ml100days-serialize-2

‘2019/Jan/15/Tue 09:24:50’

​

机器学习100天——第二天：简单线性回归

第一步：数据预处理

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

datasets = pd.read_csv("../datasets/studentscores.csv")
datasets.head()
Hours	Scores
0	2.5	21
1	5.1	47
2	3.2	27
3	8.5	75
4	3.5	30

X = datasets.iloc[:,:1].values
Y = datasets.iloc[:,1].values
X,Y
​
(array([[2.5],
        [5.1],
        [3.2],
        [8.5],
        [3.5],
        [1.5],
        [9.2],
        [5.5],
        [8.3],
        [2.7],
        [7.7],
        [5.9],
        [4.5],
        [3.3],
        [1.1],
        [8.9],
        [2.5],
        [1.9],
        [6.1],
        [7.4],
        [2.7],
        [4.8],
        [3.8],
        [6.9],
        [7.8]]),
 array([21, 47, 27, 75, 30, 20, 88, 60, 81, 25, 85, 62, 41, 42, 17, 95, 30,
        24, 67, 69, 30, 54, 35, 76, 86], dtype=int64))

from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size = 1/4,random_state = 0 )

训练线性回归

from sklearn.linear_model import LinearRegression
#使用训练集对模型进行训练
regressor = LinearRegression()
regressor = regressor.fit(X_train, Y_train)

Y_pred = regressor.predict(X_test)

可视化

训练集结果可视化

​

#散点图
plt.scatter(X_train , Y_train, color = 'red')
#线图
plt.plot(X_train , regressor.predict(X_train), 'bo-')
plt.show()

测试集结果可视化

#散点图
plt.scatter(X_test , Y_test, color = 'red')
#线图
plt.plot(X_test ,Y_pred, 'bo-')
plt.show()

​