-
Notifications
You must be signed in to change notification settings - Fork 0
/
PredictiveRegressionModel.py
180 lines (146 loc) · 8.6 KB
/
PredictiveRegressionModel.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
from pyspark.ml.regression import LinearRegression, RandomForestRegressor, GBTRegressor
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from PredictionAlgorithms.PredictiveUtilities import PredictiveUtilities
from PredictionAlgorithms.PredictiveEvaluation import PredictiveEvaluation
from PredictionAlgorithms.PredictiveConstants import PredictiveConstants
spark = \
SparkSession.builder.appName('predictive_Analysis').master('local[*]').getOrCreate()
spark.sparkContext.setLogLevel('ERROR')
'''
trainDataRation = ration of training data, take input from the user
learningRate = learning rate applied on the model, take input from the user
dataset_add = dataset address, from the user
feature_colm = column as a features is taken from the user
relation_list = relationship list of each column needed to be applied
relation = whether it is linear relation or non linear taken from the user end
'''
class PredictiveRegressionModel(PredictiveEvaluation):
def __init__(self, trainDataRatio, dataset_add, feature_colm, label_colm, relation_list,
relation, userId, locationAddress, algoName, modelSheetName,spark):
self.trainDataRatio = trainDataRatio
self.datasetAdd = dataset_add
self.featuresColmList = feature_colm
self.labelColmList = label_colm
self.relationshipList = relation_list
self.relation = relation
self.userId = userId
self.locationAddress = locationAddress
self.algoName = algoName
self.modelSheetName = PredictiveConstants.PREDICTION_ + modelSheetName
# self.spark = spark
# only for etlpart of the dataset
# PredictiveUtilities = PredictiveUtilities()
ETLOnDatasetStats = \
PredictiveUtilities.ETLOnDataset(datasetAdd=self.datasetAdd,
featuresColmList=self.featuresColmList,
labelColmList=self.labelColmList,
relationshipList=self.relationshipList,
relation=self.relation,
trainDataRatio=self.trainDataRatio,
spark=spark,
userId=userId)
self.dataset = ETLOnDatasetStats.get(PredictiveConstants.DATASET)
self.featuresColm = ETLOnDatasetStats.get(PredictiveConstants.FEATURESCOLM)
self.labelColm = ETLOnDatasetStats.get(PredictiveConstants.LABELCOLM)
self.trainData = ETLOnDatasetStats.get(PredictiveConstants.TRAINDATA)
self.testData = ETLOnDatasetStats.get(PredictiveConstants.TESTDATA)
self.idNameFeaturesOrdered = ETLOnDatasetStats.get(PredictiveConstants.IDNAMEFEATURESORDERED)
def linearModel(self):
linearRegressionModelfit = \
LinearRegression(featuresCol=self.featuresColm, labelCol=self.labelColm,
predictionCol=self.modelSheetName)
regressor = linearRegressionModelfit.fit(self.trainData)
regressionStat = self.regressionModelEvaluation(regressor=regressor, spark=spark)
# persisting the model
modelName = "linearRegressionModel"
extention = ".parquet"
modelStorageLocation = self.locationAddress + self.userId.upper() + modelName.upper() + extention
regressor.write().overwrite().save(modelStorageLocation)
regressionStat["modelPersistLocation"] = {"modelName": modelName,
PredictiveConstants.MODELSTORAGELOCATION: modelStorageLocation}
return regressionStat
def ridgeLassoModel(self, regParam):
regParam = 0.05 if regParam == None else float(regParam)
elasticNetPara = 1 if self.algoName == PredictiveConstants.LASSO_REG else 0
ridgeLassoModelFit = \
LinearRegression(featuresCol=self.featuresColm,
labelCol=self.labelColm,
elasticNetParam=elasticNetPara,
regParam=regParam,
predictionCol=self.modelSheetName)
regressor = ridgeLassoModelFit.fit(self.trainData)
