Pickle export

pickle_export.py

# with X_train, X_test, Y_train, Y_test
import dill
from sklearn_pandas import DataFrameMapper
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import FunctionTransformer

def is_adult(x): return x > 18

clf = Pipeline([
    ("mapper", DataFrameMapper([
        (['age'], FunctionTransformer(is_adult)),
        (features, None)
    ])),
    ("classifier", LogisticRegression())
])

clf.fit(X_train, Y_train)
print(clf.score(X_test, Y_test))

with open('pipeline.pk', 'wb') as f:
    dill.dump(clf, f)