def supperclassify(train_set, train_label, test_set, test_label):
'''Different methods'''
train_voted = voting(train_set)
aux = train_voted == train_label
correct = sum(aux.astype(int))
_accuracy = (correct * 100) / len(train_label)
_precision, _recall, _f1score, _support = ut.get_measures_for_each_class(
train_label, train_voted)
print 'Estimator VOTING'
print 'Average Accuracy:\t', _accuracy
print 'Average Precision:\t', _precision
print 'Average Recall:\t', _recall
print 'Average F1 Measure:\t', _f1score
print '\n'
lambdas = weighted_voting_getlambdas(train_set, train_label)
results = weighted_voting(test_set, lambdas)
aux = results == test_label
correct = sum(aux.astype(int))
_accuracy = (correct * 100) / len(test_label)
_precision, _recall, _f1score, _support = ut.get_measures_for_each_class(
test_label, results)
print 'Estimator W_VOTING'
print 'Average Accuracy:\t', _accuracy
print 'Average Precision:\t', _precision
print 'Average Recall:\t', _recall
print 'Average F1 Measure:\t', _f1score
rf = clf.classifier_randomForest(train_set, train_label)
results = clf.evaluateResults(rf,
test_set,
test_label,
estimator_name='RF')
lr = clf.logistic_regression(train_set, train_label)
results = clf.evaluateResults(lr,
test_set,
test_label,
estimator_name='LR')
svm = clf.classifier_svm(train_set, train_label)
results = clf.evaluateResults(svm,
test_set,
test_label,
estimator_name='SVM')
rbf = clf.rbf_classifier(train_set, train_label)
results = clf.evaluateResults(rbf,
test_set,
test_label,
estimator_name='RBF')
def supperclassify(train_set, train_label, test_set, test_label):
'''Different methods'''
train_voted = voting(train_set)
aux = train_voted == train_label
correct = sum(aux.astype(int))
_accuracy = (correct * 100) / len(train_label)
_precision, _recall, _f1score, _support = ut.get_measures_for_each_class(train_label, train_voted)
print 'Estimator VOTING'
print 'Average Accuracy:\t', _accuracy
print 'Average Precision:\t', _precision
print 'Average Recall:\t', _recall
print 'Average F1 Measure:\t', _f1score
print '\n'
lambdas = weighted_voting_getlambdas(train_set, train_label)
results = weighted_voting(test_set, lambdas)
aux = results == test_label
correct = sum(aux.astype(int))
_accuracy = (correct * 100) / len(test_label)
_precision, _recall, _f1score, _support = ut.get_measures_for_each_class(test_label, results)
print 'Estimator W_VOTING'
print 'Average Accuracy:\t', _accuracy
print 'Average Precision:\t', _precision
print 'Average Recall:\t', _recall
print 'Average F1 Measure:\t', _f1score
rf = clf.classifier_randomForest(train_set, train_label)
results = clf.evaluateResults(rf, test_set, test_label, estimator_name='RF')
lr = clf.logistic_regression(train_set, train_label)
results = clf.evaluateResults(lr, test_set, test_label, estimator_name='LR')
svm = clf.classifier_svm(train_set, train_label)
results = clf.evaluateResults(svm, test_set, test_label, estimator_name='SVM')
rbf = clf.rbf_classifier(train_set, train_label)
results = clf.evaluateResults(rbf, test_set, test_label, estimator_name='RBF')
# import pdb; pdb.set_trace()
tweets = np.array(tweets)
labels = np.array(labels)
# Extract tweet partition
train_tweets = tweets[np.array(train)]
train_tweets, test_tweets, train_labels, test_labels = tweets[train], tweets[test], labels[train], labels[test]
print len(test_tweets)
print len(train_tweets)
train_tweets = np.hstack(train_tweets)
dictionary, tweets_features, vectorizer = bow.bow(train_tweets, vec="tfidf")
'''
Training different classifiers.
'''
svm = clf.classifier_svm(tweets_features, train_labels)
rf = clf.classifier_randomForest(tweets_features, train_labels)
ada = clf.adaboost(tweets_features, train_labels)
lr = clf.logistic_regression(tweets_features, train_labels)
'''
Test the different classifiers with the test tweets.
'''
pred = vectorizer.transform(test_tweets)
pred = pred.toarray()
_results, _accuracyLR, _precisionLR, _recallLR, _f_measureLR = clf.evaluateResults(lr, pred, test_labels,
estimator_name='Logistic regression',
file_name=results_folder)
_results, _accuracyRF, _precisionRF, _recallRF, _f_measureRF = clf.evaluateResults(rf, pred, test_labels,
train_tweets = np.hstack(train_tweets)
dictionary, tweets_features, vectorizer = bow.bow(train_tweets,
vec="tfidf")
# dictionary, tweets_features, vectorizer = bow.bow(train_tweets, vec="count")
# print dictionary
'''Dimsionality reduction'''
# LDA
# lda = clf.lda(tweets_features, train_labels)
# print tweets_features.shape
'''
Training different classifiers.
'''
# forest = clf.classifier_randomForest(tweets_features, train_labels)
svm = clf.classifier_svm(tweets_features, train_labels)
# mlp = clf.multilayer_perceptron(tweets_features, train_labels)
# ada = clf.adaboost(tweets_features, train_labels)
# lr = clf.logistic_regression(tweets_features, train_labels)
# ONE VS ALL CLASSIFIER WITH DIFFERENT ESTIMATORS.
# estimator = clf.svm.SVC(random_state=0)
# oneVSall_svm = clf.onevsall(tweets_features, train_labels, estimator)
#
# estimator = clf.MLP()
# oneVSall_mlp = clf.onevsall(tweets_features, train_labels, estimator)
#
# estimator = clf.RandomForestClassifier(n_estimators=50)
# oneVSall_rf = clf.onevsall(tweets_features, train_labels, estimator)
'''
Test the different classifiers with the test tweets.