecAssembler_ab6a72b9ff3a","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17","z_sim18","z_sim19"]},"defaultParamMap":{"outputCol":"vecAssembler_ab6a72b9ff3a__output","handleInvalid":"error"}} +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680262758441,"sparkVersion":"3.1.2","uid":"vecAssembler_d9c5b06776d6","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17","z_sim18","z_sim19"]},"defaultParamMap":{"outputCol":"vecAssembler_d9c5b06776d6__output","handleInvalid":"error"}} diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/.part-00000.crc deleted file mode 100644 index 09c53b6b9..000000000 Binary files a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/part-00000 deleted file mode 100644 index d91bc8328..000000000 --- a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1679653593509,"sparkVersion":"3.1.2","uid":"poly_5441bacea924","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_5441bacea924__output"}} diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc new file mode 100644 index 000000000..bf006a7ad Binary files /dev/null and b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/_SUCCESS b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/1_poly_5441bacea924/metadata/_SUCCESS rename to models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/part-00000 new file mode 100644 index 000000000..f05bf89bc --- /dev/null +++ b/models/100/model/classifier/best.model/estimator/stages/1_poly_9e0e03752d9e/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680262758623,"sparkVersion":"3.1.2","uid":"poly_9e0e03752d9e","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_9e0e03752d9e__output"}} diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc deleted file mode 100644 index e310df959..000000000 Binary files a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/.part-00000.crc and /dev/null differ diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/part-00000 deleted file mode 100644 index 1809ec525..000000000 --- a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1679653593660,"sparkVersion":"3.1.2","uid":"logreg_8bb21326b817","paramMap":{"fitIntercept":true,"predictionCol":"z_prediction","probabilityCol":"z_probability","maxIter":100,"featuresCol":"z_feature","labelCol":"z_isMatch"},"defaultParamMap":{"fitIntercept":true,"predictionCol":"prediction","regParam":0.0,"tol":1.0E-6,"probabilityCol":"probability","standardization":true,"family":"auto","elasticNetParam":0.0,"maxIter":100,"threshold":0.5,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"featuresCol":"features","aggregationDepth":2,"labelCol":"label"}} diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/._SUCCESS.crc b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/._SUCCESS.crc similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/._SUCCESS.crc rename to models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/._SUCCESS.crc diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc new file mode 100644 index 000000000..5bacd9efd Binary files /dev/null and b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/_SUCCESS b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/_SUCCESS similarity index 100% rename from models/100/model/classifier/best.model/estimator/stages/2_logreg_8bb21326b817/metadata/_SUCCESS rename to models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/_SUCCESS diff --git a/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/part-00000 b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/part-00000 new file mode 100644 index 000000000..2e966f745 --- /dev/null +++ b/models/100/model/classifier/best.model/estimator/stages/2_logreg_c64f720bac8d/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680262758752,"sparkVersion":"3.1.2","uid":"logreg_c64f720bac8d","paramMap":{"maxIter":100,"featuresCol":"z_feature","labelCol":"z_isMatch","fitIntercept":true,"probabilityCol":"z_probability","predictionCol":"z_prediction"},"defaultParamMap":{"maxIter":100,"featuresCol":"features","elasticNetParam":0.0,"labelCol":"label","fitIntercept":true,"regParam":0.0,"maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","probabilityCol":"probability","aggregationDepth":2,"tol":1.0E-6,"family":"auto","threshold":0.5,"predictionCol":"prediction","standardization":true}} diff --git a/models/100/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/100/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 3d7778a26..ac3353725 100644 Binary files a/models/100/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/100/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/evaluator/metadata/part-00000 b/models/100/model/classifier/best.model/evaluator/metadata/part-00000 index e9ff4520c..6bbda4919 100644 --- a/models/100/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/100/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1679653592846,"sparkVersion":"3.1.2","uid":"binEval_193e68f2fb20","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","rawPredictionCol":"rawPrediction","labelCol":"label","numBins":1000}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680262758064,"sparkVersion":"3.1.2","uid":"binEval_d85e7822d500","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","labelCol":"label","numBins":1000,"rawPredictionCol":"rawPrediction"}} diff --git a/models/100/model/classifier/best.model/metadata/.part-00000.crc b/models/100/model/classifier/best.model/metadata/.part-00000.crc index 7157acaf4..da8566a41 100644 Binary files a/models/100/model/classifier/best.model/metadata/.part-00000.crc and b/models/100/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/100/model/classifier/best.model/metadata/part-00000 b/models/100/model/classifier/best.model/metadata/part-00000 index d46ba7e77..02e82db77 100644 --- a/models/100/model/classifier/best.model/metadata/part-00000 +++ b/models/100/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1679653592157,"sparkVersion":"3.1.2","uid":"cv_9205a151ad83","paramMap":{"seed":-1191137437,"numFolds":2,"foldCol":"","estimatorParamMaps":[[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_8bb21326b817","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_8bb21326b817","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"seed":-1191137437,"numFolds":3,"foldCol":""},"avgMetrics":[0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680262757721,"sparkVersion":"3.1.2","uid":"cv_b6b3e46792cc","paramMap":{"numFolds":2,"seed":-1191137437,"foldCol":"","estimatorParamMaps":[[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_c64f720bac8d","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_c64f720bac8d","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"seed":-1191137437,"foldCol":""},"avgMetrics":[0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571,0.9821428571428571],"persistSubModels":false} diff --git a/models/101/model/block/zingg.block/.part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet.crc b/models/101/model/block/zingg.block/.part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet.crc new file mode 100644 index 000000000..a177349a3 Binary files /dev/null and b/models/101/model/block/zingg.block/.part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet.crc differ diff --git a/models/101/model/block/zingg.block/part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet b/models/101/model/block/zingg.block/part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet new file mode 100644 index 000000000..830220c86 Binary files /dev/null and b/models/101/model/block/zingg.block/part-00000-9ac38206-8cb9-4357-a37b-7279e46adda7-c000.snappy.parquet differ diff --git a/models/101/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/101/model/classifier/best.model/bestModel/metadata/.part-00000.crc index 617a52c17..a0f519cd3 100644 Binary files a/models/101/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/101/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/101/model/classifier/best.model/bestModel/metadata/part-00000 b/models/101/model/classifier/best.model/bestModel/metadata/part-00000 index f60647d7e..145f5e4f8 100644 --- a/models/101/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/101/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680245294860,"sparkVersion":"3.1.2","uid":"pipeline_f729a6b01032","paramMap":{"stageUids":["vecAssembler_5a4a15106c47","poly_993555b1f9db","logreg_d93ca38a2205"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680265841416,"sparkVersion":"3.1.2","uid":"pipeline_f47d307ed35b","paramMap":{"stageUids":["vecAssembler_7e2cbf38f293","poly_747cf01a21ce","logreg_549169031548"]},"defaultParamMap":{}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc new file mode 100644 index 000000000..05cf882a5 Binary files /dev/null and b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/_SUCCESS b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/_SUCCESS rename to models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 new file mode 100644 index 000000000..a7fa78a8a --- /dev/null +++ b/models/101/model/classifier/best.model/bestModel/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680265841509,"sparkVersion":"3.1.2","uid":"vecAssembler_7e2cbf38f293","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_7e2cbf38f293__output"}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc new file mode 100644 index 000000000..9b3ff2bb4 Binary files /dev/null and b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/_SUCCESS b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/_SUCCESS rename to models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/part-00000 b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/part-00000 new file mode 100644 index 000000000..e59858f60 --- /dev/null +++ b/models/101/model/classifier/best.model/bestModel/stages/1_poly_747cf01a21ce/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680265841610,"sparkVersion":"3.1.2","uid":"poly_747cf01a21ce","paramMap":{"outputCol":"z_feature","inputCol":"z_featurevector","degree":3},"defaultParamMap":{"outputCol":"poly_747cf01a21ce__output","degree":2}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/._SUCCESS.crc b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/._SUCCESS.crc rename to models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/.part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet.crc b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/.part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet.crc new file mode 100644 index 000000000..a2e613edf Binary files /dev/null and b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/.part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/_SUCCESS b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/_SUCCESS rename to models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/_SUCCESS diff --git a/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet new file mode 100644 index 000000000..a1925b6e3 Binary files /dev/null and b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/data/part-00000-4488bb70-c1b3-4678-ba31-5c344b30d8ea-c000.snappy.parquet differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/.part-00000.crc b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/.part-00000.crc new file mode 100644 index 000000000..52c742e5b Binary files /dev/null and b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/_SUCCESS b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/_SUCCESS rename to models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/part-00000 b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/part-00000 new file mode 100644 index 000000000..f4279eadd --- /dev/null +++ b/models/101/model/classifier/best.model/bestModel/stages/2_logreg_549169031548/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680265841700,"sparkVersion":"3.1.2","uid":"logreg_549169031548","paramMap":{"probabilityCol":"z_probability","threshold":0.4,"maxIter":100,"labelCol":"z_isMatch","regParam":1.0E-4,"fitIntercept":true,"predictionCol":"z_prediction","featuresCol":"z_feature"},"defaultParamMap":{"standardization":true,"tol":1.0E-6,"probabilityCol":"probability","threshold":0.5,"elasticNetParam":0.0,"maxIter":100,"aggregationDepth":2,"labelCol":"label","rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"regParam":0.0,"fitIntercept":true,"family":"auto","featuresCol":"features","predictionCol":"prediction"}} diff --git a/models/101/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/101/model/classifier/best.model/estimator/metadata/.part-00000.crc index 5e397fc43..220360ca7 100644 Binary files a/models/101/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/101/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/101/model/classifier/best.model/estimator/metadata/part-00000 b/models/101/model/classifier/best.model/estimator/metadata/part-00000 index e8a1dbde7..4869ab4c5 100644 --- a/models/101/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/101/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1680245294278,"sparkVersion":"3.1.2","uid":"pipeline_f729a6b01032","paramMap":{"stageUids":["vecAssembler_5a4a15106c47","poly_993555b1f9db","logreg_d93ca38a2205"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680265840860,"sparkVersion":"3.1.2","uid":"pipeline_f47d307ed35b","paramMap":{"stageUids":["vecAssembler_7e2cbf38f293","poly_747cf01a21ce","logreg_549169031548"]},"defaultParamMap":{}} diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc