def testGetGridModels(prostateDataset):
grid = H2OGridSearch(labelCol="AGE", hyperParameters={"seed": [1, 2, 3]}, splitRatio=0.8, algo=H2OGBM(),
strategy="RandomDiscrete", maxModels=3, maxRuntimeSecs=60, selectBestModelBy="RMSE")
grid.fit(prostateDataset)
models = grid.getGridModels()
assert len(models) == 3
def testGetGridModelsMetrics(prostateDataset):
grid = H2OGridSearch(labelCol="AGE", hyperParameters={"seed": [1, 2, 3]}, splitRatio=0.8, algo=H2OGBM(),
strategy="RandomDiscrete", maxModels=3, maxRuntimeSecs=60, selectBestModelBy="RMSE")
grid.fit(prostateDataset)
metrics = grid.getGridModelsMetrics()
assert metrics.count() == 3
assert metrics.columns == ['MOJO Model ID', 'MSE', 'MeanResidualDeviance', 'R2', 'RMSE']
metrics.collect() # try materializing
def testGetGridModelsNoParams(prostateDataset):
grid = H2OGridSearch(labelCol="AGE", splitRatio=0.8, algo=H2OGBM(),
strategy="RandomDiscrete", maxModels=3, maxRuntimeSecs=60, selectBestModelBy="RMSE")
grid.fit(prostateDataset)
params = grid.getGridModelsParams()
assert params.count() == 1
assert params.columns == ['MOJO Model ID']
params.collect() # try materializing
def testGetAlgoViaSetter():
# SW-2276, 3rd call of getAlgo failed
grid = H2OGridSearch(hyperParameters={"seed": [1, 2, 3]},
strategy="RandomDiscrete",
maxModels=3,
maxRuntimeSecs=60,
selectBestModelBy="RMSE")
grid.setAlgo(H2OGBM().setNtrees(100).setLabelCol("AGE").setSplitRatio(0.8))
grid.getAlgo()
grid.getAlgo()
assert grid.getAlgo().getNtrees() == 100
def testGetGridModelsParams(prostateDataset):
grid = H2OGridSearch(hyperParameters={"seed": [1, 2, 3]},
algo=H2OGBM(splitRatio=0.8, labelCol="AGE"),
strategy="RandomDiscrete",
maxModels=3,
maxRuntimeSecs=60,
selectBestModelBy="RMSE")
grid.fit(prostateDataset)
params = grid.getGridModelsParams()
assert params.count() == 3
assert params.columns == ['MOJO Model ID', 'seed']
params.collect() # try materializing
def testGetAlgoViaConstructor():
# SW-2276, 3rd call of getAlgo failed
grid = H2OGridSearch(hyperParameters={"seed": [1, 2, 3]},
algo=H2OGBM(labelCol="AGE",
ntrees=100,
splitRatio=0.8),
strategy="RandomDiscrete",
maxModels=3,
maxRuntimeSecs=60,
selectBestModelBy="RMSE")
grid.getAlgo()
grid.getAlgo()
assert grid.getAlgo().getNtrees() == 100
def gridSearchTester(algo, prostateDataset):
grid = H2OGridSearch(labelCol="AGE", hyperParameters={"seed": [1, 2, 3]}, splitRatio=0.8, algo=algo,
strategy="RandomDiscrete", maxModels=3, maxRuntimeSecs=60, selectBestModelBy="RMSE")
pipeline = Pipeline(stages=[grid])
pipeline.write().overwrite().save("file://" + os.path.abspath("build/grid_pipeline"))
loadedPipeline = Pipeline.load("file://" + os.path.abspath("build/grid_pipeline"))
model = loadedPipeline.fit(prostateDataset)
model.write().overwrite().save("file://" + os.path.abspath("build/grid_pipeline_model"))
loadedModel = PipelineModel.load("file://" + os.path.abspath("build/grid_pipeline_model"))
loadedModel.transform(prostateDataset).count()
def testParams():
grid = H2OGridSearch(featuresCols=[],
algo=None,
splitRatio=1.0,
hyperParameters={},
labelCol="label",
weightCol=None,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
strategy="Cartesian",
maxRuntimeSecs=0.0,
maxModels=0,
seed=-1,
stoppingRounds=0,
stoppingTolerance=0.001,
stoppingMetric="AUTO",
nfolds=0,
selectBestModelBy="AUTO",
selectBestModelDecreasing=True,
foldCol=None,
convertUnknownCategoricalLevelsToNa=True,
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
convertInvalidNumbersToNa=False)
assert grid.getFeaturesCols() == []
assert grid.getSplitRatio() == 1.0
assert grid.getHyperParameters() == {}
assert grid.getLabelCol() == "label"
assert grid.getWeightCol() == None
assert grid.getAllStringColumnsToCategorical() == True
assert grid.getColumnsToCategorical() == []
assert grid.getStrategy() == "Cartesian"
assert grid.getMaxRuntimeSecs() == 0.0
assert grid.getMaxModels() == 0
assert grid.getSeed() == -1
assert grid.getStoppingRounds() == 0
assert grid.getStoppingTolerance() == 0.001
assert grid.getStoppingMetric() == "AUTO"
assert grid.getNfolds() == 0
assert grid.getSelectBestModelBy() == "AUTO"
assert grid.getSelectBestModelDecreasing() == True
assert grid.getFoldCol() == None
assert grid.getConvertUnknownCategoricalLevelsToNa() == True
assert grid.getPredictionCol() == "prediction"
assert grid.getDetailedPredictionCol() == "detailed_prediction"
assert grid.getWithDetailedPredictionCol() == False
assert grid.getConvertInvalidNumbersToNa() == False
