Merge pull request #4123 from h2oai/ntrees_actual_test_fix

PUBDEV-6754 test fix - missing seed

h2o-py/tests/testdir_algos/sharedtree/pyunit_PUBDEV-6754_ntrees_actual_for_tree_algos.py

@@ -13,8 +13,8 @@ def tree_algos_ntree_actual():
   prostate[1] = prostate[1].asfactor()
   prostate.summary()
   ntrees_original = 1000
-
-  prostate_gbm = H2OGradientBoostingEstimator(nfolds=5,ntrees=ntrees_original, distribution="bernoulli", stopping_metric="MSE", stopping_tolerance=0.01, stopping_rounds=5)
+  
+  prostate_gbm = H2OGradientBoostingEstimator(nfolds=5,ntrees=ntrees_original, distribution="bernoulli", stopping_metric="MSE", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
   prostate_gbm.train(x=list(range(2,9)), y=1, training_frame=prostate)
 
   print("\n")
@@ -27,7 +27,7 @@ def tree_algos_ntree_actual():
   assert prostate_gbm.ntrees_actual() == prostate_gbm._model_json['output']['model_summary']['number_of_trees'][0] == prostate_gbm.summary()['number_of_trees'][0]
 
 
-  prostate_if = H2OIsolationForestEstimator(sample_rate = 0.1, max_depth = 20, ntrees=ntrees_original, stopping_metric="anomalyscore", stopping_tolerance=0.01, stopping_rounds=5)
+  prostate_if = H2OIsolationForestEstimator(sample_rate = 0.1, max_depth = 20, ntrees=ntrees_original, stopping_metric="anomalyscore", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
   prostate_if.train(x=list(range(2,9)), y=1, training_frame=prostate)
 
   print("\n")
@@ -39,7 +39,7 @@ def tree_algos_ntree_actual():
   assert prostate_if.ntrees_actual() < ntrees_original
   assert prostate_if.ntrees_actual() == prostate_if._model_json['output']['model_summary']['number_of_trees'][0] == prostate_if.summary()['number_of_trees'][0]
 
-  prostate_drf = H2ORandomForestEstimator(ntrees=ntrees_original, max_depth=20, min_rows=10, stopping_metric="auc", stopping_tolerance=0.01, stopping_rounds=5)
+  prostate_drf = H2ORandomForestEstimator(ntrees=ntrees_original, max_depth=20, min_rows=10, stopping_metric="auc", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
   prostate_drf.train(x=list(range(2,9)), y=1, training_frame=prostate)
 
   print("\n")

h2o-r/tests/testdir_algos/sharedtree/runit_PUBDEV-6754_ntrees_actual_for_tree_algos.R

@@ -21,7 +21,7 @@ test.tree_algos.bernoulli <- function() {
   # Train H2O GBM Model:
   ntrees <- 1000
   Log.info(paste("H2O GBM with parameters:\nnfolds = 5, distribution = 'bernoulli', ntrees = ", ntrees, ", stopping_metric=\"MSE\", stopping_tolerance=0.01, stopping_rounds=5\n", sep = ""))
-  prostate_gbm.h2o <- h2o.gbm(x = 3:9, y = "CAPSULE", training_frame = prostate.hex, nfolds = 5, distribution = "bernoulli", ntrees = ntrees, stopping_metric="MSE", stopping_tolerance=0.01, stopping_rounds=5)
+  prostate_gbm.h2o <- h2o.gbm(x = 3:9, y = "CAPSULE", training_frame = prostate.hex, nfolds = 5, distribution = "bernoulli", ntrees = ntrees, stopping_metric="MSE", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
 
   Log.info("GBM Model: number of trees set by user before building the model is:"); print(ntrees)
   Log.info("GBM Model: number of trees built with early-stopping is:"); print(h2o.get_ntrees_actual(prostate_gbm.h2o))
@@ -31,7 +31,7 @@ test.tree_algos.bernoulli <- function() {
 
   # Train H2O Isolation Forest Model:
   Log.info(paste("H2O Isolation Forest with parameters:\nsample_rate = 0.1, max_depth = 20, ntrees = ", ntrees, ", stopping_metric=\"AUTO\", stopping_tolerance=0.01, stopping_rounds=5\n", sep = ""))
-  prostate_if.h2o <- h2o.isolationForest(sample_rate = 0.1, max_depth = 20, training_frame = prostate.hex, ntrees=ntrees, stopping_metric="AUTO", stopping_tolerance=0.01, stopping_rounds=5)
+  prostate_if.h2o <- h2o.isolationForest(sample_rate = 0.1, max_depth = 20, training_frame = prostate.hex, ntrees=ntrees, stopping_metric="AUTO", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
 
   Log.info("Isolation Forest Model: number of trees set by user before building the model is:"); print(ntrees)
   Log.info("Isolation Forest Model: number of trees built with early-stopping is:"); print(h2o.get_ntrees_actual(prostate_if.h2o))
@@ -41,7 +41,7 @@ test.tree_algos.bernoulli <- function() {
 
   # Train H2O Random Forest Model:
   Log.info(paste("H2O Random Forest with parameters:\nx = 1:4, y = 5,max_depth=20, min_rows=10, ntrees = ", ntrees, ", stopping_metric=\"AUTO\", stopping_tolerance=0.01, stopping_rounds=5\n", sep = ""))
-  prostate_rf.h2o <- h2o.randomForest(x = 1:4, y = 5, ntrees=ntrees, max_depth=20, min_rows=10, training_frame = prostate.hex, stopping_metric="AUTO", stopping_tolerance=0.01, stopping_rounds=5)
+  prostate_rf.h2o <- h2o.randomForest(x = 1:4, y = 5, ntrees=ntrees, max_depth=20, min_rows=10, training_frame = prostate.hex, stopping_metric="AUTO", stopping_tolerance=0.01, stopping_rounds=5, seed=1)
 
   Log.info("Random Forest Model: number of trees set by user before building the model is:"); print(ntrees)
   Log.info("Random Forest Model: number of trees built with early-stopping is:"); print(h2o.get_ntrees_actual(prostate_rf.h2o))