regressionStat = self.regressionModelEvaluation(regressor=regressor, spark=spark)
# persisting model
modelName = "lassoRegressionModel" if self.algoName == PredictiveConstants.LASSO_REG \
else "ridgeRegressionModel"
extention = ".parquet"
modelStorageLocation = self.locationAddress + self.userId.upper() + modelName.upper() + extention
regressor.write().overwrite().save(modelStorageLocation)
regressionStat["modelPersistLocation"] = {"modelName": modelName,
"modelStorageLocation": modelStorageLocation}
return regressionStat
# for future
def randomForestRegressorModel(self):
randomForestRegressorModelFit = \
RandomForestRegressor(labelCol=self.labelColm,
featuresCol=self.featuresColm,
numTrees=10,predictionCol=self.modelSheetName)
regressor = randomForestRegressorModelFit.fit(self.trainData)
# predictionData = regressor.transform(self.testData)
regressionStat = self.randomGradientRegressionModelEvaluation(regressor=regressor)
# persisting model
modelName = "randomForestModel"
extention = ".parquet"
modelStorageLocation = self.locationAddress + self.userId.upper() + modelName.upper() + extention
regressor.write().overwrite().save(modelStorageLocation)
regressionStat["modelPersistLocation"] = {"modelName": modelName,
"modelStorageLocation": modelStorageLocation}
return regressionStat
def gradientBoostRegressorModel(self):
gradientBoostRegressorModelFit = \
GBTRegressor(labelCol=self.labelColm,
featuresCol=self.featuresColm,
predictionCol=self.modelSheetName)
regressor = gradientBoostRegressorModelFit.fit(self.trainData)
# predictionData = regressor.transform(self.testData)
regressionStat = self.randomGradientRegressionModelEvaluation(regressor=regressor)
# persisting model
modelName = "gradientBoostModel"
extention = ".parquet"
modelStorageLocation = self.locationAddress + self.userId.upper() + modelName.upper() + extention
regressor.write().overwrite().save(modelStorageLocation)
regressionStat["modelPersistLocation"] = {"modelName": modelName,
"modelStorageLocation": modelStorageLocation}
return regressionStat
# reference for the future development.
"""
randomForestModelFit = randomForestModel.fit(dataset)
predictionData = randomForestModelFit.transform(dataset)
numericalFeatures.append("prediction")
predictionData.select(numericalFeatures).show()
from pyspark.ml.evaluation import RegressionEvaluator
metricsList = ['r2', 'rmse', 'mse', 'mae']
testDataMetrics = {}
for metric in metricsList:
evaluator = RegressionEvaluator(labelCol=label, predictionCol="prediction", metricName=metric)
metricValue = evaluator.evaluate(predictionData)
testDataMetrics[metric] = metricValue
print('testDataMetrics :', testDataMetrics)
from pyspark.ml.regression import GBTRegressor
gradientBoostingmodel = GBTRegressor(labelCol=label, featuresCol='features', maxIter=10)
gradientBoostFittingTrainingData = gradientBoostingmodel.fit(dataset)
gBPredictionData = gradientBoostFittingTrainingData.transform(dataset)
numericalFeatures.append(label)
gBPredictionData.select(numericalFeatures).show()
metricsList = ['r2', 'rmse', 'mse', 'mae']
testDataMetrics = {}
for metric in metricsList:
evaluator = RegressionEvaluator(labelCol=label, predictionCol="prediction", metricName=metric)
metricValue = evaluator.evaluate(gBPredictionData)
testDataMetrics[metric] = metricValue
print('testDataMetrics :', testDataMetrics)
predictionData.select(numericalFeatures).write.csv("/home/fidel/Downloads/randomForestPredictionArushiDataFinal.csv",header=True)
gBPredictionData.select(numericalFeatures).write.csv("/home/fidel/Downloads/gradientBoostingArushiDataset.csv",header=True)
"""
# return metric