new file mode 100644 index 000000000..551601dae Binary files /dev/null and b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/_SUCCESS b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/_SUCCESS rename to models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 new file mode 100644 index 000000000..d4d60eca7 --- /dev/null +++ b/models/101/model/classifier/best.model/estimator/stages/0_vecAssembler_7e2cbf38f293/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680265841028,"sparkVersion":"3.1.2","uid":"vecAssembler_7e2cbf38f293","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_7e2cbf38f293__output"}} diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc new file mode 100644 index 000000000..4ef69fadf Binary files /dev/null and b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/_SUCCESS b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/_SUCCESS rename to models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/part-00000 b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/part-00000 new file mode 100644 index 000000000..9aca086b5 --- /dev/null +++ b/models/101/model/classifier/best.model/estimator/stages/1_poly_747cf01a21ce/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680265841196,"sparkVersion":"3.1.2","uid":"poly_747cf01a21ce","paramMap":{"outputCol":"z_feature","inputCol":"z_featurevector","degree":3},"defaultParamMap":{"outputCol":"poly_747cf01a21ce__output","degree":2}} diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/._SUCCESS.crc b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/._SUCCESS.crc similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/._SUCCESS.crc rename to models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/._SUCCESS.crc diff --git a/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/.part-00000.crc b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/.part-00000.crc new file mode 100644 index 000000000..375f8336c Binary files /dev/null and b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/_SUCCESS b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/_SUCCESS similarity index 100% rename from models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/_SUCCESS rename to models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/_SUCCESS diff --git a/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/part-00000 b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/part-00000 new file mode 100644 index 000000000..516fda795 --- /dev/null +++ b/models/101/model/classifier/best.model/estimator/stages/2_logreg_549169031548/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680265841325,"sparkVersion":"3.1.2","uid":"logreg_549169031548","paramMap":{"probabilityCol":"z_probability","maxIter":100,"labelCol":"z_isMatch","fitIntercept":true,"predictionCol":"z_prediction","featuresCol":"z_feature"},"defaultParamMap":{"standardization":true,"tol":1.0E-6,"probabilityCol":"probability","threshold":0.5,"elasticNetParam":0.0,"maxIter":100,"aggregationDepth":2,"labelCol":"label","rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"regParam":0.0,"fitIntercept":true,"family":"auto","featuresCol":"features","predictionCol":"prediction"}} diff --git a/models/101/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/101/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 25cf168a3..a50fc0830 100644 Binary files a/models/101/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/101/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/101/model/classifier/best.model/evaluator/metadata/part-00000 b/models/101/model/classifier/best.model/evaluator/metadata/part-00000 index 00451cd7e..c3243e9cb 100644 --- a/models/101/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/101/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680245294084,"sparkVersion":"3.1.2","uid":"binEval_6474a4cf721e","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","labelCol":"label","rawPredictionCol":"rawPrediction","numBins":1000}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680265840687,"sparkVersion":"3.1.2","uid":"binEval_0d11aa51189a","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"numBins":1000,"metricName":"areaUnderROC","labelCol":"label","rawPredictionCol":"rawPrediction"}} diff --git a/models/101/model/classifier/best.model/metadata/.part-00000.crc b/models/101/model/classifier/best.model/metadata/.part-00000.crc index 9c6250e4a..70d3976e6 100644 Binary files a/models/101/model/classifier/best.model/metadata/.part-00000.crc and b/models/101/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/101/model/classifier/best.model/metadata/part-00000 b/models/101/model/classifier/best.model/metadata/part-00000 index 968e5d4e5..a9c729b89 100644 --- a/models/101/model/classifier/best.model/metadata/part-00000 +++ b/models/101/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680245293746,"sparkVersion":"3.1.2","uid":"cv_061b761fa61f","paramMap":{"seed":-1191137437,"numFolds":2,"foldCol":"","estimatorParamMaps":[[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_d93ca38a2205","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_d93ca38a2205","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"seed":-1191137437,"numFolds":3,"foldCol":""},"avgMetrics":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680265840365,"sparkVersion":"3.1.2","uid":"cv_393e1eb89b73","paramMap":{"foldCol":"","seed":-1191137437,"numFolds":2,"estimatorParamMaps":[[{"parent":"logreg_549169031548","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_549169031548","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_549169031548","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"foldCol":"","seed":-1191137437,"numFolds":3},"avgMetrics":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"persistSubModels":false} diff --git a/models/102/model/block/zingg.block/.part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet.crc b/models/102/model/block/zingg.block/.part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet.crc new file mode 100644 index 000000000..206678805 Binary files /dev/null and b/models/102/model/block/zingg.block/.part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet.crc differ diff --git a/models/102/model/block/zingg.block/part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet b/models/102/model/block/zingg.block/part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet new file mode 100644 index 000000000..2b9a3f344 Binary files /dev/null and b/models/102/model/block/zingg.block/part-00000-55161d44-418c-44be-8bdf-f61060763ab7-c000.snappy.parquet differ diff --git a/models/102/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/102/model/classifier/best.model/bestModel/metadata/.part-00000.crc index a10c2ae8d..7e3958ce8 100644 Binary files a/models/102/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/102/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/102/model/classifier/best.model/bestModel/metadata/part-00000 b/models/102/model/classifier/best.model/bestModel/metadata/part-00000 index 4e50cdb7c..847df512d 100644 --- a/models/102/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/102/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680101698667,"sparkVersion":"3.1.2","uid":"pipeline_154fa7193cef","paramMap":{"stageUids":["vecAssembler_4a175f1d12b3","poly_d99d0c8d8dc7","logreg_4d7c6b94b7cd"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680267927465,"sparkVersion":"3.1.2","uid":"pipeline_62bf9a708195","paramMap":{"stageUids":["vecAssembler_1b8b8c8ee99d","poly_a486678959df","logreg_4fb040d64b43"]},"defaultParamMap":{}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc new file mode 100644 index 000000000..369030fdb Binary files /dev/null and b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/_SUCCESS b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/_SUCCESS rename to models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 new file mode 100644 index 000000000..e17f35fbf --- /dev/null +++ b/models/102/model/classifier/best.model/bestModel/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680267927556,"sparkVersion":"3.1.2","uid":"vecAssembler_1b8b8c8ee99d","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17"]},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_1b8b8c8ee99d__output"}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/.part-00000.crc b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/.part-00000.crc new file mode 100644 index 000000000..73f9282dd Binary files /dev/null and b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/_SUCCESS b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/_SUCCESS rename to models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/part-00000 b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/part-00000 new file mode 100644 index 000000000..07cb72356 --- /dev/null +++ b/models/102/model/classifier/best.model/bestModel/stages/1_poly_a486678959df/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680267927660,"sparkVersion":"3.1.2","uid":"poly_a486678959df","paramMap":{"degree":3,"inputCol":"z_featurevector","outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_a486678959df__output"}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/._SUCCESS.crc b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/._SUCCESS.crc rename to models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/.part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet.crc b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/.part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet.crc new file mode 100644 index 000000000..c36874e63 Binary files /dev/null and b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/.part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/_SUCCESS b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/_SUCCESS rename to models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/_SUCCESS diff --git a/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet new file mode 100644 index 000000000..197784acc Binary files /dev/null and b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/data/part-00000-7d0f69d7-9c97-4051-8073-3bb33e96ed0e-c000.snappy.parquet differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc new file mode 100644 index 000000000..9e60fc6d2 Binary files /dev/null and b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/_SUCCESS b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/_SUCCESS rename to models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/part-00000 b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/part-00000 new file mode 100644 index 000000000..bff18e9af --- /dev/null +++ b/models/102/model/classifier/best.model/bestModel/stages/2_logreg_4fb040d64b43/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680267927756,"sparkVersion":"3.1.2","uid":"logreg_4fb040d64b43","paramMap":{"regParam":1.0E-4,"fitIntercept":true,"threshold":0.4,"probabilityCol":"z_probability","labelCol":"z_isMatch","featuresCol":"z_feature","predictionCol":"z_prediction","maxIter":100},"defaultParamMap":{"regParam":0.0,"fitIntercept":true,"family":"auto","tol":1.0E-6,"threshold":0.5,"rawPredictionCol":"rawPrediction","standardization":true,"maxBlockSizeInMB":0.0,"aggregationDepth":2,"elasticNetParam":0.0,"probabilityCol":"probability","labelCol":"label","featuresCol":"features","predictionCol":"prediction","maxIter":100}} diff --git a/models/102/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/102/model/classifier/best.model/estimator/metadata/.part-00000.crc index 78d014e1b..5d8336a8f 100644 Binary files a/models/102/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/102/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/102/model/classifier/best.model/estimator/metadata/part-00000 b/models/102/model/classifier/best.model/estimator/metadata/part-00000 index 20de73e64..8fd931c13 100644 --- a/models/102/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/102/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1680101698112,"sparkVersion":"3.1.2","uid":"pipeline_154fa7193cef","paramMap":{"stageUids":["vecAssembler_4a175f1d12b3","poly_d99d0c8d8dc7","logreg_4d7c6b94b7cd"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680267926923,"sparkVersion":"3.1.2","uid":"pipeline_62bf9a708195","paramMap":{"stageUids":["vecAssembler_1b8b8c8ee99d","poly_a486678959df","logreg_4fb040d64b43"]},"defaultParamMap":{}} diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc new file mode 100644 index 000000000..48e00e42a Binary files /dev/null and b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/_SUCCESS b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/_SUCCESS rename to models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 new file mode 100644 index 000000000..522947a1b --- /dev/null +++ b/models/102/model/classifier/best.model/estimator/stages/0_vecAssembler_1b8b8c8ee99d/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680267927094,"sparkVersion":"3.1.2","uid":"vecAssembler_1b8b8c8ee99d","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14","z_sim15","z_sim16","z_sim17"]},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_1b8b8c8ee99d__output"}} diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/.part-00000.crc b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/.part-00000.crc new file mode 100644 index 000000000..4030808cc Binary files /dev/null and b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/_SUCCESS b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/_SUCCESS rename to models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/part-00000 b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/part-00000 new file mode 100644 index 000000000..559d1934d --- /dev/null +++ b/models/102/model/classifier/best.model/estimator/stages/1_poly_a486678959df/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680267927266,"sparkVersion":"3.1.2","uid":"poly_a486678959df","paramMap":{"degree":3,"inputCol":"z_featurevector","outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_a486678959df__output"}} diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/._SUCCESS.crc b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/._SUCCESS.crc similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/._SUCCESS.crc rename to models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/._SUCCESS.crc diff --git a/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc new file mode 100644 index 000000000..8137d1b6e Binary files /dev/null and b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/_SUCCESS b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/_SUCCESS similarity index 100% rename from models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/_SUCCESS rename to models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/_SUCCESS diff --git a/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/part-00000 b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/part-00000 new file mode 100644 index 000000000..26125f148 --- /dev/null +++ b/models/102/model/classifier/best.model/estimator/stages/2_logreg_4fb040d64b43/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680267927374,"sparkVersion":"3.1.2","uid":"logreg_4fb040d64b43","paramMap":{"fitIntercept":true,"probabilityCol":"z_probability","labelCol":"z_isMatch","featuresCol":"z_feature","predictionCol":"z_prediction","maxIter":100},"defaultParamMap":{"regParam":0.0,"fitIntercept":true,"family":"auto","tol":1.0E-6,"threshold":0.5,"rawPredictionCol":"rawPrediction","standardization":true,"maxBlockSizeInMB":0.0,"aggregationDepth":2,"elasticNetParam":0.0,"probabilityCol":"probability","labelCol":"label","featuresCol":"features","predictionCol":"prediction","maxIter":100}} diff --git a/models/102/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/102/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 71c272f07..20e476fcf 100644 Binary files a/models/102/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/102/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/102/model/classifier/best.model/evaluator/metadata/part-00000 b/models/102/model/classifier/best.model/evaluator/metadata/part-00000 index c061e0427..eed03b705 100644 --- a/models/102/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/102/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680101697886,"sparkVersion":"3.1.2","uid":"binEval_94a4787ded2d","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"numBins":1000,"labelCol":"label","metricName":"areaUnderROC","rawPredictionCol":"rawPrediction"}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680267926719,"sparkVersion":"3.1.2","uid":"binEval_06f033c31bc2","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"labelCol":"label","rawPredictionCol":"rawPrediction","numBins":1000,"metricName":"areaUnderROC"}} diff --git a/models/102/model/classifier/best.model/metadata/.part-00000.crc b/models/102/model/classifier/best.model/metadata/.part-00000.crc index c718a7075..576bea1c0 100644 Binary files a/models/102/model/classifier/best.model/metadata/.part-00000.crc and b/models/102/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/102/model/classifier/best.model/metadata/part-00000 b/models/102/model/classifier/best.model/metadata/part-00000 index a5aa22068..bc40f462e 100644 --- a/models/102/model/classifier/best.model/metadata/part-00000 +++ b/models/102/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680101697416,"sparkVersion":"3.1.2","uid":"cv_38f218539a64","paramMap":{"numFolds":2,"foldCol":"","seed":-1191137437,"estimatorParamMaps":[[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_4d7c6b94b7cd","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_4d7c6b94b7cd","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"foldCol":"","seed":-1191137437},"avgMetrics":[0.9043570889894419,0.9043570889894419,0.9043570889894419,0.9043570889894419,0.9014102564102564,0.9014102564102564,0.9014102564102564,0.9014102564102564,0.914304298642534,0.914304298642534,0.914304298642534,0.914304298642534,0.9293627450980393,0.9293627450980393,0.9293627450980393,0.9293627450980393,0.9535218702865762,0.9535218702865762,0.9535218702865762,0.9535218702865762],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680267926444,"sparkVersion":"3.1.2","uid":"cv_25d6be85c7f5","paramMap":{"foldCol":"","seed":-1191137437,"numFolds":2,"estimatorParamMaps":[[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_4fb040d64b43","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_4fb040d64b43","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"foldCol":"","seed":-1191137437,"numFolds":3},"avgMetrics":[0.9976470588235293,0.9976470588235293,0.9976470588235293,0.9970588235294118,0.9970588235294118,0.9976470588235293,0.9976470588235293,0.9976470588235293,0.9970588235294118,0.9970588235294118,0.9976470588235293,0.9976470588235293,0.9976470588235293,0.9970588235294118,0.9970588235294118,0.9976470588235293,0.9976470588235293,0.9976470588235293,0.9970588235294118,0.9970588235294118],"persistSubModels":false} diff --git a/models/102/trainingData/marked/._SUCCESS.crc b/models/102/trainingData/marked/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/102/trainingData/marked/._SUCCESS.crc differ diff --git a/models/102/trainingData/marked/.part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..d478db09e Binary files /dev/null and b/models/102/trainingData/marked/.part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..9fe814de3 Binary files /dev/null and b/models/102/trainingData/marked/.part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..6497790f9 Binary files /dev/null and b/models/102/trainingData/marked/.part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..fcc7ccef0 Binary files /dev/null and b/models/102/trainingData/marked/.part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..075c84a7f Binary files /dev/null and b/models/102/trainingData/marked/.part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..0c4414c12 Binary files /dev/null and b/models/102/trainingData/marked/.part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..81e0a5f17 Binary files /dev/null and b/models/102/trainingData/marked/.part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..7710da0ef Binary files /dev/null and b/models/102/trainingData/marked/.part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..1a181bdbb Binary files /dev/null and b/models/102/trainingData/marked/.part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..084a67173 Binary files /dev/null and b/models/102/trainingData/marked/.part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..c67b39783 Binary files /dev/null and b/models/102/trainingData/marked/.part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..d5cc58b4f Binary files /dev/null and b/models/102/trainingData/marked/.part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..342700adf Binary files /dev/null and b/models/102/trainingData/marked/.part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..c36ddd816 Binary files /dev/null and b/models/102/trainingData/marked/.part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..1a9069bda Binary files /dev/null and b/models/102/trainingData/marked/.part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..795a76a68 Binary files /dev/null and b/models/102/trainingData/marked/.part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..5583b52c9 Binary files /dev/null and b/models/102/trainingData/marked/.part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..5ce5546c3 Binary files /dev/null and b/models/102/trainingData/marked/.part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..a7b371206 Binary files /dev/null and b/models/102/trainingData/marked/.part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..e75b1c26b Binary files /dev/null and b/models/102/trainingData/marked/.part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..22445158f Binary files /dev/null and b/models/102/trainingData/marked/.part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/.part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc b/models/102/trainingData/marked/.part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc new file mode 100644 index 000000000..0522e13d1 Binary files /dev/null and b/models/102/trainingData/marked/.part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/marked/_SUCCESS b/models/102/trainingData/marked/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/102/trainingData/marked/part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..e9d86db84 Binary files /dev/null and b/models/102/trainingData/marked/part-00000-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..df4584be3 Binary files /dev/null and b/models/102/trainingData/marked/part-00005-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..0240b0e30 Binary files /dev/null and b/models/102/trainingData/marked/part-00011-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..bf79a1169 Binary files /dev/null and b/models/102/trainingData/marked/part-00017-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..22dddb248 Binary files /dev/null and b/models/102/trainingData/marked/part-00025-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..4ecd0a8c5 Binary files /dev/null and b/models/102/trainingData/marked/part-00034-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..89fc9838e Binary files /dev/null and b/models/102/trainingData/marked/part-00040-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..bdcb5a945 Binary files /dev/null and b/models/102/trainingData/marked/part-00044-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..d134cb428 Binary files /dev/null and b/models/102/trainingData/marked/part-00050-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..e3a591ea4 Binary files /dev/null and b/models/102/trainingData/marked/part-00061-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..c07818bf9 Binary files /dev/null and b/models/102/trainingData/marked/part-00066-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..4d7e14833 Binary files /dev/null and b/models/102/trainingData/marked/part-00071-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..131cfb693 Binary files /dev/null and b/models/102/trainingData/marked/part-00083-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..11dcd321a Binary files /dev/null and b/models/102/trainingData/marked/part-00084-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..f564638a3 Binary files /dev/null and b/models/102/trainingData/marked/part-00093-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..009d60032 Binary files /dev/null and b/models/102/trainingData/marked/part-00104-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..c07ccaa1f Binary files /dev/null and b/models/102/trainingData/marked/part-00105-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..a7a22fede Binary files /dev/null and b/models/102/trainingData/marked/part-00116-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..bf223288c Binary files /dev/null and b/models/102/trainingData/marked/part-00119-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..d320ada67 Binary files /dev/null and b/models/102/trainingData/marked/part-00127-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..738b9fb0c Binary files /dev/null and b/models/102/trainingData/marked/part-00135-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/marked/part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet b/models/102/trainingData/marked/part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet new file mode 100644 index 000000000..b05d5766f Binary files /dev/null and b/models/102/trainingData/marked/part-00143-d89e97d8-6e3d-46ba-b925-25dd23d5f855-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/._SUCCESS.crc b/models/102/trainingData/unmarked/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/102/trainingData/unmarked/._SUCCESS.crc differ diff --git a/models/102/trainingData/unmarked/.part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..c220614db Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..5aa97ded9 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..40aca3e30 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..d4cfe5d99 