def testParams():
automl = H2OAutoML(featuresCols=[],
labelCol="label",
allStringColumnsToCategorical=True,
columnsToCategorical=[],
splitRatio=1.0,
foldCol=None,
weightCol=None,
ignoredCols=[],
includeAlgos=["XGbooST"],
excludeAlgos=["DRF", "DeePLeArNING"],
projectName="test",
maxRuntimeSecs=3600.0,
stoppingRounds=3,
stoppingTolerance=0.001,
stoppingMetric="AUTO",
nfolds=5,
convertUnknownCategoricalLevelsToNa=True,
seed=-1,
sortMetric="AUTO",
balanceClasses=False,
classSamplingFactors=None,
maxAfterBalanceSize=5.0,
keepCrossValidationPredictions=True,
keepCrossValidationModels=True,
maxModels=0,
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
convertInvalidNumbersToNa=False)
assert automl.getFeaturesCols() == []
assert automl.getLabelCol() == "label"
assert automl.getAllStringColumnsToCategorical() == True
assert automl.getColumnsToCategorical() == []
assert automl.getSplitRatio() == 1.0
assert automl.getFoldCol() == None
assert automl.getWeightCol() == None
assert automl.getIgnoredCols() == []
assert automl.getIncludeAlgos() == ["XGBoost"]
assert automl.getExcludeAlgos() == ["DRF", "DeepLearning"]
assert automl.getProjectName() == "test"
assert automl.getMaxRuntimeSecs() == 3600.0
assert automl.getStoppingRounds() == 3
assert automl.getStoppingTolerance() == 0.001
assert automl.getStoppingMetric() == "AUTO"
assert automl.getNfolds() == 5
assert automl.getConvertUnknownCategoricalLevelsToNa() == True
assert automl.getSeed() == -1
assert automl.getSortMetric() == "AUTO"
assert automl.getBalanceClasses() == False
assert automl.getClassSamplingFactors() == None
assert automl.getMaxAfterBalanceSize() == 5.0
assert automl.getKeepCrossValidationPredictions() == True
assert automl.getKeepCrossValidationModels() == True
assert automl.getMaxModels() == 0
assert automl.getPredictionCol() == "prediction"
assert automl.getDetailedPredictionCol() == "detailed_prediction"
assert automl.getWithDetailedPredictionCol() == False
assert automl.getConvertInvalidNumbersToNa() == False
def h2o_automl(df, label, columns, **kargs):
H2OContext.getOrCreate(Spark.instance.spark)
df_sti = string_to_index(df, input_cols=label)
df_va = vector_assembler(df_sti, input_cols=columns)
automl = H2OAutoML(convertUnknownCategoricalLevelsToNa=True,
maxRuntimeSecs=60, # 1 minutes
seed=1,
maxModels=3,
labelCol=label + "_index",
**kargs)
model = automl.fit(df_va)
df_raw = model.transform(df_va)
df_pred = df_raw.withColumn("prediction", when(df_raw.prediction_output["value"] > 0.5, 1.0).otherwise(0.0))
return df_pred, model
stopWords=["the", "a", "", "in", "on", "at", "as", "not", "for"],
caseSensitive=False)
## Hash the words
hashingTF = HashingTF(inputCol=stopWordsRemover.getOutputCol(),
outputCol="wordToIndex",
numFeatures=1 << 10)
## Create inverse document frequencies model
idf = IDF(inputCol=hashingTF.getOutputCol(),
outputCol="tf_idf",
minDocFreq=4)
## Create H2OAutoML model
automl = H2OAutoML(convertUnknownCategoricalLevelsToNa=False,
seed=1,
maxRuntimeSecs=300, # 5 minutes
predictionCol="label")
## Remove all helper columns
colPruner = ColumnPruner(columns=[idf.getOutputCol(), hashingTF.getOutputCol(), stopWordsRemover.getOutputCol(), tokenizer.getOutputCol()])
## Create the pipeline by defining all the stages
pipeline = Pipeline(stages=[tokenizer, stopWordsRemover, hashingTF, idf, automl, colPruner])
## Train the pipeline model
data = load()
model = pipeline.fit(data)
##
## Make predictions on unlabeled data
## Spam detector
featuresCols=[idf.getOutputCol()],
predictionCol="label")
elif algo == "dl":
## Create H2ODeepLearning model
algoStage = H2ODeepLearning(epochs=10,
seed=1,
l1=0.001,
l2=0.0,
hidden=[200, 200],
featuresCols=[idf.getOutputCol()],
predictionCol="label")
elif algo == "automl":
## Create H2OAutoML model
algoStage = H2OAutoML(
convertUnknownCategoricalLevelsToNa=True,
maxRuntimeSecs=60, # 1 minutes
seed=1,
predictionCol="label")
## Remove all helper columns
colPruner = ColumnPruner(columns=[
idf.getOutputCol(),
hashingTF.getOutputCol(),
stopWordsRemover.getOutputCol(),
tokenizer.getOutputCol()
])
## Create the pipeline by defining all the stages
pipeline = Pipeline(
stages=[tokenizer, stopWordsRemover, hashingTF, idf, algoStage, colPruner])
def getAlgorithmForGetLeaderboardTesting():
automl = H2OAutoML(labelCol="CAPSULE", ignoredCols=["ID"])
automl.setExcludeAlgos(["GLM"])
automl.setMaxModels(5)
automl.setSortMetric("AUC")
return automl
gbm = H2OGBM(splitRatio=0.8,
seed=1,
featuresCols=[idf.getOutputCol()],
labelCol="label")
dl = H2ODeepLearning(epochs=10,
seed=1,
l1=0.001,
l2=0.0,
hidden=[200, 200],
featuresCols=[idf.getOutputCol()],
labelCol="label")
automl = H2OAutoML(
convertUnknownCategoricalLevelsToNa=True,
maxRuntimeSecs=60 * 100, # 100 minutes
maxModels=10,
seed=1,
labelCol="label")
xgboost = H2OXGBoost(convertUnknownCategoricalLevelsToNa=True,
featuresCols=[idf.getOutputCol()],
labelCol="label")
data = load()
def trainPipelineModel(idf, hashingTF, stopWordsRemover, tokenizer, algoStage,
data):
## Remove all helper columns
colPruner = ColumnPruner(columns=[
idf.getOutputCol(),