『数据挖掘』scikit-learn包的进阶学习笔记——第二章：线性回归

代码部分参考：2-linear-regression

# coding:utf-8
__author__ = "LCG22_2016_05_30"

import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties

# font = FontProperties(fname=r"C:\Users\LCG22\Desktop\work\learn\Python\PythonLearn\DataSet\learn_data_set\pizza.xlsx", size=10)
# print font

def runplt():
    plt.figure()
    # plt.title("匹萨价格与直径数据", fontproperties=font)
    # plt.xlabel("直径（英寸）", fontproperties=font)
    # plt.ylabel("价格（美元）", fontproperties=font)
    plt.title("1")
    plt.xlabel("2")
    plt.ylabel("3")
    plt.axis([0, 25, 0, 25])
    plt.grid(True)
    return plt
plt = runplt()
x = [[6], [8], [10], [14], [18]]
y = [[7], [9], [13], [17.5], [18]]
plt.plot(x, y, "k.")
#plt.show()

from sklearn.linear_model import LinearRegression

# 创建并拟合模型
model = LinearRegression()
model.fit(x, y)
print ("预测一张12英寸匹萨价格：$%.2f" % model.predict([12])[0])

plt = runplt()
plt.plot(x, y, "k.")
x2 = [[0], [10], [14], [25]]
model = LinearRegression()
model.fit(x, y)
y2 = model.predict(x2)
plt.plot(x, y, "k.")
plt.plot(x2, y2, "g-")

# 残差预测值
yr = model.predict(x)
for idx, x_value in enumerate(x):
    plt.plot([x_value, x_value], [y[idx], yr[idx]], "r-")

#plt.show()

import numpy as np
print "残差平方和： %.2f" % np.mean((model.predict(x) - y) ** 2)