How to use the sklearn2pmml.preprocessing.CutTransformer function in sklearn2pmml
To help you get started, we’ve selected a few sklearn2pmml examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
openscoring / papis.io / RandomForestAudit.py View on Github 
mapper = DataFrameMapper([
("Education", CategoricalDomain()),
("Employment", CategoricalDomain()),
("Gender", CategoricalDomain()),
("Marital", CategoricalDomain()),
("Occupation", CategoricalDomain()),
("Age", [ContinuousDomain(), CutTransformer(bins = [17, 28, 37, 47, 83], labels = ["q1", "q2", "q3", "q4"])]),
("Hours", ContinuousDomain()),
("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 Openscoringaudit_df = pandas.read_csv("csv/Audit.csv")
#print(audit_df.head(5))
audit_X = audit_df[audit_df.columns.difference(["Adjusted"])]
audit_y = audit_df["Adjusted"]
h2o.init()
mapper = DataFrameMapper([
("Education", CategoricalDomain()),
("Employment", CategoricalDomain()),
("Gender", CategoricalDomain()),
("Marital", CategoricalDomain()),
("Occupation", CategoricalDomain()),
("Age", [ContinuousDomain(), CutTransformer(bins = [17, 28, 37, 47, 83], labels = ["q1", "q2", "q3", "q4"])]),
("Hours", ContinuousDomain()),
("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)from xgboost import XGBClassifier
import pandas
import sys
audit_df = pandas.read_csv("csv/Audit.csv")
#print(audit_df.head(5))
audit_X = audit_df[audit_df.columns.difference(["Adjusted"])]
audit_y = audit_df["Adjusted"]
scalar_mapper = DataFrameMapper([
("Education", [CategoricalDomain(), LabelBinarizer(), SelectKBest(chi2, k = 3)]),
("Employment", [CategoricalDomain(), LabelBinarizer(), SelectKBest(chi2, k = 3)]),
("Occupation", [CategoricalDomain(), LabelBinarizer(), SelectKBest(chi2, k = 3)]),
("Age", [ContinuousDomain(), CutTransformer(bins = [17, 28, 37, 47, 83], labels = ["q1", "q2", "q3", "q4"]), LabelBinarizer()]),
("Hours", ContinuousDomain()),
("Income", ContinuousDomain()),
(["Hours", "Income"], Alias(ExpressionTransformer("X[1] / (X[0] * 52)"), "Hourly_Income"))
])
interaction_mapper = DataFrameMapper([
("Gender", [CategoricalDomain(), LabelBinarizer()]),
("Marital", [CategoricalDomain(), LabelBinarizer()])
])
classifier = XGBClassifier()
pipeline = PMMLPipeline([
("mapper", FeatureUnion([
("scalar_mapper", scalar_mapper),
("interaction", Pipeline([
("interaction_mapper", interaction_mapper),
("polynomial", PolynomialFeatures())sklearn2pmml
Python library for converting Scikit-Learn pipelines to PMML
