机器学习_线性回归最小二乘法求解

import sklearn.datasets as data
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import matplotlib as mpl


class LinearRegression:
    def __init__(self):
        pass

    def fit(self, X, y):
        X = np.asmatrix(X.copy())
        y = np.asmatrix(y).reshape(-1, 1)
        self.w_ = (X.T * X).I * X.T * y

    def predict(self, X):
        X = np.asmatrix(X.copy())
        result = X * self.w_
        return np.array(result).ravel()


if __name__ == '__main__':
    boston = data.load_boston()
    col_names = np.append(boston.feature_names, 'MEDV')
    data = pd.DataFrame(data=np.c_[boston.data, boston.target], columns=col_names)
    t = data.sample(len(data), random_state=0)
    # 增加一列 但是在最后添加 故不使用
    # t['ddd'] = 1
    # 往前面增加一列的方法
    print(t)
    newColumns = t.columns.insert(0, 'intercept')
    # 注意必须更新一下，否则会出现添加到最后一列的效果
    t = t.reindex(columns=newColumns)
    t['intercept'] = 1
    # print(t)
    train_x = t.iloc[:400, :-1]
    train_y = t.iloc[:400, -1].values
    test_x = t.iloc[400:, :-1]
    test_y = t.iloc[400:, -1].values
    print(test_y)
    # print(train_x)
    Lr = LinearRegression()
    Lr.fit(train_x, train_y)
    result = Lr.predict(test_x)
    # print(result)
    # print(np.mean((result - test_y) ** 2))
    # print(Lr.w_)
    print(result)
    print(test_y)
    mpl.rcParams['font.family'] = 'SimHei'
    mpl.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(10, 10))
    plt.plot(result, "ro-", label='预测值')
    plt.plot(test_y, "go-", label='真实值')
    plt.title('线性回归预测')
    plt.xlabel('样本个数')
    plt.ylabel('房价')
    plt.legend()
    plt.show()