pipeline.py

# Import pipeline
from sklearn.pipeline import Pipeline

# Import classifiers
from sklearn.linear_model import LogisticRegression
from sklearn.multiclass import OneVsRestClassifier

# Import CountVectorizer
from sklearn.feature_extraction.text import CountVectorizer

# Import other preprocessing modules
from sklearn.preprocessing import Imputer
from sklearn.feature_selection import chi2, SelectKBest

# Select 300 best features
chi_k = 300

# Import functional utilities
from sklearn.preprocessing import FunctionTransformer, MaxAbsScaler
from sklearn.pipeline import FeatureUnion

# Perform preprocessing
get_text_data = FunctionTransformer(combine_text_columns, validate=False)
get_numeric_data = FunctionTransformer(lambda x: x[NUMERIC_COLUMNS], validate=False)

# Create the token pattern: TOKENS_ALPHANUMERIC
TOKENS_ALPHANUMERIC = '[A-Za-z0-9]+(?=\\s+)'

# Import the hashing vectorizer
from sklearn.feature_extraction.text import HashingVectorizer

# Instantiate the winning model pipeline: pl
pl = Pipeline([
        ('union', FeatureUnion(
            transformer_list = [
                ('numeric_features', Pipeline([
                    ('selector', get_numeric_data),
                    ('imputer', Imputer())
                ])),
                ('text_features', Pipeline([
                    ('selector', get_text_data),
                    ('vectorizer', HashingVectorizer(token_pattern=TOKENS_ALPHANUMERIC,
                                                     non_negative=True, norm=None, binary=False,
                                                     ngram_range=(1, 2))),
                    ('dim_red', SelectKBest(chi2, chi_k))
                ]))
             ]
        )),
        ('int', SparseInteractions(degree=2)),
        ('scale', MaxAbsScaler()),
        ('clf', OneVsRestClassifier(LogisticRegression()))
    ])