def combined_crossval(claim_ids, target, rootdist_matrix, tf_matrix, questionmark, folds=7, do_custom_folds=True):
custom_folds = cv_fold_generator(claim_ids, folds)
rootdist_feature = sparse.csr_matrix(rootdist_matrix)
questionmark_feature = questionmark
ppdb_alignment_feature = sparse.csr_matrix(get_ppdb_alignment_feature())
combined_all = sparse.hstack((
rootdist_feature,
questionmark_feature,
ppdb_alignment_feature,
tf_matrix
))
plot_2D_data(combined_all, target)
if do_custom_folds:
folds = custom_folds
print("Classifier: ", '[accuracy,', 'f1_macro,', 'recall_macro,', 'precision_macro]')
print("Logistic regression ovr L1: ", logistic_regression(combined_all, target, folds, 'l1', 1000000, 'ovr'))
print("Logistic regression ovr L2: ", logistic_regression(combined_all, target, folds, 'l2', 1000000, 'ovr'))
print("Logistic regression multiclass L1: ", logistic_regression(combined_all, target, folds, 'l1', 1000000, 'multinomial'))
print("Logistic regression multiclass L2: ", logistic_regression(combined_all, target, folds, 'l2', 1000000, 'multinomial'))
print("SVM Cross-validation")
svm_crossval_grid(combined_all, target, folds)
print("Naive Bayes: ", naive_bayes(combined_all.toarray(), target, folds))
def naive_bayes(input_dict):
""" Naive Bayes algorithm for classification """
from sklearn.naive_bayes import GaussianNB
y_pred = GaussianNB()
output_dict = {}
output_dict['bayes_out'] = c.naive_bayes()
return output_dict
# Adding length of a each review feature
print("After adding length review feature")
X = functions.add_length_review_feature(X, length_of_reviews)
print(X)
# Adding Part of Speech Tag Feature
print("After adding Part of Speech Tag feature")
prp_list = functions.create_pos_features(reviews)
X = functions.add_pos_feature(X, prp_list)
print(X)
# Logistic Regression
# --------------------------------------------
classifier = classification.logistic_regression(X, scores)
# Naive Bayes
# --------------------------------------------
classifier = classification.naive_bayes(X, scores)
# K Nearest Neighbors
# --------------------------------------------
classifier = classification.knearest_neighbors(X, scores)
# Decision Trees
# --------------------------------------------
classifier = classification.decision_trees(X, scores)
# Random Forests
# --------------------------------------------
classifier = classification.random_forest(X, scores)
if __name__ == '__main__':
print('Running Classifiers for dianping dataset')
print("Does not include extra features")
print("Using Bag of Words")
print('------------------------------------------')
stop = dianping.gather_stopwords()
labels, reviews = dianping.read_chinese()
BOW, vec = dianping.chinese_BOW(reviews, stop)
# Logistic Regression
# --------------------------------------------
classifier = classification.logistic_regression(BOW, labels)
# Naive Bayes
# --------------------------------------------
classifier = classification.naive_bayes(BOW, labels)
# K Nearest Neighbors
# --------------------------------------------
classifier = classification.knearest_neighbors(BOW, labels)
# Decision Trees
# --------------------------------------------
classifier = classification.decision_trees(BOW, labels)
# Random Forests
# --------------------------------------------
classifier = classification.random_forest(BOW, labels)
def naive_bayes(input_dict):
"""Naive Bayes learner"""
p = input_dict['params']
return {'learner': classification.naive_bayes(p)}