算法001.机器学习其它资料机器学习100天

简单线性回归实现

Catalogue
  1. 第一步：数据预处理
  2. 第二步：训练集使用简单线性回归模型来训练
  3. 第三步：预测结果
  4. 第四步：可视化

第一步：数据预处理

1
2
3
4
5
6
7
8
9
10
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

dataset = pd.read_csv('studentscores.csv')
X = dataset.iloc[ : ,   : 1 ].values
Y = dataset.iloc[ : , 1 ].values

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)

第二步：训练集使用简单线性回归模型来训练

1
2
3
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor = regressor.fit(X_train, Y_train)

第三步：预测结果

1
Y_pred = regressor.predict(X_test)

第四步：可视化

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.model_selection import KFold
from sklearn.model_selection import train_test_split


dataset = pd.read_csv('~/Documents/100-Days-Of-ML-Code/datasets/studentscores.csv')
X = dataset.iloc[ : ,   : 1 ].values
Y = dataset.iloc[ : , 1 ].values

X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size = 1/4, random_state = 0) 

from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor = regressor.fit(X_train, Y_train)

Y_pred = regressor.predict(X_test)

plt.scatter(X_train , Y_train, color = 'red')
plt.plot(X_train , regressor.predict(X_train), color ='blue')
plt.show()

plt.scatter(X_test , Y_test, color = 'red')
plt.plot(X_test , regressor.predict(X_test), color ='blue')
plt.show()