python机器学习09 多元线性回归(波士顿房价预测)

多元线性回归(波士顿房价预测)

导入模块

1554348229334

import pandas as pd

import matplotlib.pyplot as plt

from matplotlib.font_manager import FontProperties

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

%matplotlib inline

font = FontProperties(fname='/Library/Fonts/Heiti.ttc')

获取数据

df = pd.read_csv('housing-data.txt', sep='\s+', header=0)

X = df.iloc[:, :-1].values

y = df['MEDV'].values

# 将数据分成训练集（0.7）和测试集（0.3）

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

训练模型

lr = LinearRegression()

# 训练模型

lr.fit(X_train, y_train)

# 预测训练集数据

y_train_predict = lr.predict(X_train)

# 预测测试集数据

y_test_predict = lr.predict(X_test)

可视化

# y_train_predict-y_train训练数据误差值

plt.scatter(y_train_predict, y_train_predict-y_train, c='r',

            marker='s', edgecolor='white', label='训练数据')

# y_train_predict-y_train测试数据误差值

plt.scatter(y_test_predict, y_test_predict-y_test, c='g',

            marker='o', edgecolor='white', label='测试数据')

plt.xlabel('预测值', fontproperties=font)

plt.ylabel('误差值', fontproperties=font)

# 可视化y=0的一条直线即误差为0的直线

plt.hlines(y=0, xmin=-10, xmax=50, color='k')

plt.xlim(-10, 50)

plt.legend(prop=font)

plt.show()

png

均方误差测试

from sklearn.metrics import mean_squared_error

# 训练集的均方误差

train_mse = mean_squared_error(y_train,y_train_predict)

# 测试集的均方误差

test_mse = mean_squared_error(y_test,y_test_predict)

print('训练集的均方误差:{}'.format(train_mse))

print('测试集的均方误差:{}'.format(test_mse))

训练集的均方误差:23.049177061822277

测试集的均方误差:19.901828312902534

  训练集的均方误差是19.4，而测试集的均方误差是28.4，可以发现测试集的误差更大了，也就是说训练集过拟合了。