-
-
Save AdamGreenhill/f78f7e300834fb4ea55e67e139b923a7 to your computer and use it in GitHub Desktop.
Sentiment analysis with scikit-learn
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # You need to install scikit-learn: | |
| # sudo pip install scikit-learn | |
| # | |
| # Dataset: Polarity dataset v2.0 | |
| # http://www.cs.cornell.edu/people/pabo/movie-review-data/ | |
| # | |
| # Full discussion: | |
| # https://marcobonzanini.wordpress.com/2015/01/19/sentiment-analysis-with-python-and-scikit-learn | |
| import sys | |
| import os | |
| import time | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn import svm | |
| from sklearn.metrics import classification_report | |
| def usage(): | |
| print("Usage:") | |
| print("python %s <data_dir>" % sys.argv[0]) | |
| if __name__ == '__main__': | |
| if len(sys.argv) < 2: | |
| usage() | |
| sys.exit(1) | |
| data_dir = sys.argv[1] | |
| classes = ['pos', 'neg'] | |
| # Read the data | |
| train_data = [] | |
| train_labels = [] | |
| test_data = [] | |
| test_labels = [] | |
| for curr_class in classes: | |
| dirname = os.path.join(data_dir, curr_class) | |
| for fname in os.listdir(dirname): | |
| with open(os.path.join(dirname, fname), 'r') as f: | |
| content = f.read() | |
| if fname.startswith('cv9'): | |
| test_data.append(content) | |
| test_labels.append(curr_class) | |
| else: | |
| train_data.append(content) | |
| train_labels.append(curr_class) | |
| # Create feature vectors | |
| vectorizer = TfidfVectorizer(min_df=5, | |
| max_df = 0.8, | |
| sublinear_tf=True, | |
| use_idf=True) | |
| train_vectors = vectorizer.fit_transform(train_data) | |
| test_vectors = vectorizer.transform(test_data) | |
| # Perform classification with SVM, kernel=rbf | |
| classifier_rbf = svm.SVC() | |
| t0 = time.time() | |
| classifier_rbf.fit(train_vectors, train_labels) | |
| t1 = time.time() | |
| prediction_rbf = classifier_rbf.predict(test_vectors) | |
| t2 = time.time() | |
| time_rbf_train = t1-t0 | |
| time_rbf_predict = t2-t1 | |
| # Perform classification with SVM, kernel=linear | |
| classifier_linear = svm.SVC(kernel='linear') | |
| t0 = time.time() | |
| classifier_linear.fit(train_vectors, train_labels) | |
| t1 = time.time() | |
| prediction_linear = classifier_linear.predict(test_vectors) | |
| t2 = time.time() | |
| time_linear_train = t1-t0 | |
| time_linear_predict = t2-t1 | |
| # Perform classification with SVM, kernel=linear | |
| classifier_liblinear = svm.LinearSVC() | |
| t0 = time.time() | |
| classifier_liblinear.fit(train_vectors, train_labels) | |
| t1 = time.time() | |
| prediction_liblinear = classifier_liblinear.predict(test_vectors) | |
| t2 = time.time() | |
| time_liblinear_train = t1-t0 | |
| time_liblinear_predict = t2-t1 | |
| # Print results in a nice table | |
| print("Results for SVC(kernel=rbf)") | |
| print("Training time: %fs; Prediction time: %fs" % (time_rbf_train, time_rbf_predict)) | |
| print(classification_report(test_labels, prediction_rbf)) | |
| print("Results for SVC(kernel=linear)") | |
| print("Training time: %fs; Prediction time: %fs" % (time_linear_train, time_linear_predict)) | |
| print(classification_report(test_labels, prediction_linear)) | |
| print("Results for LinearSVC()") | |
| print("Training time: %fs; Prediction time: %fs" % (time_liblinear_train, time_liblinear_predict)) | |
| print(classification_report(test_labels, prediction_liblinear)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment