How to use the sklearn2pmml.feature_extraction.text.Splitter 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.

github ankane / eps / test / support / python / lightgbm_regression.py View on Github external
from sklearn2pmml.decoration import ContinuousDomain, CategoricalDomain
from sklearn2pmml.pipeline import PMMLPipeline
from sklearn2pmml.preprocessing import PMMLLabelEncoder
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]))
github ankane / eps / test / support / python / lightgbm_classification.py View on Github external
from sklearn_pandas import DataFrameMapper

binary = False

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]))
github ankane / eps / test / support / python / linear_regression.py View on Github external
from sklearn2pmml import sklearn2pmml
from sklearn2pmml.decoration import ContinuousDomain, CategoricalDomain
from sklearn2pmml.pipeline import PMMLPipeline
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

AGPL-3.0
Latest version published 18 hours ago

Package Health Score

76 / 100
Full package analysis

Similar packages