线性回归

import matplotlib.pyplot as plt
import numpy as np
#读取的是sklearn自带的数据集
from sklearn import datasets
class LinearRegression():
    def __init__(self):
        self.w = None

    def fit(self, X, y):
        #在第0列填充1
        X = np.insert(X, 0, 1, axis=1) 
        print(X.shape)
        #X.T.dot(X) 求逆运算 没有考虑矩阵的逆不存在的情况
        X_ = np.linalg.inv(X.T.dot(X))
        self.w = X_.dot(X.T).dot(y)
        

    def predict(self, X):
        # Insert constant ones for bias weights
        X = np.insert(X, 0, 1, axis=1)
        y_pred = X.dot(self.w)
        return y_pred
def mean_squared_error(y_true, y_pred):
    #np.power数组元素求n次方
    mse = np.mean(np.power(y_true - y_pred, 2))
    return mse
def main():
    # Load the diabetes dataset
    diabetes = datasets.load_diabetes()
    #print(diabetes)
    #diabetes没有shape的属性
    #print(diabetes.shape) AttributeError: shape
    # Use only one feature
    #X = diabetes.data[:, 2]直接取到的是一个一维的数据，要把它变成n*1二维数组的形式，需在列上增加维度
    X = diabetes.data[:, np.newaxis, 2]
    
    print (X.shape)
    # Split the data into training/testing sets
    #X[:-20]从头开始到倒数第20行
    x_train, x_test = X[:-20], X[-20:]

    # Split the targets into training/testing sets
    y_train, y_test = diabetes.target[:-20], diabetes.target[-20:]

    clf = LinearRegression()
    clf.fit(x_train, y_train)
    y_pred = clf.predict(x_test)

    # Print the mean squared error
    print ("Mean Squared Error:", mean_squared_error(y_test, y_pred))

    # Plot the results
    plt.scatter(x_test[:,0], y_test,  color='black')
    plt.plot(x_test[:,0], y_pred, color='y', linewidth=3)
    plt.show()

执行main函数：main()

运行结果