Spooky Author Identification - Grid search for VotingClassifier

blog_grid.py

import pandas as pd
from sklearn import linear_model
from sklearn.ensemble import VotingClassifier
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.model_selection import GridSearchCV
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline

Y_COLUMN = "author"
TEXT_COLUMN = "text"

unigram_log_pipe = Pipeline([
    ('cv', CountVectorizer()),
    ('logreg', linear_model.LogisticRegression())
])

ngram_pipe = Pipeline([
    ('cv', CountVectorizer(ngram_range=(1, 2))),
    ('mnb', MultinomialNB())
])

tfidf_pipe = Pipeline([
    ('tfidf', TfidfVectorizer(min_df=3, max_features=None,
                              strip_accents='unicode', analyzer='word', token_pattern=r'\w{1,}',
                              ngram_range=(1, 3), use_idf=1, smooth_idf=1, sublinear_tf=1,
                              stop_words='english')),
    ('mnb', MultinomialNB())
])

classifiers = [
    ("ngram", ngram_pipe),
    ("unigram", unigram_log_pipe),
    ("tfidf", tfidf_pipe),
]

mixed_pipe = Pipeline([
    ("voting", VotingClassifier(classifiers, voting="soft"))
])


def combinations_on_off(num_classifiers):
    return [[int(x) for x in list("{0:0b}".format(i).zfill(num_classifiers))]
            for i in range(1, 2 ** num_classifiers)]


param_grid = dict(
    voting__weights=combinations_on_off(len(classifiers))
)

train_df = pd.read_csv("train.csv", usecols=[Y_COLUMN, TEXT_COLUMN])
y = train_df[Y_COLUMN].copy()
X = pd.Series(train_df[TEXT_COLUMN])

grid_search = GridSearchCV(mixed_pipe, param_grid=param_grid, n_jobs=-1, verbose=10, scoring="neg_log_loss")

grid_search.fit(X, y)

cv_results = grid_search.cv_results_

for mean_score, params in zip(cv_results["mean_test_score"], cv_results["params"]):
    print(params, mean_score)

print("Best score: %0.3f" % grid_search.best_score_)
print("Best parameters set:")
best_parameters = grid_search.best_estimator_.get_params()
for param_name in sorted(param_grid.keys()):
    print("\t%s: %r" % (param_name, best_parameters[param_name]))