How to use sklearn2pmml - 10 common examples
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.
ankane / eps / test / support / python / lightgbm_regression.py View on Github 
text_features = ["model"]
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), PMMLLabelEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter(), max_features=5)]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LGBMRegressor(n_estimators=1000))
])
# use model__sample_weight for weight
pipeline.fit(data, data["hwy"], model__categorical_feature=[3, 4])
sklearn2pmml(pipeline, "test/support/python/lightgbm_regression.pmml")
print(pipeline.predict(data[:10]))def test_sklearn2pmml(self):
# Export to PMML
pipeline = PMMLPipeline([
("classifier", self.ref)
])
pipeline.fit(self.train[0], self.train[1])
sklearn2pmml(pipeline, "tree_sklearn2pmml.pmml", with_repr = True)
try:
# Import PMML
model = PMMLTreeClassifier(pmml='tree_sklearn2pmml.pmml')
# Verify classification
Xte, _ = self.test
assert np.array_equal(
self.ref.predict_proba(Xte),
model.predict_proba(Xte)
)
finally:
remove("tree_sklearn2pmml.pmml")def test_sklearn2pmml(self):
# Export to PMML
pipeline = PMMLPipeline([
("classifier", self.ref)
])
pipeline.fit(self.test[0], self.test[1])
sklearn2pmml(pipeline, "forest_sklearn2pmml.pmml", with_repr = True)
try:
# Import PMML
model = PMMLForestClassifier(pmml='forest_sklearn2pmml.pmml')
# Verify classification
Xte, _ = self.test
assert np.array_equal(
self.ref.predict_proba(Xte),
model.predict_proba(Xte)
)
finally:
remove("forest_sklearn2pmml.pmml")text_features = []
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), PMMLLabelEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter())]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LGBMClassifier(n_estimators=1000))
])
pipeline.fit(data, data["drv"], model__categorical_feature=[3])
suffix = "binary" if binary else "multiclass"
sklearn2pmml(pipeline, "test/support/python/lightgbm_" + suffix + ".pmml")
print(list(pipeline.predict(data[:10])))
print(list(pipeline.predict_proba(data[0:1])[0]))categorical_features = ["drv", "class"]
text_features = ["model"]
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), OneHotEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter(), max_features=5)]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LinearRegression())
])
pipeline.fit(data, data["hwy"])
sklearn2pmml(pipeline, "test/support/python/linear_regression_text.pmml")
print(list(pipeline.predict(data[:10])))def setUp(self):
iris = load_iris()
X = iris.data.astype(np.float64)
y = iris.target.astype(np.int32)
model = RandomForestClassifier(max_depth=4)
model.fit(X, y)
params = {'copyright': 'Václav Čadek', 'model_name': 'Iris Model'}
self.model = model
self.pmml = sklearn2pmml(self.model, **params)
self.num_trees = len(self.model.estimators_)
self.num_inputs = model.n_features_
self.num_outputs = model.n_classes_
self.features = ['x{}'.format(i) for i in range(self.num_inputs)]
self.class_names = ['y{}'.format(i) for i in range(self.num_outputs)]def test_sklearn2pmml(self):
# Export to PMML
pipeline = PMMLPipeline([
("classifier", self.ref)
])
pipeline.fit(self.test[0], self.test[1])
sklearn2pmml(pipeline, "forest_sklearn2pmml.pmml", with_repr = True)
try:
# Import PMML
model = PMMLForestClassifier(pmml='forest_sklearn2pmml.pmml')
# Verify classification
Xte, _ = self.test
assert np.array_equal(
self.ref.predict_proba(Xte),
model.predict_proba(Xte)
)from sklearn2pmml.feature_extraction.text import Splitter
from sklearn_pandas import DataFrameMapper
data = pd.read_csv("test/support/mpg.csv")
numeric_features = ["displ", "year", "cyl"]
categorical_features = ["drv", "class"]
text_features = ["model"]
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), PMMLLabelEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter(), max_features=5)]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LGBMRegressor(n_estimators=1000))
])
# use model__sample_weight for weight
pipeline.fit(data, data["hwy"], model__categorical_feature=[3, 4])
sklearn2pmml(pipeline, "test/support/python/lightgbm_regression.pmml")
print(pipeline.predict(data[:10]))data = pd.read_csv("test/support/mpg.csv")
if binary:
data["drv"] = data["drv"].replace("r", "4")
numeric_features = ["displ", "year", "cyl"]
categorical_features = ["class"]
text_features = []
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), PMMLLabelEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter())]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LGBMClassifier(n_estimators=1000))
])
pipeline.fit(data, data["drv"], model__categorical_feature=[3])
suffix = "binary" if binary else "multiclass"
sklearn2pmml(pipeline, "test/support/python/lightgbm_" + suffix + ".pmml")
print(list(pipeline.predict(data[:10])))
print(list(pipeline.predict_proba(data[0:1])[0]))from sklearn2pmml.feature_extraction.text import Splitter
from sklearn_pandas import DataFrameMapper
data = pd.read_csv("test/support/mpg.csv")
numeric_features = ["displ", "year", "cyl"]
categorical_features = ["drv", "class"]
text_features = ["model"]
mapper = DataFrameMapper(
[(numeric_features, [ContinuousDomain()])] +
[([f], [CategoricalDomain(), OneHotEncoder()]) for f in categorical_features] +
[(f, [CategoricalDomain(), CountVectorizer(tokenizer=Splitter(), max_features=5)]) for f in text_features]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("model", LinearRegression())
])
pipeline.fit(data, data["hwy"])
sklearn2pmml(pipeline, "test/support/python/linear_regression_text.pmml")
print(list(pipeline.predict(data[:10])))sklearn2pmml
Python library for converting Scikit-Learn pipelines to PMML
