def main():
data = pd.read_csv('input' + os.sep + 'salary.csv')
X = data['experience']
Y = data['salary']
path = 'output' + os.sep + 'gradient_descent.csv'
step = 0.005
print("step:", step)
threshold = gen_threshold(Y, 0.001)
print("threshold:", threshold)
max_loop_num = 1000
print("max_loop_num:", max_loop_num)
train(X, Y, path, step, threshold, max_loop_num)
Y_pred = predict(path, X)
draw_graph(X, Y, Y_pred)
Y = np.array(Y).reshape((len(Y), 1))
Y_pred = np.array(Y_pred).reshape((len(Y_pred), 1))
rmse_ration = calculate_rmse_ration(Y, Y_pred)
print("rmse ratio:", rmse_ration)
return
def main():
data = pd.read_csv('input' + os.sep + 'salary.csv')
experiences = np.array(data['experience'])
salaries = np.array(data['salary'])
# 将特征数据集分为训练集和测试集，除了最后 4 个作为测试用例，其他都用于训练
X_train = experiences[:7]
X_train = X_train.reshape(-1,1)
X_test = experiences[7:]
X_test = X_test.reshape(-1,1)
# 把目标数据（特征对应的真实值）也分为训练集和测试集
y_train = salaries[:7]
y_test = salaries[7:]
model_file_path = "output" + os.sep + "linear_regression_model.sav"
train(X_train, y_train, model_file_path)
y_predicted = predict(X_test, model_file_path)
rmse_ration = calculate_rmse_ration(y_test, y_predicted)
print("rmse ratio:", rmse_ration)
draw_graph(X_test, y_test, y_predicted)
def main():
model_file_path = "output" + os.sep + "linear_regression_model_mv.sav"
ignored_columns = ['ZN', 'CHAS', 'NOX', 'RM', 'DIS', 'RAD', 'TAX', 'PIRATIO', 'B', 'LSTAT']
X, Y = load_data('input' + os.sep + 'housing.csv', False, ignored_columns)
X = preprocess(X, "normalize")
X_train, y_train, X_test, y_test = split_dataset(X, Y)
train(X_train, y_train, model_file_path)
y_predicted = predict(X_test, model_file_path)
rmse_ration = calculate_rmse_ration(y_test, y_predicted)
print("rmse ratio:", rmse_ration)
def main(input_path, output_path, ignored_columns, preprocess_type,
training_data_rate, step_length, threshold_rate, max_loop_num,
dynamic_step):
print("input:", input_path)
print("output:", output_path)
print("\n")
if ignored_columns is not None:
print("ignored_columns:", ignored_columns)
print("\n")
print("preprocess_type:", preprocess_type)
print("training_data_rate:", training_data_rate)
print("\n")
print("threshold_rate:", threshold_rate)
print("max_loop_num:", max_loop_num)
print("step_length:", step_length)
if dynamic_step:
print("dynamic stepping ...")
else:
print("static stepping ...")
print("\n")
start_time = datetime.now()
X, Y = load_data(input_path, True, ignored_columns)
X = preprocess(X, preprocess_type)
X_train, y_train, X_test, y_test = split_dataset(X, Y, training_data_rate)
threshold = gen_threshold(Y, threshold_rate)
train(X_train, y_train, output_path, step_length, threshold, max_loop_num,
dynamic_step)
Y_pred = predict(output_path, X_test)
rmse_ration = calculate_rmse_ration(y_test, Y_pred)
print("rmse ratio (rmse / y_mean) is:", rmse_ration, "\n")
end_time = datetime.now()
execution_duration = end_time - start_time
print("execution duration:", execution_duration, "\n")
return
def main():
data = pd.read_csv('input' + os.sep + 'salary.csv')
X = data['experience']
Y = data['salary']
path = 'output' + os.sep + 'lsm.csv'
lsm(X, Y, path)
Y_pred = predict(path, X)
draw_graph(X, Y, Y_pred)
Y = np.array(Y).reshape((len(Y), 1))
rmse_ration = calculate_rmse_ration(Y, Y_pred)
print("rmse ratio:", rmse_ration)
return
def main():
ignored_columns = [
'ZN', 'CHAS', 'NOX', 'RM', 'DIS', 'RAD', 'TAX', 'PIRATIO', 'B', 'LSTAT'
]
X, Y = load_data('input' + os.sep + 'housing.csv', True, ignored_columns)
X = preprocess(X, "normalize")
X_train, y_train, X_test, y_test = split_dataset(X, Y)
path = 'output' + os.sep + 'lsm_multivariant.csv'
lsm(X_train, y_train, path)
y_predicted = predict(path, X_test)
rmse_ration = calculate_rmse_ration(y_test, y_predicted)
print("rmse ratio:", rmse_ration)
return