y_train, y_test = y[train_index], y[test_index]
X_den_train, X_den_test = X_den[train_index], X_den[test_index]
# feed models
clf_mNB.fit(X_train, y_train)
clf_ridge.fit(X_train, y_train)
clf_SGD.fit(X_train, y_train)
clf_lSVC.fit(X_train, y_train)
clf_SVC.fit(X_train, y_train)
# get prediction for this fold run
prob_mNB = clf_mNB.predict_proba(X_test)
prob_ridge = clf_ridge.decision_function(X_test)
prob_SGD = clf_SGD.decision_function(X_test)
prob_lSVC = clf_lSVC.decision_function(X_test)
prob_SVC = clf_SVC.predict_proba(X_test)
# add prob functions into the z 2d-array
z_temp = (prob_mNB + prob_ridge + prob_SGD + prob_lSVC + prob_SVC)
z = np.append(z, z_temp, axis=0)
# remove the first sub-1d-array of z, due to the creation with 0s
z = np.delete(z, 0, 0)
# the result of z is a 2d array with shape of (n_samples, n_categories)
# the elements are the sum of probabilities of classifiers on each (sample,category) pair
print z
print 'z shape: ', z.shape
y_train_train, y_train_test = y_train[train_index], y_train[test_index]
# X_den_train, X_den_test = X_den[train_index], X_den[test_index]
# feed models
clf_mNB.fit(X_train_train, y_train_train)
# clf_kNN.fit(X_train_train, y_train_train)
clf_ridge.fit(X_train_train, y_train_train)
clf_lSVC.fit(X_train_train, y_train_train)
clf_SVC.fit(X_train_train, y_train_train)
# get prediction for this fold run
prob_mNB = clf_mNB.predict_proba(X_train_test)
# prob_kNN = clf_kNN.predict_proba(X_train_test)
prob_ridge = clf_ridge.decision_function(X_train_test)
prob_lSVC = clf_lSVC.decision_function(X_train_test)
prob_SVC = clf_SVC.predict_proba(X_train_test)
# update z array for each model
# z_temp = prob_lSVC
# z_temp = (prob_ridge + prob_lSVC)
z_temp = (prob_mNB + prob_ridge + prob_lSVC + prob_SVC)
z = np.append(z, z_temp, axis=0)
# remove the first sub-1d-array of z, due to the creation with 0s
z = np.delete(z, 0, 0)
# the result of z is a 2d array with shape of (n_samples, n_categories)
# the elements are the sum of probabilities of classifiers on each (sample,category) pair
# Possible preprocessing on z
# z = normalize(z, norm="l2")
print doc
for label in labels:
# label[0]: score; label[1]: #
print data_train.target_names[label[1]], label[0]
print
#####################################
# decision_function and predict_proba
print clf_nb
pred_prob = clf_nb.predict_proba(X_new)
print pred_prob
print
print clf_lsvc
pred_decision = clf_lsvc.decision_function(X_new)
print pred_decision
print
print clf_svc
# SVC should have the decision_function method, but got error:
# error - ValueError: setting an array element with a sequence
# pred_decision = clf_svc.decision_function(X_new)
pred_prob = clf_svc.predict_proba(X_new)
print pred_prob
print
print clf_sgd
pred_decision = clf_sgd.decision_function(X_new)
# pred_prob is only supported for binary classification!
# pred_prob = clf_sgd.predict_proba(X_new)
# split ~140k into ~100k training and ~40k test
ff_train, ff_val = split_dataframe(test_ff)
print("Training...")
t1 = time()
vectorizer = CountVectorizer()
train_counts = vectorizer.fit_transform(ff_train["TitlePlusBody"])
tfidf_transformer = TfidfTransformer(use_idf=False)
# 98190x285052
train_tfidf_table = tfidf_transformer.fit_transform(train_counts)
clf = LinearSVC().fit(train_tfidf_table, ff_train["OpenStatus"])
print("Testing...")
test_counts = vectorizer.transform(ff_val["TitlePlusBody"])
test_tfidf_table = tfidf_transformer.transform(test_counts)
predict = clf.predict(test_tfidf_table)
print("np.mean: %f" % (np.mean(predict == ff_val["OpenStatus"])))
linear_decisions = clf.decision_function(test_tfidf_table)
predicted_probs = (1 / (1 + np.exp(- linear_decisions))) ** 3.5
print("MCLL: %f" % (mcll(predicted_probs, ff_val["OpenStatus"].values)))
t2 = time()
print("done in %d seconds" % (t2 - t1))