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..6ca2e5799 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..93f0c8396 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..1be0e5648 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..21c545080 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..6dc1adc81 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..f043c5144 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..a1b71299d Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..dbc6bb182 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..52c9f31a3 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..89bc0672c Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..5621f66a7 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..bcb358830 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..ed6965b3c Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..ffbe66ed9 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..c3a761734 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..e99014a5b Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/.part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc b/models/102/trainingData/unmarked/.part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc new file mode 100644 index 000000000..8c73be574 Binary files /dev/null and b/models/102/trainingData/unmarked/.part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet.crc differ diff --git a/models/102/trainingData/unmarked/_SUCCESS b/models/102/trainingData/unmarked/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/102/trainingData/unmarked/part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..19ee4fa2e Binary files /dev/null and b/models/102/trainingData/unmarked/part-00000-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..1fa578030 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00001-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..a58224018 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00002-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..0c5175c11 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00003-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..db0dbe389 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00004-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..c1002b9bf Binary files /dev/null and b/models/102/trainingData/unmarked/part-00005-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..c86a0b6af Binary files /dev/null and b/models/102/trainingData/unmarked/part-00006-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..f354c8ab2 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00007-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..825c88c75 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00008-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..b1053525d Binary files /dev/null and b/models/102/trainingData/unmarked/part-00009-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..6027e8e98 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00010-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..1078dccc6 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00011-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..00b586708 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00012-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..0e4c7b69b Binary files /dev/null and b/models/102/trainingData/unmarked/part-00013-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..397cfde96 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00014-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..ee27a10ea Binary files /dev/null and b/models/102/trainingData/unmarked/part-00015-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..757a71f3b Binary files /dev/null and b/models/102/trainingData/unmarked/part-00016-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..a20794db4 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00017-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..8ed0ec366 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00018-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..50a73d81c Binary files /dev/null and b/models/102/trainingData/unmarked/part-00019-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/102/trainingData/unmarked/part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet b/models/102/trainingData/unmarked/part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet new file mode 100644 index 000000000..0f74ac8b0 Binary files /dev/null and b/models/102/trainingData/unmarked/part-00020-20f7f302-09ce-41e0-ae37-0d2376f650cb-c000.snappy.parquet differ diff --git a/models/103/model/block/zingg.block/.part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet.crc b/models/103/model/block/zingg.block/.part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet.crc deleted file mode 100644 index b3de23315..000000000 Binary files a/models/103/model/block/zingg.block/.part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/103/model/block/zingg.block/.part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet.crc b/models/103/model/block/zingg.block/.part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet.crc new file mode 100644 index 000000000..188972fe7 Binary files /dev/null and b/models/103/model/block/zingg.block/.part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet.crc differ diff --git a/models/103/model/block/zingg.block/part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet b/models/103/model/block/zingg.block/part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet deleted file mode 100644 index d03eab5f9..000000000 Binary files a/models/103/model/block/zingg.block/part-00000-52cc335d-ee3c-4a83-95ab-c7102c85d412-c000.snappy.parquet and /dev/null differ diff --git a/models/103/model/block/zingg.block/part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet b/models/103/model/block/zingg.block/part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet new file mode 100644 index 000000000..83ac9878b Binary files /dev/null and b/models/103/model/block/zingg.block/part-00000-740dc996-1258-4468-bdbc-f5a891fe0a08-c000.snappy.parquet differ diff --git a/models/103/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/metadata/.part-00000.crc index 62b1f8e8e..2f5c3d795 100644 Binary files a/models/103/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/103/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/metadata/part-00000 index d1cb72c08..1bf8a7413 100644 --- a/models/103/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/103/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680013839842,"sparkVersion":"3.1.2","uid":"pipeline_6bdb624d34ef","paramMap":{"stageUids":["vecAssembler_d00f2c39b11a","poly_443766300674","logreg_0079fab6ffc2"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680262158848,"sparkVersion":"3.1.2","uid":"pipeline_8335b048edf8","paramMap":{"stageUids":["vecAssembler_9865120ec20e","poly_63b331cc0445","logreg_3a0f59767628"]},"defaultParamMap":{}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc new file mode 100644 index 000000000..032d1473b Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/_SUCCESS b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 new file mode 100644 index 000000000..733c3bb9a --- /dev/null +++ b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680262158938,"sparkVersion":"3.1.2","uid":"vecAssembler_9865120ec20e","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4"]},"defaultParamMap":{"outputCol":"vecAssembler_9865120ec20e__output","handleInvalid":"error"}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc deleted file mode 100644 index db98e0fa5..000000000 Binary files a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 deleted file mode 100644 index ba59a91d3..000000000 --- a/models/103/model/classifier/best.model/bestModel/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680013839937,"sparkVersion":"3.1.2","uid":"vecAssembler_d00f2c39b11a","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4"]},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_d00f2c39b11a__output"}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/.part-00000.crc deleted file mode 100644 index 45d97b73e..000000000 Binary files a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/part-00000 deleted file mode 100644 index 99c1fcfc0..000000000 --- a/models/103/model/classifier/best.model/bestModel/stages/1_poly_443766300674/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680013840111,"sparkVersion":"3.1.2","uid":"poly_443766300674","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_443766300674__output","degree":2}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/.part-00000.crc new file mode 100644 index 000000000..72f10de03 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/_SUCCESS b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/part-00000 new file mode 100644 index 000000000..fa49fd197 --- /dev/null +++ b/models/103/model/classifier/best.model/bestModel/stages/1_poly_63b331cc0445/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680262159038,"sparkVersion":"3.1.2","uid":"poly_63b331cc0445","paramMap":{"inputCol":"z_featurevector","outputCol":"z_feature","degree":3},"defaultParamMap":{"outputCol":"poly_63b331cc0445__output","degree":2}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/.part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/.part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet.crc deleted file mode 100644 index 501b182b5..000000000 Binary files a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/.part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc deleted file mode 100644 index ad30e127f..000000000 Binary files a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/part-00000 deleted file mode 100644 index 5225b9329..000000000 --- a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680013840199,"sparkVersion":"3.1.2","uid":"logreg_0079fab6ffc2","paramMap":{"predictionCol":"z_prediction","labelCol":"z_isMatch","fitIntercept":true,"regParam":1.0,"maxIter":100,"featuresCol":"z_feature","threshold":0.4,"probabilityCol":"z_probability"},"defaultParamMap":{"family":"auto","predictionCol":"prediction","labelCol":"label","standardization":true,"fitIntercept":true,"regParam":0.0,"aggregationDepth":2,"maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","elasticNetParam":0.0,"maxIter":100,"featuresCol":"features","threshold":0.5,"tol":1.0E-6,"probabilityCol":"probability"}} diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/._SUCCESS.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/.part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/.part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet.crc new file mode 100644 index 000000000..91cba6883 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/.part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/_SUCCESS b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet similarity index 65% rename from models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet rename to models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet index 8c0e9a331..ad68ca661 100644 Binary files a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_0079fab6ffc2/data/part-00000-be65f123-c3f1-4da8-9d51-53479ad5b96c-c000.snappy.parquet and b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/data/part-00000-4c054ebd-b13e-4492-bd09-dc73c8f4013c-c000.snappy.parquet differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc new file mode 100644 index 000000000..2d16025bb Binary files /dev/null and b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/_SUCCESS b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/part-00000 b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/part-00000 new file mode 100644 index 000000000..3f5852457 --- /dev/null +++ b/models/103/model/classifier/best.model/bestModel/stages/2_logreg_3a0f59767628/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680262159143,"sparkVersion":"3.1.2","uid":"logreg_3a0f59767628","paramMap":{"maxIter":100,"threshold":0.4,"labelCol":"z_isMatch","regParam":1.0,"predictionCol":"z_prediction","fitIntercept":true,"probabilityCol":"z_probability","featuresCol":"z_feature"},"defaultParamMap":{"elasticNetParam":0.0,"maxIter":100,"threshold":0.5,"tol":1.0E-6,"labelCol":"label","family":"auto","regParam":0.0,"predictionCol":"prediction","standardization":true,"fitIntercept":true,"featuresCol":"features","probabilityCol":"probability","maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","aggregationDepth":2}} diff --git a/models/103/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/metadata/.part-00000.crc index f7491b395..b63d1fb41 100644 Binary files a/models/103/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/103/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/metadata/part-00000 index d94b062b8..07098a6cd 100644 --- a/models/103/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/103/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1680013839351,"sparkVersion":"3.1.2","uid":"pipeline_6bdb624d34ef","paramMap":{"stageUids":["vecAssembler_d00f2c39b11a","poly_443766300674","logreg_0079fab6ffc2"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680262158363,"sparkVersion":"3.1.2","uid":"pipeline_8335b048edf8","paramMap":{"stageUids":["vecAssembler_9865120ec20e","poly_63b331cc0445","logreg_3a0f59767628"]},"defaultParamMap":{}} diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc