【ML】线性回归 [多因子]（LinearRegression）实践（基于sklearn）

数据准备

使用数据：USA_Housing.csv

读取数据

import pandas as pd
import numpy as np
# 读取数据
origin_data = pd.read_csv('USA_Housing.csv')
print(type(origin_data))
# 删除无用的列
data = origin_data.drop(columns=['Address'])
data.head()

输出：

<class 'pandas.core.frame.DataFrame'>

	Avg. Area Income	Avg. Area House Age	Avg. Area	Number of Rooms	Avg. Area Number of Bedrooms	Area Population Price
0	79545.45857	5.682861	7.009188	4.09	23086.80050	1.059034e+06
1	79248.64245	6.002900	6.730821	3.09	40173.07217	1.505891e+06
2	61287.06718	5.865890	8.512727	5.13	36882.15940	1.058988e+06
3	63345.24005	7.188236	5.586729	3.26	34310.24283	1.260617e+06
4	59982.19723	5.040555	7.839388	4.23	26354.10947	6.309435e+05

绘制图表（观察数据规律）

# 观察数据
from matplotlib import pyplot as plt
plt.subplot(231)
plt.scatter(data.loc[:,'Avg. Area Income'], data.loc[:,'Price'])
plt.title('Income')

plt.subplot(232)
plt.scatter(data.loc[:,'Avg. Area House Age'], data.loc[:,'Price'])
plt.title('Age')

plt.subplot(233)
plt.scatter(data.loc[:,'Avg. Area Number of Rooms'], data.loc[:,'Price'])
plt.title('Rooms')

plt.subplot(234)
plt.scatter(data.loc[:,'Avg. Area Number of Bedrooms'], data.loc[:,'Price'])
plt.title('Bedrooms')

plt.subplot(235)
plt.scatter(data.loc[:,'Area Population'], data.loc[:,'Price'])
plt.title('Population')

单因子训练（为了做对比）

# rooms单因子测试
from sklearn.linear_model import LinearRegression
x_1 = data.loc[:,'Avg. Area Number of Rooms']
x_1 = np.array(x_1).reshape(-1,1);
y = data.loc[:,'Price']
lr_1 = LinearRegression()
lr_1.fit(x_1, y)

预测+评估（单因子）

# 预测+评估
y_predict_1 = lr_1.predict(x_1)
# 评估 MSE，r2
from sklearn.metrics import mean_squared_error, r2_score
MSE_1 = mean_squared_error(y,y_predict_1)
r2_score_1 = r2_score(y,y_predict_1)
print(MSE_1, r2_score_1)

输出：

110620797457.445  0.11267062524906302

显然，r2_score只有0.11效果很差

多因子训练

#使用多因子方式
lr_mutil = LinearRegression()
x_mutil = data.drop(['Price'], axis=1)
lr_mutil.fit(x_mutil, y)

预测+评估（多因子）

# 预测
y_mutil_predict = lr_mutil.predict(x_mutil)
# 评估 MSE，r2
MSE_mutil = mean_squared_error(y,y_mutil_predict)
r2_mutil_score = r2_score(y,y_mutil_predict)
print(MSE_mutil, r2_mutil_score)

输出

10219734313.031612  0.9180238195119546

r2_score达到了0.918效果提升明显

图形展示

查看y和y_mutil_predict的聚合程度，聚合度越高越好

# 图形展示
plt.figure(figsize=(4,4))
plt.scatter(y_mutil_predict,y)