Threading Regression of machine learning

Linear regression formula:

Import pandas as PD
import matplotlib.pyplot as plt

columns = ["mpg", "cylinders", "displacement", "horsepower", "" Weight "," acceleration "," model year "," origin "," car name "]
#由于原使数据只有数据, so columns is to add them to the category of columns, delim_ Whitespace represents a space as a separator for
cars = pd.read_table ("D:\\test\machinelearning\\auto-mpg.data", Delim_whitespace=true, Names=columns)
Cars.head (2)

Year Car

	mpg	Cylinders	Displacement	horsepower	Weight	Acceleration	Model	Origin	name
0	18.0	8	307.0	130.0	3504.0	12.0	70	1	Chevrolet Chevelle Malibu
1	15.0	8	350.0	165.0	3693.0	11.5	70	1	Buick Skylark 320

Fig = plt.figure ()
ax1=fig.add_subplot (2,1,1)
cars.plot ("Weight", "mpg", kind= "scatter", ax=ax1)
Plt.show ()

Import Sklearn from 
sklearn.linear_model import linearregression

lr =linearregression (); #获取线性回归模型
Lr.fit (cars[["weight"]], cars["mpg") #输入是重量, the output is the distance per gallon to run, training it
prediction = lr.predict (cars[["Weight"]) #训练完后 , you can test with test data to see what the predicted output value is, for the convenience of still using the training data
print (Prediction[0:5])
print (cars["mpg"][0:5])

[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

Plt.scatter (cars["Weight"],cars["mpg"],c= ' red ')
plt.scatter (cars["Weight"],prediction,c= ' blue ')
Plt.show ()

From sklearn.metrics import mean_squared_error
MSE = mean_squared_error (cars["mpg"],prediction) #求真实值与预测值之间的均方差
Print (MSE)

18.7809397346

mse**0.5 #再开根号

4.3336981591509574