def predict(self, data_vectorized):
target_names = ['negative', 'positive']
#x_test_v_scaled = self.scaler.fit_transform(data_vectorized['x_test_v'])
x_test_v_scaled = data_vectorized['x_test_v']
start_time = time.time()
self.prediction_liblinear = self.Classifier_liblinear.predict(
x_test_v_scaled)
self.time_prediction = (time.time() - start_time)
logging.info("prediction finished - %6.2f seconds " %
self.time_prediction)
# cross validation
# logging.info("cross validation ... ")
# start_time = time.time()
# scores = cross_val_score(self.Classifier_liblinear,
# data_vectorized['x_train_v'],
# data_vectorized['y_train'],
# cv=3, n_jobs=-1)
#
# logging.info("Cross-Validation Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
# logging.info("Cross-Validation finished- %6.2f seconds " % (time.time() - start_time))
# # # Print results in a nice table linearSVC
logging.info("Results for LinearSVC()")
logging.info("Training time: %fs; Prediction time: %fs" %
(self.time_training, self.time_prediction))
logging.info(
classification_report(data_vectorized['y_test'],
self.prediction_liblinear,
target_names=target_names))
# ### plot top features - only possible for linear and tfidf
try:
plotter.plot_coefficients(
self.Classifier_liblinear,
data_vectorized['vectorizer'].get_feature_names(),
fname=self.name)
except:
logging.info('feature-plotting not possible')
io.save_classifier(self.Classifier_liblinear)
# for ind, i in enumerate(Cs):
# plt.plot(Tol, scores[ind], label='C: ' + str(i))
# plt.legend()
# plt.xlabel('Los')
# plt.ylabel('Mean score')
# plt.show()
import thesis.Visualization as plotter
# plot the most informative features of the best pipeline
features = grid_search.best_estimator_.named_steps['vect'].get_feature_names()
logging.info(features[0])
logging.info(len(features))
clf = grid_search.best_estimator_.named_steps['clf']
plotter.plot_coefficients(clf, features,fname='test')
# show best accuracy from the 4 fold cross validation with the validation data
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(parameters.keys()):
print("\t%s: %r" % (param_name, best_parameters[param_name]))
# print classification_report with the unseen testing data
clf = grid_search.best_estimator_
prediction = clf.predict(data['x_test'])
target_names = ['negative', 'positive']
print(classification_report(data['y_test'], prediction, target_names=target_names))