def classify(features, results, test_features, test_results, C, gamma):
cli = "%s@%s" %(C, gamma)
st = time.time()
log.info("Classifier begins")
classifier = SVC(C=C, gamma=gamma, kernel="rbf")
classifier.fit(features, results)
st2 = time.time()
prediction = classifier.predict(test_features)
log.info("id: %s Training time: %s, Prediction time: %s" %(cli, st2-st, time.time()-st2) )
error = 0
for index, value in enumerate(prediction):
if test_results[index] != value:
error += 1
return (error/float(len(test_results))) * 100
def classify(train_file, test_file):
"""
Train a model and test
train_file: file that the model is trained on
test_file: file that is used to test the model
"""
X_train, y_train = load_svmlight_file(train_file)
X_test, y_test = load_svmlight_file(test_file, X_train.shape[1])
# X_train = X_train.todense()
# X_test = X_test.todense()
clf = SparseSVC(kernel="linear", C=0.2)
# clf = LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(X_train, y_train)
y_predict = clf.predict(X_test)
print sklearn.metrics.classification_report(y_test, y_predict)
print sklearn.metrics.confusion_matrix(y_test, y_predict)
# 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
pred_mNB = clf_mNB.predict(X_train_test)
pred_kNN = clf_kNN.predict(X_train_test)
pred_ridge = clf_ridge.predict(X_train_test)
pred_lSVC = clf_lSVC.predict(X_train_test)
pred_SVC = clf_SVC.predict(X_train_test)
# update z array for each model
z_mNB = np.append(z_mNB , pred_mNB , axis=None)
z_kNN = np.append(z_kNN , pred_kNN , axis=None)
z_ridge = np.append(z_ridge , pred_ridge, axis=None)
z_lSVC = np.append(z_lSVC , pred_lSVC , axis=None)
z_SVC = np.append(z_SVC , pred_SVC , axis=None)
# putting z's from each model into one 2d matrix
# this is the (feature) input, similar as X, for level 1
# In level 1, y is still y.
# z = np.array([z_bNB, z_mNB, z_kNN, z_ridge, z_SGD, z_lSVC, z_SVC, z_tree, z_logis], dtype=np.int32)
z = np.array([z_mNB, z_kNN, z_ridge, z_lSVC, z_SVC], dtype=np.int32)
z = z.transpose()
X_den_train, X_den_test = X_den[train_index], X_den[test_index]
# feed models
clf_mNB.fit(X_train, y_train)
clf_kNN.fit(X_train, y_train)
clf_ridge.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
pred_mNB = clf_mNB.predict(X_test)
pred_kNN = clf_kNN.predict(X_test)
pred_ridge = clf_ridge.predict(X_test)
pred_lSVC = clf_lSVC.predict(X_test)
pred_SVC = clf_SVC.predict(X_test)
# update z array for each model
z_mNB = np.append(z_mNB , pred_mNB , axis=None)
z_kNN = np.append(z_kNN , pred_kNN , axis=None)
z_ridge = np.append(z_ridge , pred_ridge, axis=None)
z_lSVC = np.append(z_lSVC , pred_lSVC , axis=None)
z_SVC = np.append(z_SVC , pred_SVC , axis=None)
# putting z's from each model into one 2d matrix
# this is the (feature) input, similar as X, for level 1
# In level 1, y is still y.
# z = np.array([z_bNB, z_mNB, z_kNN, z_ridge, z_SGD, z_lSVC, z_SVC, z_tree, z_logis], dtype=np.int32)
z = np.array([z_mNB, z_kNN, z_ridge, z_lSVC, z_SVC], dtype=np.int32)
z = z.transpose()
# Initialize variables for couting the average
f1_all = []
f5_all = []
acc_all = []
pre_all = []
rec_all = []
# Test for 10 rounds using the results from 10 fold cross validations
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
# fit and predict
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
# print y_test
# print pred
# print type(pred)
# output tree into graph
# out = StringIO()
# out = export_graphviz(clf, out_file=out)
# metrics
# # Original
f1_score = metrics.f1_score(y_test, pred)
f5_score = metrics.fbeta_score(y_test, pred, beta=0.5)
acc_score = metrics.zero_one_score(y_test, pred)
