logging.info('Derived features shape:')
logging.info(derived_features.shape)
features_tfidf = pandas.DataFrame(tfidfX.todense())
# Assign column names to make it easier to print most useful features later
features_tfidf.columns = tfidf.get_feature_names()
features_combined = pandas.concat([features_tfidf, derived_features],
axis=1)
logging.info('Combined features shape:')
logging.info(features_combined.shape)
svm_object = LinearSVC()
clf = CalibratedClassifierCV(svm_object)
classifier = balancer.OneVsRestClassifierBalance(clf)
logging.info('Training classifier')
classifier.fit(features_combined.values, labels_matrix)
logging.info('Saving TFIDF vectorizer')
joblib.dump(tfidf, vectorizer_filename)
logging.info('Saving binarizer')
joblib.dump(mlb, binarizer_filename)
logging.info('Saving model')
joblib.dump(classifier, model_filename)
end = time.time()
runtime_in_seconds = end - start
logging.info('Processing completed in {0}'.format(runtime_in_seconds))
except Error as e:
logging.exception(e)
url_corpus, heading_text_corpus, content_corpus)
logging.info('Derived features shape:')
logging.info(derived_features.shape)
features_tfidf = pandas.DataFrame(tfidfX.todense())
# Assign column names to make it easier to print most useful features later
features_tfidf.columns = tfidf.get_feature_names()
features_combined = pandas.concat([features_tfidf, derived_features],
axis=1)
logging.info('Combined features shape:')
logging.info(features_combined.shape)
classifiers_to_test = [
(balancer.OneVsRestClassifierBalance(LinearSVC()), 'SVM (Linear)'),
(balancer.OneVsRestClassifierBalance(RandomForestClassifier()),
'Random Forest'),
(balancer.OneVsRestClassifierBalance(GaussianNB()), 'Naive Bayes'),
(balancer.OneVsRestClassifierBalance(LogisticRegression()),
'Logistic Regression'),
(balancer.OneVsRestClassifierBalance(KNeighborsClassifier()),
'k-Nearest Neighbour')
]
for classifier, classifier_name in classifiers_to_test:
logging.info(f'Running experiment for {classifier_name}')
logging.info('Getting per-class scores')
y_pred = cross_val_predict(classifier,
features_combined.values,
labels_matrix,
cv=10)
url_corpus, heading_text_corpus, content_corpus)
logging.info('Derived features shape:')
logging.info(derived_features.shape)
features_tfidf = pandas.DataFrame(tfidfX.todense())
# Assign column names to make it easier to print most useful features later
features_tfidf.columns = tfidf.get_feature_names()
features_combined = pandas.concat([features_tfidf, derived_features],
axis=1)
logging.info('Combined features shape:')
logging.info(features_combined.shape)
svm_object = LinearSVC()
classifier = balancer.OneVsRestClassifierBalance(svm_object)
logging.info('Computing overall results')
scores_kappa = cross_val_score(classifier,
features_combined.values,
labels_matrix,
cv=10,
scoring=kappa_scorer()).mean()
logging.info('Kappa : {0}'.format(scores_kappa))
end = time.time()
runtime_in_seconds = end - start
logging.info('Processing completed in {0}'.format(runtime_in_seconds))
except Error as e:
logging.exception(e)
