def logistic_gd(df_train, df_test, Y):
""" logistic gradient descent """
binary = utils.check_binary(df_train[Y])
model = gd.logistic_gradient(df_train, df_train[Y], 0.1, max_iterations=5)
print model
predict = gd.predict(df_train, model, binary, True)
print predict
error_train = mystats.get_error(predict, df_train[Y], binary)
predict = gd.predict(df_test, model, binary, True)
print predict
error_test = mystats.get_error(predict, df_test[Y], binary)
return [error_train, error_test]
def testLogisticGradient():
""" logistic gradient descent """
df_test, df_train = utils.split_test_and_train(utils.load_and_normalize_spam_data())
Y = 'is_spam'
binary = utils.check_binary(df_train[Y])
model = gd.logistic_gradient(df_train, df_train[Y], .1, max_iterations=5)
#print model
#raw_input()
predict = gd.predict(df_train, model, binary, True)
print predict
error_train = mystats.get_error(predict, df_train[Y], binary)
#raw_input()
predict = gd.predict(df_test, model, binary, True)
print predict
error_test = mystats.get_error(predict, df_test[Y], binary)
print 'error train {} error_test {}'.format(error_train, error_test)
return [error_train, error_test]
def testLogGradient2():
X = np.random.random(size=[10, 2])
y = utils.sigmoid(X[:, 0]* .5 + 2 * X[:, 1] + 3)
df = pd.DataFrame(data=X)
w = gd.logistic_gradient(df, y, .05)
print w
