Python纯代码通过神经网络实现线性回归的拟合方式

# -*- coding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
class SimpleDataReader(object):
    def __init__(self, data_file):
        self.train_file_name = data_file
        self.num_train = 0
        self.XTrain = None
        self.YTrain = None
    # read data from file
    def ReadData(self):
        # data = np.load(self.train_file_name)
        # self.XTrain = data["data"]
        # self.YTrain = data["label"]
        self.XTrain = np.array([0.95, 3, 4, 5.07, 6.03, 8.21, 8.85, 12.02, 15], dtype=float)
        self.YTrain = np.array([5.1, 8.7, 11.5, 13, 15.3, 18, 21, 26.87, 32.5], dtype=float)
        self.num_train = self.XTrain.shape[0]
        #end if
    # get batch training data
    def GetSingleTrainSample(self, iteration):
        x = self.XTrain[iteration]
        y = self.YTrain[iteration]
        return x, y
    def GetWholeTrainSamples(self):
        return self.XTrain, self.YTrain
class NeuralNet(object):
    def __init__(self, eta):
        self.eta = eta
        self.w = 0
        self.b = 0
    def __forward(self, x):
        z = x * self.w + self.b
        return z
    def __backward(self, x,y,z):
        dz = z - y                  # 原错误为：dz = x * (z - y)
        db = dz
        dw = dz
        return dw, db
    def __update(self, dw, db):
        self.w = self.w - self.eta * dw
        self.b = self.b - self.eta * db
    def train(self, dataReader):
        for i in range(dataReader.num_train):
            # get x and y value for one sample
            x,y = dataReader.GetSingleTrainSample(i)
            # get z from x,y
            z = self.__forward(x)
            # calculate gradient of w and b
            dw, db = self.__backward(x, y, z)
            # update w,b
            self.__update(dw, db)
            # end for
    def inference(self, x):
        return self.__forward(x)
if __name__ == '__main__':
    # read data
    sdr = SimpleDataReader('ch04.npz')
    sdr.ReadData()
    # create net
    eta = 0.1
    net = NeuralNet(eta)
    net.train(sdr)
    # result
    print("w=%f,b=%f" %(net.w, net.b))
    # 绘图部分
    trainX,trainY = sdr.GetWholeTrainSamples()
    fig = plt.figure()
    ax = fig.add_subplot(111)
    # 绘制散点图
    ax.scatter(trainX,trainY)
    # 绘制线性回归
    x = np.arange(0, 15, 0.01)
    f = np.vectorize(net.inference, excluded=['x'])
    plt.plot(x,f(x),color='red')
    # 显示图表
    plt.show()

#1．数据获取
import pandas as pd
data = pd.read_excel('运力数据表.xlsx')
x = data.iloc[:20,:4]
y = data.iloc[:20,4:]
#2．导入线性回归模块,简称为LR
from sklearn.linear_model import LinearRegression as LR
lr = LR()             #创建线性回归模型类
lr.fit(x,y)         #拟合
slr=lr.score(x,y)   #判定系数 R^2
c_x=lr.coef_         #x对应的回归系数
c_b=lr.intercept_   #回归系数常数项
#3．预测
x1 = data.iloc[20:,:4]
r1=lr.predict(x1)    #采用自带函数预测
#print('x回归系数为：',c_x)
#print('回归系数常数项为：',c_b)
#print('判定系数为：',slr)
#print('样本预测值为：',r1)
n=list(data["公里客运量（万人）"])
n.extend(r1[:,0])
num=pd.DataFrame(n).dropna()
g=list(data["公里货运量（万吨）"])
g.extend(r1[:,1])
gravity=pd.DataFrame(g).dropna()
import pandas as pd
import matplotlib.pyplot as plt  #导入绘图库中的pyplot模块,并且简称为plt
#构造绘图所需的横轴数据列和纵轴数据列
#在figure界面上绘制线性图
plt.rcParams['font.sans-serif'] = 'SimHei'     #设置字体为SimHei
plt.figure(1)
plt.plot(data["年份"],num,'r*--')  #红色“*”号连续图,
plt.xlabel('日期')
plt.ylabel('公里客运量（万人')
plt.title('公里客运量（万人)走势图')
plt.xticks(data["年份"],rotation = 45)
plt.savefig('myfigure1')
plt.figure(2)
plt.plot(data["年份"],gravity,'b*--')  #红色“*”号连续图,
plt.xlabel('日期')
plt.ylabel('公里货运量（万吨）')
plt.title('公里货运量（万吨）走势图')
plt.xticks(data["年份"],rotation = 45)
plt.savefig('myfigure2')
from sklearn.neural_network import MLPRegressor 
clf = MLPRegressor(solver='lbfgs', alpha=1e-5,hidden_layer_sizes=8, random_state=1) 
clf.fit(x, y);   
rv=clf.score(x,y)
r2=clf.predict(x1)   
print('样本预测值为：',r2)
n2=list(data["公里客运量（万人）"])
n2.extend(r2[:,0])
num2=pd.DataFrame(n2).dropna()
g2=list(data["公里货运量（万吨）"])
g2.extend(r2[:,1])
gravity2=pd.DataFrame(g2).dropna()