new file mode 100644 index 000000000..1af61740d Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/_SUCCESS b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 new file mode 100644 index 000000000..7d15c0de0 --- /dev/null +++ b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_9865120ec20e/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680262158542,"sparkVersion":"3.1.2","uid":"vecAssembler_9865120ec20e","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4"]},"defaultParamMap":{"outputCol":"vecAssembler_9865120ec20e__output","handleInvalid":"error"}} diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc deleted file mode 100644 index dfeebe053..000000000 Binary files a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 deleted file mode 100644 index afadabb93..000000000 --- a/models/103/model/classifier/best.model/estimator/stages/0_vecAssembler_d00f2c39b11a/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680013839542,"sparkVersion":"3.1.2","uid":"vecAssembler_d00f2c39b11a","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4"]},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_d00f2c39b11a__output"}} diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/.part-00000.crc deleted file mode 100644 index d0222e30a..000000000 Binary files a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/part-00000 deleted file mode 100644 index ac0cef65f..000000000 --- a/models/103/model/classifier/best.model/estimator/stages/1_poly_443766300674/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680013839648,"sparkVersion":"3.1.2","uid":"poly_443766300674","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_443766300674__output","degree":2}} diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/.part-00000.crc new file mode 100644 index 000000000..8b9442709 Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/_SUCCESS b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/part-00000 new file mode 100644 index 000000000..e81594e8e --- /dev/null +++ b/models/103/model/classifier/best.model/estimator/stages/1_poly_63b331cc0445/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680262158661,"sparkVersion":"3.1.2","uid":"poly_63b331cc0445","paramMap":{"inputCol":"z_featurevector","outputCol":"z_feature","degree":3},"defaultParamMap":{"outputCol":"poly_63b331cc0445__output","degree":2}} diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc deleted file mode 100644 index 36f364682..000000000 Binary files a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/.part-00000.crc and /dev/null differ diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/part-00000 deleted file mode 100644 index 8f6cb5a59..000000000 --- a/models/103/model/classifier/best.model/estimator/stages/2_logreg_0079fab6ffc2/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680013839756,"sparkVersion":"3.1.2","uid":"logreg_0079fab6ffc2","paramMap":{"predictionCol":"z_prediction","labelCol":"z_isMatch","fitIntercept":true,"featuresCol":"z_feature","maxIter":100,"probabilityCol":"z_probability"},"defaultParamMap":{"family":"auto","predictionCol":"prediction","labelCol":"label","standardization":true,"fitIntercept":true,"regParam":0.0,"aggregationDepth":2,"maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","elasticNetParam":0.0,"maxIter":100,"featuresCol":"features","threshold":0.5,"tol":1.0E-6,"probabilityCol":"probability"}} diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/._SUCCESS.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc new file mode 100644 index 000000000..a7ab3f019 Binary files /dev/null and b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/_SUCCESS b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/part-00000 b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/part-00000 new file mode 100644 index 000000000..ec56f6b2a --- /dev/null +++ b/models/103/model/classifier/best.model/estimator/stages/2_logreg_3a0f59767628/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680262158758,"sparkVersion":"3.1.2","uid":"logreg_3a0f59767628","paramMap":{"maxIter":100,"labelCol":"z_isMatch","predictionCol":"z_prediction","fitIntercept":true,"probabilityCol":"z_probability","featuresCol":"z_feature"},"defaultParamMap":{"elasticNetParam":0.0,"maxIter":100,"threshold":0.5,"tol":1.0E-6,"labelCol":"label","family":"auto","regParam":0.0,"predictionCol":"prediction","standardization":true,"fitIntercept":true,"featuresCol":"features","probabilityCol":"probability","maxBlockSizeInMB":0.0,"rawPredictionCol":"rawPrediction","aggregationDepth":2}} diff --git a/models/103/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/103/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 27d3a5b5a..7274518f4 100644 Binary files a/models/103/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/103/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/evaluator/metadata/part-00000 b/models/103/model/classifier/best.model/evaluator/metadata/part-00000 index 92f47086f..919df1d12 100644 --- a/models/103/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/103/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680013839161,"sparkVersion":"3.1.2","uid":"binEval_37a0d9e27f7b","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","numBins":1000,"rawPredictionCol":"rawPrediction","labelCol":"label"}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680262158196,"sparkVersion":"3.1.2","uid":"binEval_96fc63cfa323","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"numBins":1000,"metricName":"areaUnderROC","rawPredictionCol":"rawPrediction","labelCol":"label"}} diff --git a/models/103/model/classifier/best.model/metadata/.part-00000.crc b/models/103/model/classifier/best.model/metadata/.part-00000.crc index c3ec5050d..a9bb4ed6d 100644 Binary files a/models/103/model/classifier/best.model/metadata/.part-00000.crc and b/models/103/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/103/model/classifier/best.model/metadata/part-00000 b/models/103/model/classifier/best.model/metadata/part-00000 index 6e7bc9e63..b1a19da92 100644 --- a/models/103/model/classifier/best.model/metadata/part-00000 +++ b/models/103/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680013838806,"sparkVersion":"3.1.2","uid":"cv_07757d959e12","paramMap":{"foldCol":"","numFolds":2,"seed":-1191137437,"estimatorParamMaps":[[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_0079fab6ffc2","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_0079fab6ffc2","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"foldCol":"","numFolds":3,"seed":-1191137437},"avgMetrics":[0.582995951417004,0.6077935222672064,0.6620698380566802,0.7555668016194332,0.768092105263158,0.582995951417004,0.6077935222672064,0.6620698380566802,0.7555668016194332,0.768092105263158,0.582995951417004,0.6077935222672064,0.6620698380566802,0.7555668016194332,0.768092105263158,0.582995951417004,0.6077935222672064,0.6620698380566802,0.7555668016194332,0.768092105263158],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680262157956,"sparkVersion":"3.1.2","uid":"cv_c242990c394f","paramMap":{"numFolds":2,"foldCol":"","seed":-1191137437,"estimatorParamMaps":[[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_3a0f59767628","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_3a0f59767628","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"foldCol":"","seed":-1191137437},"avgMetrics":[0.586411943319838,0.586411943319838,0.586411943319838,0.586411943319838,0.6077935222672064,0.6077935222672064,0.6077935222672064,0.6077935222672064,0.6620698380566802,0.6620698380566802,0.6620698380566802,0.6620698380566802,0.7555668016194332,0.7555668016194332,0.7555668016194332,0.7555668016194332,0.768092105263158,0.768092105263158,0.768092105263158,0.768092105263158],"persistSubModels":false} diff --git a/models/104/model/block/zingg.block/.part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet.crc b/models/104/model/block/zingg.block/.part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet.crc deleted file mode 100644 index c4bf0d293..000000000 Binary files a/models/104/model/block/zingg.block/.part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/104/model/block/zingg.block/.part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet.crc b/models/104/model/block/zingg.block/.part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet.crc new file mode 100644 index 000000000..e780df45b Binary files /dev/null and b/models/104/model/block/zingg.block/.part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet.crc differ diff --git a/models/104/model/block/zingg.block/part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet b/models/104/model/block/zingg.block/part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet deleted file mode 100644 index 52081fd1e..000000000 Binary files a/models/104/model/block/zingg.block/part-00000-07b6b24c-dbb8-4056-be49-37827718f79f-c000.snappy.parquet and /dev/null differ diff --git a/models/104/model/block/zingg.block/part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet b/models/104/model/block/zingg.block/part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet new file mode 100644 index 000000000..7ff693359 Binary files /dev/null and b/models/104/model/block/zingg.block/part-00000-88c65090-204a-4b45-b2f9-5a743eeddb37-c000.snappy.parquet differ diff --git a/models/104/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/metadata/.part-00000.crc index c99681584..5d0ce55fd 100644 Binary files a/models/104/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/104/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/metadata/part-00000 index 32d4176f9..444be19ca 100644 --- a/models/104/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/104/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1642264838747,"sparkVersion":"3.1.2","uid":"pipeline_8566bf7dad2a","paramMap":{"stageUids":["vecAssembler_6512829ad6e8","poly_1897eabfa440","logreg_bf272c896a01"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680273559856,"sparkVersion":"3.1.2","uid":"pipeline_7b7cf22a434d","paramMap":{"stageUids":["vecAssembler_ff75a98fdd66","poly_bb9a8037ef3c","logreg_e969b654a565"]},"defaultParamMap":{}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc deleted file mode 100644 index 8e2404ebf..000000000 Binary files a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 deleted file mode 100644 index afaa8251f..000000000 --- a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1642264838803,"sparkVersion":"3.1.2","uid":"vecAssembler_6512829ad6e8","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5"]},"defaultParamMap":{"outputCol":"vecAssembler_6512829ad6e8__output","handleInvalid":"error"}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc new file mode 100644 index 000000000..ac50fde20 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/_SUCCESS b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 new file mode 100644 index 000000000..45eff264b --- /dev/null +++ b/models/104/model/classifier/best.model/bestModel/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680273559942,"sparkVersion":"3.1.2","uid":"vecAssembler_ff75a98fdd66","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_ff75a98fdd66__output"}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/.part-00000.crc deleted file mode 100644 index b69f200f6..000000000 Binary files a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/part-00000 deleted file mode 100644 index b125ee33b..000000000 --- a/models/104/model/classifier/best.model/bestModel/stages/1_poly_1897eabfa440/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1642264838858,"sparkVersion":"3.1.2","uid":"poly_1897eabfa440","paramMap":{"inputCol":"z_featurevector","outputCol":"z_feature","degree":3},"defaultParamMap":{"outputCol":"poly_1897eabfa440__output","degree":2}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc new file mode 100644 index 000000000..e9deed5d4 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/_SUCCESS b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/part-00000 new file mode 100644 index 000000000..86384d734 --- /dev/null +++ b/models/104/model/classifier/best.model/bestModel/stages/1_poly_bb9a8037ef3c/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680273560034,"sparkVersion":"3.1.2","uid":"poly_bb9a8037ef3c","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_bb9a8037ef3c__output","degree":2}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/.part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/.part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet.crc deleted file mode 100644 index f58c10f3f..000000000 Binary files a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/.part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc deleted file mode 100644 index f70cfbcd3..000000000 Binary files a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/part-00000 deleted file mode 100644 index fa7626cc9..000000000 --- a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1642264838915,"sparkVersion":"3.1.2","uid":"logreg_bf272c896a01","paramMap":{"labelCol":"z_isMatch","regParam":0.1,"predictionCol":"z_prediction","maxIter":100,"fitIntercept":true,"featuresCol":"z_feature","threshold":0.4,"probabilityCol":"z_probability"},"defaultParamMap":{"labelCol":"label","regParam":0.0,"standardization":true,"tol":1.0E-6,"elasticNetParam":0.0,"predictionCol":"prediction","maxIter":100,"fitIntercept":true,"rawPredictionCol":"rawPrediction","family":"auto","featuresCol":"features","maxBlockSizeInMB":0.0,"aggregationDepth":2,"threshold":0.5,"probabilityCol":"probability"}} diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/._SUCCESS.