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()
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,
estimator_name='RF',
file_name=results_folder)
_results, _accuracySVM, _precisionSVM, _recallSVM, _f_measureSVM = clf.evaluateResults(svm, pred, test_labels,
estimator_name='SVM',
file_name=results_folder)
_results, _accuracyADA, _precisionADA, _recallADA, _f_measureADA = clf.evaluateResults(ada, pred, test_labels,
estimator_name='ADABOOST',
file_name=results_folder)
accuracyLR.append(_accuracyLR)
precisionLR.append(_precisionLR)
recallLR.append(_recallLR)
# oneVSall_rf = clf.onevsall(tweets_features, train_labels, estimator)
'''
Test the different classifiers with the test tweets.
'''
pred = vectorizer.transform(test_tweets)
pred = pred.toarray()
# pred = SelectKBest(chi2, k=4500).fit_transform(pred, test_labels)
# evaluateResults(lda, pred, test_labels, estimator_name='LDA')
# results, accuracyLR, precisionLR, recallLR, f_measureLR = clf.evaluateResults(lr, pred, test_labels,
# estimator_name='Logistic regression')
# results, accuracyRF, precisionRF, recallRF, f_measureRF = clf.evaluateResults(forest, pred, test_labels,
# estimator_name='RF')
results, accuracySVM, precisionSVM, recallSVM, f_measureSVM = clf.evaluateResults(
svm, pred, test_labels, estimator_name='SVM')
# results, accuracyADA, precisionADA, recallADA, f_measureADA = clf.evaluateResults(ada, pred, test_labels,
# estimator_name='ADABOOST')
# results, accuracyMLP, precisionMLP, recallMLP, f_measureMLP = clf.evaluateResults(mlp, pred, test_labels,
# estimator_name='MLP')
#
# results, accuracyOVASVM, precisionOVASVM, recallOVASVM, f_measureOVASVM = clf.evaluateResults(oneVSall_svm, pred,
# test_labels,
# estimator_name='one versus all SVM')
# # evaluateResults(oneVSall_mlp, pred, test_labels, estimator_name='one versus all MLP')
# results, accuracyOVARF, precisionOVARF, recallOVARF, f_measureOVARF = clf.evaluateResults(oneVSall_rf, pred,
# test_labels,
# estimator_name='one versus all RF')
print 'Accuracy SVM:\t', accuracySVM
print 'Average Precision:\t', precisionSVM
Test the different classifiers with the test tweets.
'''
pred = vectorizer.transform(test_tweets)
pred = pred.toarray()
# pred = SelectKBest(chi2, k=4500).fit_transform(pred, test_labels)
# evaluateResults(lda, pred, test_labels, estimator_name='LDA')
# results, accuracyLR, precisionLR, recallLR, f_measureLR = clf.evaluateResults(lr, pred, test_labels,
# estimator_name='Logistic regression')
# results, accuracyRF, precisionRF, recallRF, f_measureRF = clf.evaluateResults(forest, pred, test_labels,
# estimator_name='RF')
results, accuracySVM, precisionSVM, recallSVM, f_measureSVM = clf.evaluateResults(svm, pred, test_labels,
estimator_name='SVM')
# results, accuracyADA, precisionADA, recallADA, f_measureADA = clf.evaluateResults(ada, pred, test_labels,
# estimator_name='ADABOOST')
# results, accuracyMLP, precisionMLP, recallMLP, f_measureMLP = clf.evaluateResults(mlp, pred, test_labels,
# estimator_name='MLP')
#
# results, accuracyOVASVM, precisionOVASVM, recallOVASVM, f_measureOVASVM = clf.evaluateResults(oneVSall_svm, pred,
# test_labels,
# estimator_name='one versus all SVM')
# # evaluateResults(oneVSall_mlp, pred, test_labels, estimator_name='one versus all MLP')
# results, accuracyOVARF, precisionOVARF, recallOVARF, f_measureOVARF = clf.evaluateResults(oneVSall_rf, pred,
# test_labels,
# estimator_name='one versus all RF')
print 'Accuracy SVM:\t', accuracySVM
print 'Average Precision:\t', precisionSVM
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,
estimator_name='RF',
file_name=results_folder)
_results, _accuracySVM, _precisionSVM, _recallSVM, _f_measureSVM = clf.evaluateResults(
svm,
pred,
test_labels,
estimator_name='SVM',
file_name=results_folder)
print '\nCreating Test set for super classifier ... '
val_tweet_trans = vectorizer.transform(validation_tweets)
val_tweet_trans = val_tweet_trans.toarray()
test_results = clf.test_classifiers(val_tweet_trans, validation_labels,
classifiers)
'''
Now we have a train_results and test_results. Lets train and test a super classifier
'''
print '\nTraining super classifier ... '
super_clf = clf.rbf_classifier(train_results, test_labels)
print '\nEvaluating Super classifier ... '
results, accuracy, precision, recall, f_measure = clf.evaluateResults(
super_clf,
test_results,
validation_labels,
estimator_name='Supper Classifier')
print '\n\nSuperClassify partition', j, '\n'
diagnose.supperclassify(train_results, test_labels, test_results,
validation_labels)
# np.savetxt("train_results_3.csv", train_results, delimiter=",")
# np.savetxt("train_labels_3.csv", test_labels, delimiter=",")
# np.savetxt("test_results_3.csv", test_results, delimiter=",")
# np.savetxt("test_labels_3.csv", validation_labels, delimiter=",")
# import pdb; pdb.set_trace()
# printResults(accuracy, precision, recall, f_measure, name="SUPER CLASSIFICATOR")
Train the super classifier on the test set
'''
print '\nCreating Test set for super classifier ... '
val_tweet_trans = vectorizer.transform(validation_tweets)
val_tweet_trans = val_tweet_trans.toarray()
test_results = clf.test_classifiers(val_tweet_trans, validation_labels, classifiers)
'''
Now we have a train_results and test_results. Lets train and test a super classifier
'''
print '\nTraining super classifier ... '
super_clf = clf.rbf_classifier(train_results, test_labels)
print '\nEvaluating Super classifier ... '
results, accuracy, precision, recall, f_measure = clf.evaluateResults(super_clf, test_results,
validation_labels,
estimator_name='Supper Classifier')
print '\n\nSuperClassify partition', j, '\n'
diagnose.supperclassify(train_results, test_labels, test_results, validation_labels)
# np.savetxt("train_results_3.csv", train_results, delimiter=",")
# np.savetxt("train_labels_3.csv", test_labels, delimiter=",")
# np.savetxt("test_results_3.csv", test_results, delimiter=",")
# np.savetxt("test_labels_3.csv", validation_labels, delimiter=",")
# import pdb; pdb.set_trace()
# printResults(accuracy, precision, recall, f_measure, name="SUPER CLASSIFICATOR")
