def testBinary():
not_binary = [5,6,7]
binary = [1,0,1]
df = pd.DataFrame({'not_binary': not_binary, 'binary': binary})
print df['not_binary']
nb_result = utils.check_binary(df['not_binary'])
b_result = utils.check_binary(df['binary'])
print 'not binary: {} binary: {}'.format(nb_result, b_result)
def dec_or_reg_tree(df_train, df_test, Y):
binary = utils.check_binary(df_train[Y])
if binary:
newtree = treeHW4.TreeOptimal(max_depth=1)
y = list(df_train[Y])
nondf_train = utils.pandas_to_data(df_train)
nondf_test = utils.pandas_to_data(df_test)
newtree.fit(nondf_train, y)
predict = newtree.predict(nondf_train)
error_train = mystats.get_error(predict, y, binary)
y = utils.pandas_to_data(df_test[Y])
predict = newtree.predict(nondf_test)
error_test = mystats.get_error(predict, y)
else:
node = mytree.Node(np.ones(len(df_train)))
hw1.branch_node(node, df_train, 5, Y)
model = mytree.Tree(node)
predict = model.predict_obj()
error_train = mystats.get_error(predict, df_train[Y], binary)
node.presence = np.ones(len(df_test))
hw1.test_node(node, df_test, Y)
test_tree = mytree.Tree(node)
predict = test_tree.predict_obj()
error_test = mystats.get_error(predict, df_test[Y], binary)
return [error_train, error_test]
def linear_gd_error(df, Y):
binary = utils.check_binary(df[Y])
model = gd.gradient(df, df[Y], 0.00001, max_iterations=50)
print model
predict = gd.predict(df, model, binary)
print predict
error = mystats.get_error(predict, df_train[Y], binary)
return error
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 linear_gd(df_train, df_test, Y):
""" linear gradient descent """
binary = utils.check_binary(df_train[Y])
model = gd.gradient(df_train, df_train[Y], 0.00001, max_iterations=50)
print model
predict = gd.predict(df_train, model, binary)
print predict
error_train = mystats.get_error(predict, df_train[Y], binary)
predict = gd.predict(df_test, model, binary)
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 linear_reg_errors(df_train, df_test, Y, ridge=False, sigmoid=False):
binary = utils.check_binary(df_train[Y])
error_train = linear_reg(df_train, Y, binary, ridge, sigmoid)
error_test = linear_reg(df_test, Y, binary, ridge, sigmoid)
return [error_train, error_test]