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/.part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/.part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet.crc new file mode 100644 index 000000000..1f24cf9b6 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/.part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/_SUCCESS b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet new file mode 100644 index 000000000..d16a7f934 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/data/part-00000-922a1fd9-e085-4fa1-9e26-97985b6b1d36-c000.snappy.parquet differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/.part-00000.crc b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/.part-00000.crc new file mode 100644 index 000000000..681b5fff0 Binary files /dev/null and b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/_SUCCESS b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/part-00000 b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/part-00000 new file mode 100644 index 000000000..dee5dee49 --- /dev/null +++ b/models/104/model/classifier/best.model/bestModel/stages/2_logreg_e969b654a565/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680273560122,"sparkVersion":"3.1.2","uid":"logreg_e969b654a565","paramMap":{"threshold":0.4,"featuresCol":"z_feature","labelCol":"z_isMatch","fitIntercept":true,"regParam":1.0E-4,"probabilityCol":"z_probability","predictionCol":"z_prediction","maxIter":100},"defaultParamMap":{"aggregationDepth":2,"threshold":0.5,"featuresCol":"features","labelCol":"label","fitIntercept":true,"regParam":0.0,"standardization":true,"probabilityCol":"probability","predictionCol":"prediction","tol":1.0E-6,"family":"auto","elasticNetParam":0.0,"maxIter":100,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0}} diff --git a/models/104/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/metadata/.part-00000.crc index 0f0eae57c..360427333 100644 Binary files a/models/104/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/104/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/metadata/part-00000 index 4c7876a06..c8ccab875 100644 --- a/models/104/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/104/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1642264838517,"sparkVersion":"3.1.2","uid":"pipeline_8566bf7dad2a","paramMap":{"stageUids":["vecAssembler_6512829ad6e8","poly_1897eabfa440","logreg_bf272c896a01"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680273559286,"sparkVersion":"3.1.2","uid":"pipeline_7b7cf22a434d","paramMap":{"stageUids":["vecAssembler_ff75a98fdd66","poly_bb9a8037ef3c","logreg_e969b654a565"]},"defaultParamMap":{}} diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc deleted file mode 100644 index 5ae13006c..000000000 Binary files a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 deleted file mode 100644 index 4a77d7c44..000000000 --- a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_6512829ad6e8/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1642264838580,"sparkVersion":"3.1.2","uid":"vecAssembler_6512829ad6e8","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5"]},"defaultParamMap":{"outputCol":"vecAssembler_6512829ad6e8__output","handleInvalid":"error"}} diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc new file mode 100644 index 000000000..458661dd1 Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/_SUCCESS b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 new file mode 100644 index 000000000..cc6f2d3bd --- /dev/null +++ b/models/104/model/classifier/best.model/estimator/stages/0_vecAssembler_ff75a98fdd66/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680273559432,"sparkVersion":"3.1.2","uid":"vecAssembler_ff75a98fdd66","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_ff75a98fdd66__output"}} diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/.part-00000.crc deleted file mode 100644 index e2bc83a80..000000000 Binary files a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/part-00000 deleted file mode 100644 index 85cd01893..000000000 --- a/models/104/model/classifier/best.model/estimator/stages/1_poly_1897eabfa440/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1642264838646,"sparkVersion":"3.1.2","uid":"poly_1897eabfa440","paramMap":{"inputCol":"z_featurevector","outputCol":"z_feature","degree":3},"defaultParamMap":{"outputCol":"poly_1897eabfa440__output","degree":2}} diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc new file mode 100644 index 000000000..13729505a Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/_SUCCESS b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/part-00000 new file mode 100644 index 000000000..ebb3dcaf7 --- /dev/null +++ b/models/104/model/classifier/best.model/estimator/stages/1_poly_bb9a8037ef3c/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680273559590,"sparkVersion":"3.1.2","uid":"poly_bb9a8037ef3c","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_bb9a8037ef3c__output","degree":2}} diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc deleted file mode 100644 index bc7ff8916..000000000 Binary files a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/.part-00000.crc and /dev/null differ diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/part-00000 deleted file mode 100644 index 73b73ec04..000000000 --- a/models/104/model/classifier/best.model/estimator/stages/2_logreg_bf272c896a01/metadata/part-00000 +++ /dev/null @@ -1 +0,0 @@ -{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1642264838693,"sparkVersion":"3.1.2","uid":"logreg_bf272c896a01","paramMap":{"labelCol":"z_isMatch","predictionCol":"z_prediction","maxIter":100,"fitIntercept":true,"featuresCol":"z_feature","probabilityCol":"z_probability"},"defaultParamMap":{"labelCol":"label","regParam":0.0,"standardization":true,"tol":1.0E-6,"elasticNetParam":0.0,"predictionCol":"prediction","maxIter":100,"fitIntercept":true,"rawPredictionCol":"rawPrediction","family":"auto","featuresCol":"features","maxBlockSizeInMB":0.0,"aggregationDepth":2,"threshold":0.5,"probabilityCol":"probability"}} diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/._SUCCESS.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/.part-00000.crc b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/.part-00000.crc new file mode 100644 index 000000000..750632565 Binary files /dev/null and b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/_SUCCESS b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/part-00000 b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/part-00000 new file mode 100644 index 000000000..77aa25319 --- /dev/null +++ b/models/104/model/classifier/best.model/estimator/stages/2_logreg_e969b654a565/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680273559738,"sparkVersion":"3.1.2","uid":"logreg_e969b654a565","paramMap":{"featuresCol":"z_feature","labelCol":"z_isMatch","fitIntercept":true,"probabilityCol":"z_probability","predictionCol":"z_prediction","maxIter":100},"defaultParamMap":{"aggregationDepth":2,"threshold":0.5,"featuresCol":"features","labelCol":"label","fitIntercept":true,"regParam":0.0,"standardization":true,"probabilityCol":"probability","predictionCol":"prediction","tol":1.0E-6,"family":"auto","elasticNetParam":0.0,"maxIter":100,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0}} diff --git a/models/104/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/104/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 3226aacbb..49638bcaa 100644 Binary files a/models/104/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/104/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/evaluator/metadata/part-00000 b/models/104/model/classifier/best.model/evaluator/metadata/part-00000 index d2c8a2c20..fc8a24597 100644 --- a/models/104/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/104/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1642264838427,"sparkVersion":"3.1.2","uid":"binEval_2dde9b1e5087","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"numBins":1000,"rawPredictionCol":"rawPrediction","labelCol":"label","metricName":"areaUnderROC"}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680273559105,"sparkVersion":"3.1.2","uid":"binEval_7e34ba5b976c","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"labelCol":"label","rawPredictionCol":"rawPrediction","numBins":1000,"metricName":"areaUnderROC"}} diff --git a/models/104/model/classifier/best.model/metadata/.part-00000.crc b/models/104/model/classifier/best.model/metadata/.part-00000.crc index 4e97ef209..8fc5a31aa 100644 Binary files a/models/104/model/classifier/best.model/metadata/.part-00000.crc and b/models/104/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/104/model/classifier/best.model/metadata/part-00000 b/models/104/model/classifier/best.model/metadata/part-00000 index fc08b309e..39bed092a 100644 --- a/models/104/model/classifier/best.model/metadata/part-00000 +++ b/models/104/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1642264838189,"sparkVersion":"3.1.2","uid":"cv_6f0a4beb2dde","paramMap":{"numFolds":2,"seed":-1191137437,"foldCol":"","estimatorParamMaps":[[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_bf272c896a01","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_bf272c896a01","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"seed":-1191137437,"foldCol":""},"avgMetrics":[0.9607550286875182,0.9688232536333802,0.9740919340075458,0.9777956377112496,0.975987319447235,0.9607550286875182,0.9688232536333802,0.9740919340075458,0.9777956377112496,0.975987319447235,0.9607550286875182,0.9688232536333802,0.9740919340075458,0.9777956377112496,0.975987319447235,0.9607550286875182,0.9688232536333802,0.9740919340075458,0.9777956377112496,0.975987319447235],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680273558837,"sparkVersion":"3.1.2","uid":"cv_a067ce7197d6","paramMap":{"seed":-1191137437,"foldCol":"","numFolds":2,"estimatorParamMaps":[[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e969b654a565","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e969b654a565","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"seed":-1191137437,"foldCol":"","numFolds":3},"avgMetrics":[0.9854028531243721,0.9854028531243721,0.9854028531243721,0.9854028531243721,0.9824470341347978,0.9824470341347978,0.9824470341347978,0.9824470341347978,0.9800214319201661,0.9800214319201661,0.9800214319201661,0.9800214319201661,0.9755006362601298,0.9755006362601298,0.9755006362601298,0.9755006362601298,0.97550063626013,0.97550063626013,0.97550063626013,0.97550063626013],"persistSubModels":false} diff --git a/models/105/model/block/zingg.block/.part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet.crc b/models/105/model/block/zingg.block/.part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet.crc new file mode 100644 index 000000000..3d736d8b7 Binary files /dev/null and b/models/105/model/block/zingg.block/.part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet.crc differ diff --git a/models/105/model/block/zingg.block/part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet b/models/105/model/block/zingg.block/part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet new file mode 100644 index 000000000..7bca76bff Binary files /dev/null and b/models/105/model/block/zingg.block/part-00000-2243fcf0-f721-4bb7-aec9-4fe3ec19b6f3-c000.snappy.parquet differ diff --git a/models/105/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/105/model/classifier/best.model/bestModel/metadata/.part-00000.crc index c5428cdf0..7b0ac4abc 100644 Binary files a/models/105/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/105/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/metadata/part-00000 b/models/105/model/classifier/best.model/bestModel/metadata/part-00000 index 83f99a158..105a6d2eb 100644 --- a/models/105/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/105/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680103212598,"sparkVersion":"3.1.2","uid":"pipeline_d5e19e437257","paramMap":{"stageUids":["vecAssembler_fb083bc16c10","poly_f098446192f3","logreg_e337b472ede0"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680269354290,"sparkVersion":"3.1.2","uid":"pipeline_df09f889926e","paramMap":{"stageUids":["vecAssembler_193ca804b390","poly_6c20b808f7c7","logreg_3ee29c2329bb"]},"defaultParamMap":{}} diff --git a/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc new file mode 100644 index 000000000..7051aa784 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/_SUCCESS b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/part-00000 