def main():
# CID is used to run on the department cluster
CID = opts.cluster
if (opts.load != 'none'): CID = opts.load
X_train, X_test, Y_train, Y_test, enc = f.get_data()
model = bulid_model(
X_train, X_test, Y_train, Y_test, CID, fromfile=opts.load)
newData = X_test.reshape(X_test.shape[0], 1, 100, 20)
Y_score = model.predict_proba(X_test)
roc.roc_plot(
Y_test, Y_score, 2, filepath=os.path.join('figures', CID + 'roc.jpg'),title="CNN 2D AVG pool")
Y_de = decode_y(Y_test, features=enc.active_features_)
Y_pred = model.predict(X_test)
Y_depred = decode_y(Y_pred, features=enc.active_features_)
print(classification_report(Y_de, Y_depred))
return
def main():
CID = opts.cluster
if (opts.load != 'none'): CID = opts.load
X_train, X_test, Y_train, Y_test, X, X2, X3, enc = f.get_data_pro(
testsize=0.2)
model = bulid_model(X_train,
X_test,
Y_train,
Y_test,
X,
X2,
X3,
CID,
fromfile=opts.load)
newData = X_test.reshape(X_test.shape[0], 1, 100, 20)
Y_score = model.predict_proba(X_test)
roc.roc_plot(Y_test,
Y_score,
2,
filepath=os.path.join('figures',
CID + opts.title + 'roc.svg'),
fmt='svg',
title=opts.title)
Y_de = decode_y(Y_test, features=enc.active_features_)
Y_pred = model.predict(X_test)
Y_depred = decode_y(Y_pred, features=enc.active_features_)
print(classification_report(Y_de, Y_depred))
return
SGDClassifier(loss='log',
random_state=42,
shuffle=True,
alpha=0.0001 * 0.75,
penalty='l1',
max_iter=20)),
])
_ = clf2.fit(train_data, train_target)
predicted = clf2.predict(test_data)
proba = clf2.predict_proba(test_data)
ohenc = OneHotEncoder()
Y2 = ohenc.fit_transform(test_target.reshape(-1, 1)).toarray()
roc.roc_plot(Y2,
proba,
2,
filepath=os.path.join('figures', 'tradSGD' + 'roc.svg'),
title='Logistic',
fmt='svg')
print(metrics.classification_report(
test_target,
predicted,
))
print(accuracy_score(test_target, predicted))
"""
try SVC
"""