def testIsolationForestModelGiveDifferentPredictionsOnDifferentRecords(prostateDataset):
[trainingDataset, testingDataset] = prostateDataset.randomSplit([0.9, 0.1], 42)
algo = H2OIsolationForest(seed=1)
model = algo.fit(trainingDataset)
result = model.transform(testingDataset)
predictions = result.select("prediction").take(2)
assert(predictions[0][0] != predictions[1][0])
def testExplicitValidationFrameOnIsolationForest(spark, prostateDataset):
validationDatasetPath = "file://" + os.path.abspath("../examples/smalldata/prostate/prostate_anomaly_validation.csv")
validatationDataset = spark.read.csv(validationDatasetPath, header=True, inferSchema=True)
algo = H2OIsolationForest(seed=1, validationDataFrame=validatationDataset, validationLabelCol="isAnomaly")
model = algo.fit(prostateDataset)
metrics = model.getValidationMetrics()
assert(metrics['AUC'] > 0.85)
assert(metrics['Logloss'] < 1.0)
def testPipelineSerialization(prostateDataset):
algo = H2OIsolationForest(seed=1)
pipeline = Pipeline(stages=[algo])
pipeline.write().overwrite().save("file://" + os.path.abspath("build/isolation_forest_pipeline"))
loadedPipeline = Pipeline.load("file://" + os.path.abspath("build/isolation_forest_pipeline"))
model = loadedPipeline.fit(prostateDataset)
expected = model.transform(prostateDataset)
model.write().overwrite().save("file://" + os.path.abspath("build/isolation_forest_pipeline_model"))
loadedModel = PipelineModel.load("file://" + os.path.abspath("build/isolation_forest_pipeline_model"))
result = loadedModel.transform(prostateDataset)
unit_test_utils.assert_data_frames_are_identical(expected, result)
def testIsolationForestParameters(prostateDataset):
features = ['AGE', 'RACE', 'DPROS', 'DCAPS', 'PSA']
algorithm = H2OIsolationForest(seed=1, sampleRate=0.5, featuresCols=features)
model = algorithm.fit(prostateDataset)
compareParameterValues(algorithm, model)