def build_auto_h2o(regressor, name):
transformer = ColumnTransformer(
[(column, CategoricalDomain(), [column])
for column in ["cylinders", "model_year", "origin"]] +
[(column, ContinuousDomain(), [column]) for column in
["displacement", "horsepower", "weight", "acceleration"]])
pipeline = PMMLPipeline([("transformer", transformer),
("uploader",
H2OFrameCreator(column_names=[
"cylinders", "model_year", "origin",
"displacement", "horsepower", "weight",
"acceleration"
],
column_types=[
"enum", "enum", "enum",
"numeric", "numeric",
"numeric", "numeric"
])), ("regressor", regressor)])
pipeline.fit(auto_X, H2OFrame(auto_y.to_frame()))
pipeline.verify(auto_X.sample(frac=0.05, random_state=13))
regressor = pipeline._final_estimator
store_mojo(regressor, name + ".zip")
store_pkl(pipeline, name + ".pkl")
mpg = pipeline.predict(auto_X)
mpg.set_names(["mpg"])
store_csv(mpg.as_data_frame(), name + ".csv")
def build_audit_h2o(classifier, name):
mapper = DataFrameMapper(
[([column], ContinuousDomain()) for column in ["Age", "Hours", "Income"]] +
[([column], CategoricalDomain()) for column in ["Employment", "Education", "Marital", "Occupation", "Gender", "Deductions"]]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("uploader", H2OFrameCreator()),
("classifier", classifier)
])
pipeline.fit(audit_X, H2OFrame(audit_y.to_frame(), column_types = ["categorical"]))
pipeline.verify(audit_X.sample(frac = 0.05, random_state = 13))
classifier = pipeline._final_estimator
store_mojo(classifier, name)
store_pkl(pipeline, name)
adjusted = pipeline.predict(audit_X)
adjusted.set_names(["h2o(Adjusted)", "probability(0)", "probability(1)"])
store_csv(adjusted.as_data_frame(), name)
("Income", ContinuousDomain()),
(["Hours", "Income"],
Alias(ExpressionTransformer("X[1] / (X[0] * 52)"),
"Hourly_Income"))])
classifier = H2ORandomForestEstimator(ntrees=17)
predict_proba_transformer = Pipeline([
("expression", ExpressionTransformer("X[1]")),
("cut",
Alias(CutTransformer(bins=[0.0, 0.75, 0.90, 1.0],
labels=["no", "maybe", "yes"]),
"Decision",
prefit=True))
])
pipeline = PMMLPipeline([("local_mapper", mapper),
("uploader", H2OFrameCreator()),
("remote_classifier", classifier)],
predict_proba_transformer=predict_proba_transformer)
pipeline.fit(audit_X, H2OFrame(audit_y.to_frame(),
column_types=["categorical"]))
pipeline.verify(audit_X.sample(100))
sklearn2pmml(pipeline, "pmml/RandomForestAudit.pmml")
if "--deploy" in sys.argv:
from openscoring import Openscoring
os = Openscoring("http://localhost:8080/openscoring")
os.deployFile("RandomForestAudit", "pmml/RandomForestAudit.pmml")
Pipeline([('extract', ColumnExtractor(['user_id', 'ip_address'])),
('groupby_count', AddGroupByCount())])),
('numerics',
Pipeline([('extract', ColumnExtractor(NUM_FEATS)),
('zero_fill', ZeroFillTransformer()),
('log', Log1pTransformer())]))
]))
])
##############################
# Modeling + Tuning
##############################
from h2o.cross_validation import H2OKFold
dataset = pd.concat([X_train, y_train], axis=1)
cv = H2OKFold(dataset, n_folds=5, seed=42)
# H2O approach
("H2OCreator", H2OFrameCreator()),
# ('standardize', H2OScaler()),
# ('pca', H2OPCA()),
('rf', H2ORandomForestEstimator(ntrees=20))
# something new to try
# from scipy.stats import randint
# params = {
# # "standardize__center": [True, False],
# # "standardize__scale": [True, False],
# "pca__k": 2,
# # randint(2, X_train[1:].shape[1]),
# "rf__ntrees": 20
# # randint(50,60),
# # "rf__max_depth": randint(4,8),
# # "rf__min_rows": randint(5,10),
