import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.preprocessing import MinMaxScaler

data =pd.read_excel("数据.xlsx",header=None)
data0=np.array(data.iloc[:1400,1])

#定义x、y散点坐标
x = range(1,1401)
y = data0

#用n次多项式拟合
f1 = np.polyfit(x,y,3)

p1 = np.poly1d(f1)

#也可使用yvals=np.polyval(f1, x)
yvals = p1(x)  #拟合y值

#绘图
plt.figure(figsize=(10, 8))
plot1 = plt.plot(x, y, '.',label='original values')
plot2 = plt.plot(x, yvals, 'r',label='polyfit values')
plt.xlabel('x')
plt.ylabel('y')
plt.legend(loc=4) #指定legend的位置右下角
plt.title('polyfitting')
plt.show()



def mape(y_true, y_pred):
    """
    参数:
    y_true -- 测试集目标真实值
    y_pred -- 测试集目标预测值

    返回:
    mape -- MAPE 评价指标
    """

    n = len(y_true)
    mape = sum(np.abs((y_true - y_pred) / y_true)) / n * 100
    return mape


def mae_value(y_true, y_pred):
    """
    参数:
    y_true -- 测试集目标真实值
    y_pred -- 测试集目标预测值

    返回:
    mae -- MAE 评价指标
    """

    n = len(y_true)
    mae = sum(np.abs(y_true - y_pred)) / n
    return mae
def mse(y_true, y_pred):
    error = []
    for k in range(len(y_pred)):
        error.append(y_true[k] - y_pred[k])
    squaredError = []
    absError = []
    for val in error:
        squaredError.append(val * val)  # target-prediction之差平方
        absError.append(abs(val))  # 误差绝对值
    MSE = sum(squaredError) / len(squaredError)
    return MSE
def sse(y_true, y_pred):
    sse = np.sum((y_true - y_pred) ** 2)
    return sse

def r2(y_true, y_pred):
    sst = np.sum((y_true - np.mean(y_true)) ** 2)
    r2 = 1 - (sse(y_true, y_pred) / sst)       # r2_score(y_actual, y_predicted, multioutput='raw_values')
    return r2
print("mape:",mape(y,yvals))
print("mse:",mse(y,yvals))
print("mae:",mae_value(y,yvals))
print("sse:",sse(y,yvals))
print("r2:",r2(y,yvals))

运行代码时显示如下：

 最后找出原因是数据里含有空白项，删除数据的空白即可 。