100-Days-Of-ML twoday

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dataset = pd.read_csv(‘C:\Users\Administrator\Desktop\ml 100day\MLDayTwoData.csv’)
#創建X和Y,注意一點dataframe切片包左不包右
X = dataset.iloc[ : , :1].values
Y = dataset.iloc[ : ,1].values
#由於數據量小沒有存在髒數據一目瞭然，不需要percenttime統計空值異常值等
#直接進行數據切分,注意random_state選的數字一樣，那麼每次切分所得也都一樣
from sklearn.model_selection import train_test_split
#創建切分器對象
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.25,random_state=0)
from sklearn.linear_model import LinearRegression
#創建線型迴歸對象
lr = LinearRegression()
lr = lr.fit(X_train,Y_train)
#預測結果
Y_pred = lr.predict(X_test)
#Visualization可視化
#訓練集結果可視化
plt.scatter(X_train,Y_train)
plt.plot(X_train,lr.predict(X_train))
plt.show()

#測試集結果可視化
plt.scatter(X_test,Y_test)
plt.plot(X_test,lr.predict(X_test))
plt.show()