机器学习--线性回归算法预测房价

算法原理：线性回归算法、最小均方差、梯度下降算法参考：http://blog.kamidox.com/gradient-descent.html

里面非常详细地介绍了微积分基本运算法则、线性回归算法、梯度下降算法及改进。

a. 用线性回归方法拟合正弦函数

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np

# 生成200个[-2pi,2pi]区间内的正弦函数上的点
n_dots =200
X = np.linspace(-2*np.pi,2*np.pi,n_dots)
Y = np.sin(X)+0.2*np.random.rand(n_dots)-0.1
X = X.reshape(-1,1)
Y = Y.reshape(-1,1)

from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline

def polynomial_model(degree=1):
    # degree表示多项式的阶数
    polynomial_features = PolynomialFeatures(degree=degree,include_bias=False)
    # normalize=True将特征归一化至[0,1]
    linear_regression = LinearRegression(normalize=True)
    pipeline = Pipeline([("polynomial_features",polynomial_features),("linear_regression",linear_regression)])
    return pipeline

# 分别用2、3、5、10阶多项式来拟合数据集
# 用mean_squared_error计算均方根误差，均方根误差越小，说明模型拟合效果越好
from sklearn.metrics import mean_squared_error

degrees = [2,3,5,10]
results=[]
for d in degrees:
    model = polynomial_model(degree=d)
    model.fit(X,Y)
    train_score = model.score(X,Y)
    mse = mean_squared_error(Y,model.predict(X))
    results.append({"model":model,"degree":d,"score":train_score,"mse":mse})
for r in results:
    print("degree: {}; train_score: {}; m