01_家庭用电预测：线性回归算法(时间与功率&功率与电流之间的关系)

# 引入所需要的全部包
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
from pandas import DataFrame
import time

## 设置字符集，防止中文乱码
mpl.rcParams['font.sans-serif']=[u'simHei']
mpl.rcParams['axes.unicode_minus']=False

# 加载数据
# 日期、时间、有功功率、无功功率、电压、电流、厨房用电功率、洗衣服用电功率、热水器用电功率
path1='datas/household_power_consumption_1000.txt'
df = pd.read_csv(path1, sep=';', low_memory=False)#没有混合类型的时候可以通过low_memory=F调用更多内存，加快效率）

df.head() ## 获取前五行数据查看查看

Date	Time	Global_active_power	Global_reactive_power	Voltage	Global_intensity	Sub_metering_1	Sub_metering_2	Sub_metering_3
0	16/12/2006	17:24:00	4.216	0.418	234.84	18.4	0.0	1.0	17.0
1	16/12/2006	17:25:00	5.360	0.436	233.63	23.0	0.0	1.0	16.0
2	16/12/2006	17:26:00	5.374	0.498	233.29	23.0	0.0	2.0	17.0
3	16/12/2006	17:27:00	5.388	0.502	233.74	23.0	0.0	1.0	17.0
4	16/12/2006	17:28:00	3.666	0.528	235.68	15.8	0.0	1.0	17.0

# 查看格式信息
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 9 columns):
Date