需要下載一個data：auto-mpg.data

第一步：顯示資料集圖

import pandas as pd
import matplotlib.pyplot as plt
columns = ["mpg","cylinders","displacement","horsepower","weight","acceleration","model year","origin","car name"]
cars = pd.read_table("E:/3_python_code/python_ml/data/auto-mpg.data",delim_whitespace=True,names=columns)
print (cars.head(5))
#加了兩個子圖
fig = plt.figure()
ax1 = fig.add_subplot(2,1,1)
ax2 = fig.add_subplot(2,1,2)
cars.plot("weight","mpg",kind="scatter",ax=ax1)
cars.plot("acceleration","mpg",kind="scatter",ax=ax2)
plt.show()
 

第二步：訓練並預測

import pandas as pd
import matplotlib.pyplot as plt
columns = ["mpg","cylinders","displacement","horsepower","weight","acceleration","model year","origin","car name"]
cars = pd.read_table("E:/3_python_code/python_ml/data/auto-mpg.data",delim_whitespace=True,names=columns)
# print (cars.head(5))
# #加了兩個子圖
fig = plt.figure()
# ax1 = fig.add_subplot(2,1,1)
# ax2 = fig.add_subplot(2,1,2)
# cars.plot("weight","mpg",kind="scatter",ax=ax1)
# cars.plot("acceleration","mpg",kind="scatter",ax=ax2)
# plt.show()

import sklearn
from sklearn.linear_model import  LinearRegression
lr = LinearRegression()
#訓練
lr.fit(cars[["weight"]],cars["mpg"])
#預測
predictions = lr.predict(cars[["weight"]])
from sklearn.metrics import mean_squared_error
#均方誤差
mse = mean_squared_error(cars["mpg"],predictions)
print(mse)
print(predictions[0:5])
print(cars["mpg"][0:5])
plt.scatter(cars["weight"],cars["mpg"],c="red")
plt.scatter(cars["weight"],predictions,c="blue")
plt.show()
 

輸出結果 顯示均方誤差18.78，如下

18.7809397346
[ 19.41852276  17.96764345  19.94053224  19.96356207  19.84073631]
0    18.0
1    15.0
2    18.0
3    16.0
4    17.0
Name: mpg, dtype: float64
Process finished with exit code 0

![在這裡插入圖片描述](https://img-blog.csdnimg.cn/20181127115834245.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMyMTY2Nzc5,size_16,color_FFFFFF,t_70)