Y = notices.target
vocab = tfidf.vocabulary_
print("vocab len=", len(vocab))
test_size = 0.6
X_train, X_test, y_train, y_test = \
cross_validation.train_test_split(X, Y,
test_size=test_size, random_state=0)
print("--------------------------")
print("TF-IDF - SVM")
print("--------------------------")
clf = svm.SVC()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(
metrics.classification_report(y_test, y_pred,
target_names=label_names))
print(metrics.confusion_matrix(y_test, y_pred))
crossValidationScores(clf, X_train, y_train)
###############################################################################
# Classification and ROC analysis
# Run classifier with crossvalidation and plot ROC curves
met.showRocAnalysis(X, Y)
print("-----------------------------------------------")
class_weight = {0:5}
print("Class weight=", class_weight)
clf = svm.SVC(C=100.0, cache_size=200, class_weight=class_weight, coef0=0.0, degree=3,
gamma=0.0001, kernel='rbf', max_iter= -1, probability=False, shrinking=True,
tol=0.001, verbose=False).fit(X_train, y_train)
print("Test svm.SVC score=", clf.score(X_test, y_test))
print("Train svm.SVC score=", clf.score(X_train, y_train))
print("-----------------------------------------------")
print("Metrics on TEST SET")
print("-----------------------------------------------")
y_pred = clf.predict(X_test)
print(metrics.classification_report(y_test, y_pred, target_names=label_names))
print(metrics.confusion_matrix(y_test, y_pred))
print("-----------------------------------------------")
print("Metrics on TRAIN SET")
print("-----------------------------------------------")
y_predTrain = clf.predict(X_train)
print(metrics.classification_report(y_train, y_predTrain, target_names=label_names))
print(metrics.confusion_matrix(y_train, y_predTrain))
met.crossValidationScores(clf, X_train, y_train)
met.showRocAnalysis(X_bns, Y, class_weight=class_weight)