b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/part-00000 new file mode 100644 index 000000000..e6a132f6a --- /dev/null +++ b/models/105/model/classifier/best.model/bestModel/stages/0_vecAssembler_193ca804b390/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680269354382,"sparkVersion":"3.1.2","uid":"vecAssembler_193ca804b390","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14"]},"defaultParamMap":{"outputCol":"vecAssembler_193ca804b390__output","handleInvalid":"error"}} diff --git a/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc new file mode 100644 index 000000000..43e1d3b21 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/_SUCCESS b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/part-00000 b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/part-00000 new file mode 100644 index 000000000..1ecf898f0 --- /dev/null +++ b/models/105/model/classifier/best.model/bestModel/stages/1_poly_6c20b808f7c7/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680269354481,"sparkVersion":"3.1.2","uid":"poly_6c20b808f7c7","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_6c20b808f7c7__output","degree":2}} diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/._SUCCESS.crc b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/.part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet.crc b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/.part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet.crc new file mode 100644 index 000000000..9a23f71be Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/.part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/_SUCCESS b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet new file mode 100644 index 000000000..caeeaa7ee Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/data/part-00000-a76aba6f-ebf9-4fd1-a57f-7842555314b2-c000.snappy.parquet differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc new file mode 100644 index 000000000..147b876ed Binary files /dev/null and b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/_SUCCESS b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/part-00000 b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/part-00000 new file mode 100644 index 000000000..06cc510c5 --- /dev/null +++ b/models/105/model/classifier/best.model/bestModel/stages/2_logreg_3ee29c2329bb/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680269354572,"sparkVersion":"3.1.2","uid":"logreg_3ee29c2329bb","paramMap":{"fitIntercept":true,"probabilityCol":"z_probability","predictionCol":"z_prediction","maxIter":100,"labelCol":"z_isMatch","threshold":0.4,"regParam":1.0,"featuresCol":"z_feature"},"defaultParamMap":{"fitIntercept":true,"probabilityCol":"probability","maxBlockSizeInMB":0.0,"aggregationDepth":2,"standardization":true,"rawPredictionCol":"rawPrediction","tol":1.0E-6,"predictionCol":"prediction","labelCol":"label","maxIter":100,"elasticNetParam":0.0,"threshold":0.5,"regParam":0.0,"family":"auto","featuresCol":"features"}} diff --git a/models/105/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/105/model/classifier/best.model/estimator/metadata/.part-00000.crc index ef2917ba4..e0899922d 100644 Binary files a/models/105/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/105/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/estimator/metadata/part-00000 b/models/105/model/classifier/best.model/estimator/metadata/part-00000 index 4fe0a3bdb..4b0680967 100644 --- a/models/105/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/105/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1680103212029,"sparkVersion":"3.1.2","uid":"pipeline_d5e19e437257","paramMap":{"stageUids":["vecAssembler_fb083bc16c10","poly_f098446192f3","logreg_e337b472ede0"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680269353679,"sparkVersion":"3.1.2","uid":"pipeline_df09f889926e","paramMap":{"stageUids":["vecAssembler_193ca804b390","poly_6c20b808f7c7","logreg_3ee29c2329bb"]},"defaultParamMap":{}} diff --git a/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc new file mode 100644 index 000000000..6b0809c7c Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/_SUCCESS b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/part-00000 b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/part-00000 new file mode 100644 index 000000000..3fb70dd7e --- /dev/null +++ b/models/105/model/classifier/best.model/estimator/stages/0_vecAssembler_193ca804b390/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680269353845,"sparkVersion":"3.1.2","uid":"vecAssembler_193ca804b390","paramMap":{"outputCol":"z_featurevector","inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6","z_sim7","z_sim8","z_sim9","z_sim10","z_sim11","z_sim12","z_sim13","z_sim14"]},"defaultParamMap":{"outputCol":"vecAssembler_193ca804b390__output","handleInvalid":"error"}} diff --git a/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc new file mode 100644 index 000000000..66d449fbc Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/_SUCCESS b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/part-00000 b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/part-00000 new file mode 100644 index 000000000..d675b675e --- /dev/null +++ b/models/105/model/classifier/best.model/estimator/stages/1_poly_6c20b808f7c7/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680269354005,"sparkVersion":"3.1.2","uid":"poly_6c20b808f7c7","paramMap":{"outputCol":"z_feature","degree":3,"inputCol":"z_featurevector"},"defaultParamMap":{"outputCol":"poly_6c20b808f7c7__output","degree":2}} diff --git a/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/._SUCCESS.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc new file mode 100644 index 000000000..4f5c8f680 Binary files /dev/null and b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/_SUCCESS b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/part-00000 b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/part-00000 new file mode 100644 index 000000000..9a58f6d15 --- /dev/null +++ b/models/105/model/classifier/best.model/estimator/stages/2_logreg_3ee29c2329bb/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680269354171,"sparkVersion":"3.1.2","uid":"logreg_3ee29c2329bb","paramMap":{"fitIntercept":true,"probabilityCol":"z_probability","predictionCol":"z_prediction","labelCol":"z_isMatch","maxIter":100,"featuresCol":"z_feature"},"defaultParamMap":{"fitIntercept":true,"probabilityCol":"probability","maxBlockSizeInMB":0.0,"aggregationDepth":2,"standardization":true,"rawPredictionCol":"rawPrediction","tol":1.0E-6,"predictionCol":"prediction","labelCol":"label","maxIter":100,"elasticNetParam":0.0,"threshold":0.5,"regParam":0.0,"family":"auto","featuresCol":"features"}} diff --git a/models/105/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/105/model/classifier/best.model/evaluator/metadata/.part-00000.crc index 32117dc98..c17f37970 100644 Binary files a/models/105/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/105/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/evaluator/metadata/part-00000 b/models/105/model/classifier/best.model/evaluator/metadata/part-00000 index 73d5dde75..bbd677a1a 100644 --- a/models/105/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/105/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680103211804,"sparkVersion":"3.1.2","uid":"binEval_5c6fc84f8c25","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","rawPredictionCol":"rawPrediction","numBins":1000,"labelCol":"label"}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680269353481,"sparkVersion":"3.1.2","uid":"binEval_864de8ca72e5","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"labelCol":"label","rawPredictionCol":"rawPrediction","metricName":"areaUnderROC","numBins":1000}} diff --git a/models/105/model/classifier/best.model/metadata/.part-00000.crc b/models/105/model/classifier/best.model/metadata/.part-00000.crc index 2e19cb163..f5e0dd4b9 100644 Binary files a/models/105/model/classifier/best.model/metadata/.part-00000.crc and b/models/105/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/105/model/classifier/best.model/metadata/part-00000 b/models/105/model/classifier/best.model/metadata/part-00000 index aa2f284e4..d287ed743 100644 --- a/models/105/model/classifier/best.model/metadata/part-00000 +++ b/models/105/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680103211545,"sparkVersion":"3.1.2","uid":"cv_0e01e1a0519c","paramMap":{"foldCol":"","seed":-1191137437,"numFolds":2,"estimatorParamMaps":[[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_e337b472ede0","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_e337b472ede0","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"foldCol":"","seed":-1191137437,"numFolds":3},"avgMetrics":[0.9228946706887884,0.9228946706887884,0.9228946706887884,0.9228946706887884,0.9248177476118653,0.9248177476118653,0.9248177476118653,0.9248177476118653,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9278971845148316,0.9278971845148316,0.9278971845148316,0.9278971845148316],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680269353238,"sparkVersion":"3.1.2","uid":"cv_f0f6ab438491","paramMap":{"seed":-1191137437,"numFolds":2,"foldCol":"","estimatorParamMaps":[[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0E-4","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.001","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.01","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"0.1","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.55","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.4","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.45","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.5","isJson":"true"}],[{"parent":"logreg_3ee29c2329bb","name":"regParam","value":"1.0","isJson":"true"},{"parent":"logreg_3ee29c2329bb","name":"threshold","value":"0.55","isJson":"true"}]]},"defaultParamMap":{"seed":-1191137437,"numFolds":3,"foldCol":""},"avgMetrics":[0.9228946706887884,0.9228946706887884,0.9228946706887884,0.9228946706887884,0.9248177476118653,0.9248177476118653,0.9248177476118653,0.9248177476118653,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9234728506787331,0.9278971845148316,0.9278971845148316,0.9278971845148316,0.9278971845148316],"persistSubModels":false} diff --git a/models/106/model/block/zingg.block/.part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet.crc b/models/106/model/block/zingg.block/.part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet.crc new file mode 100644 index 000000000..968aa45bd Binary files /dev/null and b/models/106/model/block/zingg.block/.part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet.crc differ diff --git a/models/106/model/block/zingg.block/part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet b/models/106/model/block/zingg.block/part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet new file mode 100644 index 000000000..68910b144 Binary files /dev/null and b/models/106/model/block/zingg.block/part-00000-a6c686ce-9f4a-403b-b667-c1725e84d3d1-c000.snappy.parquet differ diff --git a/models/106/model/classifier/best.model/bestModel/metadata/.part-00000.crc b/models/106/model/classifier/best.model/bestModel/metadata/.part-00000.crc index e86a62f6c..a6a5a72ef 100644 Binary files a/models/106/model/classifier/best.model/bestModel/metadata/.part-00000.crc and b/models/106/model/classifier/best.model/bestModel/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/metadata/part-00000 b/models/106/model/classifier/best.model/bestModel/metadata/part-00000 index fe7fc0a38..34f15b0af 100644 --- a/models/106/model/classifier/best.model/bestModel/metadata/part-00000 +++ b/models/106/model/classifier/best.model/bestModel/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680102799008,"sparkVersion":"3.1.2","uid":"pipeline_a5bb1e22800d","paramMap":{"stageUids":["vecAssembler_88aad987ca1e","poly_03f11d620c16","logreg_cde97303433a"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.PipelineModel","timestamp":1680271468643,"sparkVersion":"3.1.2","uid":"pipeline_75d0f3475905","paramMap":{"stageUids":["vecAssembler_56b817e58881","poly_45ef98b49efc","logreg_21a0f8a48785"]},"defaultParamMap":{}} diff --git a/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc new file mode 100644 index 000000000..67710fff4 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/_SUCCESS b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/part-00000 b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/part-00000 new file mode 100644 index 000000000..8c4c0bc08 --- /dev/null +++ b/models/106/model/classifier/best.model/bestModel/stages/0_vecAssembler_56b817e58881/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680271468733,"sparkVersion":"3.1.2","uid":"vecAssembler_56b817e58881","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_56b817e58881__output"}} diff --git a/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc new file mode 100644 index 000000000..2ed79e0d4 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/_SUCCESS b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/part-00000 b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/part-00000 new file mode 100644 index 000000000..f2a817202 --- /dev/null +++ b/models/106/model/classifier/best.model/bestModel/stages/1_poly_45ef98b49efc/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680271468831,"sparkVersion":"3.1.2","uid":"poly_45ef98b49efc","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_45ef98b49efc__output"}} diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/._SUCCESS.crc b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/.part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet.crc b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/.part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet.crc new file mode 100644 index 000000000..5728a243e Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/.part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/_SUCCESS b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet similarity index 51% rename from models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet rename to models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet index 291cf3465..6716522d8 100644 Binary files a/models/104/model/classifier/best.model/bestModel/stages/2_logreg_bf272c896a01/data/part-00000-24d903ba-dca9-4462-a0e6-1e33eb38dee2-c000.snappy.parquet and b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/data/part-00000-76fb5a2b-9bd4-4a4d-99ba-dd65125908fc-c000.snappy.parquet differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc new file mode 100644 index 000000000..e416323bf Binary files /dev/null and b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/_SUCCESS b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/part-00000 b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/part-00000 new file mode 100644 index 000000000..b1d87c716 --- /dev/null +++ b/models/106/model/classifier/best.model/bestModel/stages/2_logreg_21a0f8a48785/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegressionModel","timestamp":1680271468922,"sparkVersion":"3.1.2","uid":"logreg_21a0f8a48785","paramMap":{"featuresCol":"z_feature","threshold":0.4,"labelCol":"z_isMatch","fitIntercept":true,"maxIter":100,"regParam":1.0E-4,"probabilityCol":"z_probability","predictionCol":"z_prediction"},"defaultParamMap":{"featuresCol":"features","standardization":true,"threshold":0.5,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"elasticNetParam":0.0,"aggregationDepth":2,"family":"auto","labelCol":"label","fitIntercept":true,"maxIter":100,"regParam":0.0,"tol":1.0E-6,"predictionCol":"prediction","probabilityCol":"probability"}} diff --git a/models/106/model/classifier/best.model/estimator/metadata/.part-00000.crc b/models/106/model/classifier/best.model/estimator/metadata/.part-00000.crc index 79b4bc9b2..63ac3cc25 100644 Binary files a/models/106/model/classifier/best.model/estimator/metadata/.part-00000.crc and b/models/106/model/classifier/best.model/estimator/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/estimator/metadata/part-00000 b/models/106/model/classifier/best.model/estimator/metadata/part-00000 index 7da2d7ab0..6fd0c4b7e 100644 --- a/models/106/model/classifier/best.model/estimator/metadata/part-00000 +++ b/models/106/model/classifier/best.model/estimator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.Pipeline","timestamp":1680102798435,"sparkVersion":"3.1.2","uid":"pipeline_a5bb1e22800d","paramMap":{"stageUids":["vecAssembler_88aad987ca1e","poly_03f11d620c16","logreg_cde97303433a"]},"defaultParamMap":{}} +{"class":"org.apache.spark.ml.Pipeline","timestamp":1680271468029,"sparkVersion":"3.1.2","uid":"pipeline_75d0f3475905","paramMap":{"stageUids":["vecAssembler_56b817e58881","poly_45ef98b49efc","logreg_21a0f8a48785"]},"defaultParamMap":{}} diff --git a/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc new file mode 100644 index 000000000..2a19c160b Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/_SUCCESS b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/part-00000 b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/part-00000 new file mode 100644 index 000000000..c10fcc970 --- /dev/null +++ b/models/106/model/classifier/best.model/estimator/stages/0_vecAssembler_56b817e58881/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.VectorAssembler","timestamp":1680271468223,"sparkVersion":"3.1.2","uid":"vecAssembler_56b817e58881","paramMap":{"inputCols":["z_sim0","z_sim1","z_sim2","z_sim3","z_sim4","z_sim5","z_sim6"],"outputCol":"z_featurevector"},"defaultParamMap":{"handleInvalid":"error","outputCol":"vecAssembler_56b817e58881__output"}} diff --git a/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc new file mode 100644 index 000000000..ca38ccefb Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/_SUCCESS b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/part-00000 b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/part-00000 new file mode 100644 index 000000000..166fe65e1 --- /dev/null +++ b/models/106/model/classifier/best.model/estimator/stages/1_poly_45ef98b49efc/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.feature.PolynomialExpansion","timestamp":1680271468390,"sparkVersion":"3.1.2","uid":"poly_45ef98b49efc","paramMap":{"inputCol":"z_featurevector","degree":3,"outputCol":"z_feature"},"defaultParamMap":{"degree":2,"outputCol":"poly_45ef98b49efc__output"}} diff --git a/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc new file mode 100644 index 000000000..3b7b04493 Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/._SUCCESS.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc new file mode 100644 index 000000000..df7fd9e32 Binary files /dev/null and b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/_SUCCESS b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/_SUCCESS new file mode 100644 index 000000000..e69de29bb diff --git a/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/part-00000 b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/part-00000 new file mode 100644 index 000000000..3a78f2f66 --- /dev/null +++ b/models/106/model/classifier/best.model/estimator/stages/2_logreg_21a0f8a48785/metadata/part-00000 @@ -0,0 +1 @@ +{"class":"org.apache.spark.ml.classification.LogisticRegression","timestamp":1680271468539,"sparkVersion":"3.1.2","uid":"logreg_21a0f8a48785","paramMap":{"featuresCol":"z_feature","fitIntercept":true,"labelCol":"z_isMatch","maxIter":100,"predictionCol":"z_prediction","probabilityCol":"z_probability"},"defaultParamMap":{"featuresCol":"features","standardization":true,"threshold":0.5,"rawPredictionCol":"rawPrediction","maxBlockSizeInMB":0.0,"elasticNetParam":0.0,"aggregationDepth":2,"family":"auto","labelCol":"label","fitIntercept":true,"maxIter":100,"regParam":0.0,"tol":1.0E-6,"predictionCol":"prediction","probabilityCol":"probability"}} diff --git a/models/106/model/classifier/best.model/evaluator/metadata/.part-00000.crc b/models/106/model/classifier/best.model/evaluator/metadata/.part-00000.crc index a260da726..1fc0bbd36 100644 Binary files a/models/106/model/classifier/best.model/evaluator/metadata/.part-00000.crc and b/models/106/model/classifier/best.model/evaluator/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/evaluator/metadata/part-00000 b/models/106/model/classifier/best.model/evaluator/metadata/part-00000 index a6df0e8c8..60113789f 100644 --- a/models/106/model/classifier/best.model/evaluator/metadata/part-00000 +++ b/models/106/model/classifier/best.model/evaluator/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680102798247,"sparkVersion":"3.1.2","uid":"binEval_6562d00c2e22","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"metricName":"areaUnderROC","rawPredictionCol":"rawPrediction","labelCol":"label","numBins":1000}} +{"class":"org.apache.spark.ml.evaluation.BinaryClassificationEvaluator","timestamp":1680271467869,"sparkVersion":"3.1.2","uid":"binEval_05f4ed020ba6","paramMap":{"labelCol":"z_isMatch"},"defaultParamMap":{"rawPredictionCol":"rawPrediction","metricName":"areaUnderROC","labelCol":"label","numBins":1000}} diff --git a/models/106/model/classifier/best.model/metadata/.part-00000.crc b/models/106/model/classifier/best.model/metadata/.part-00000.crc index 2abbdaa27..3d9006e76 100644 Binary files a/models/106/model/classifier/best.model/metadata/.part-00000.crc and b/models/106/model/classifier/best.model/metadata/.part-00000.crc differ diff --git a/models/106/model/classifier/best.model/metadata/part-00000 b/models/106/model/classifier/best.model/metadata/part-00000 index 3cb938796..01afe501e 100644 --- a/models/106/model/classifier/best.model/metadata/part-00000 +++ b/models/106/model/classifier/best.model/metadata/part-00000 @@ -1 +1 @@ -{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680102797916,"sparkVersion":"3.1.2","uid":"cv_b7d77c103e11","paramMap":{"numFolds":2,"foldCol":"","seed":-1191137437,"estimatorParamMaps":[[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_cde97303433a","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_cde97303433a","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"foldCol":"","seed":-1191137437},"avgMetrics":[0.6961344537815126,0.6961344537815126,0.6961344537815126,0.6961344537815126,0.6586344537815125,0.6586344537815125,0.6586344537815125,0.6586344537815125,0.6294327731092437,0.6294327731092437,0.6294327731092437,0.6294327731092437,0.5751260504201681,0.5751260504201681,0.5751260504201681,0.5751260504201681,0.6637394957983194,0.6637394957983194,0.6637394957983194,0.6637394957983194],"persistSubModels":false} +{"class":"org.apache.spark.ml.tuning.CrossValidatorModel","timestamp":1680271467550,"sparkVersion":"3.1.2","uid":"cv_6a84caf3dd16","paramMap":{"numFolds":2,"foldCol":"","seed":-1191137437,"estimatorParamMaps":[[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0E-4","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.001","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.01","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"0.1","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.4","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.45","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.5","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0","isJson":"true"}],[{"parent":"logreg_21a0f8a48785","name":"threshold","value":"0.55","isJson":"true"},{"parent":"logreg_21a0f8a48785","name":"regParam","value":"1.0","isJson":"true"}]]},"defaultParamMap":{"numFolds":3,"foldCol":"","seed":-1191137437},"avgMetrics":[0.6961344537815126,0.6961344537815126,0.6961344537815126,0.6961344537815126,0.6586344537815125,0.6586344537815125,0.6586344537815125,0.6586344537815125,0.6294327731092437,0.6294327731092437,0.6294327731092437,0.6294327731092437,0.5751260504201681,0.5751260504201681,0.5751260504201681,0.5751260504201681,0.6637394957983194,0.6637394957983194,0.6637394957983194,0.6637394957983194],"persistSubModels":false} diff --git a/python/zingg/pipes.py b/python/zingg/pipes.py index 629d1e5ed..8b671c8f7 100644 --- a/python/zingg/pipes.py +++ b/python/zingg/pipes.py @@ -79,8 +79,8 @@ def __init__(self, name, location = None, schema = None): Pipe.addProperty(self, FilePipe.LOCATION, location) if(schema != None): #df = spark.read.format(JPipe.FORMAT_CSV).schema(schema).load(location) - s = JStructType.fromDDL(schema) - Pipe.setSchema(self, s.json()) + #s = JStructType.fromDDL(schema) + Pipe.setSchema(self, schema) print("set schema ") def setDelimiter(self, delimiter): diff --git a/test/InMemPipeTest.py b/test/InMemPipeTest.py index bb337b1de..e313930b6 100644 --- a/test/InMemPipeTest.py +++ b/test/InMemPipeTest.py @@ -11,7 +11,7 @@ description = FieldDefinition("description", "string", MatchType.TEXT) description.setStopWords("examples/amazon-google/stopWords.csv") manufacturer = FieldDefinition("manufacturer","string", MatchType.FUZZY) -price = FieldDefinition("price", "string", MatchType.FUZZY) +price = FieldDefinition("price", "double", MatchType.FUZZY) fieldDefs = [id, title, description, manufacturer, price] args.setFieldDefinition(fieldDefs) @@ -34,16 +34,16 @@ ,StructField("title", StringType(), True)\ ,StructField("description", StringType(), True)\ ,StructField("manufacturer", StringType(), True)\ - ,StructField("price", StringType(), True)]) + ,StructField("price", DoubleType(), True)]) #gDF = pandas.read_csv("~/zingg/examples/amazon-google/Amazon.csv", encoding="iso-8859-1") #amzDF = pandas.DataFrame() #gDF=pandas.DataFrame() inputPipeAmazon=InMemoryPipe("amz") #inputPipeAmazon.setSchema("id string, title string, description string, manufacturer string, price string") -inputPipeAmazon.setDataset(spark.read.format("csv").schema(schema).load("../zingg//examples/amazon-google/Amazon.csv")) +inputPipeAmazon.setDataset(spark.read.format("csv").schema(schema).load("examples/amazon-google/Amazon.csv")) inputPipeGoogle=InMemoryPipe("google") -inputPipeGoogle.setDataset(spark.read.format("csv").schema(schema).load("../zingg/examples/amazon-google/GoogleProducts.csv")) +inputPipeGoogle.setDataset(spark.read.format("csv").schema(schema).load("examples/amazon-google/GoogleProducts.csv")) args.setData(inputPipeAmazon,inputPipeGoogle) @@ -52,7 +52,7 @@ args.setOutput(outputPipe) -options = ClientOptions([ClientOptions.PHASE,"link"]) +options = ClientOptions([ClientOptions.PHASE,"match"]) #Zingg execution for the given phase zingg = Zingg(args, options)