共享单车数据分析

#1.导包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
#解决中文显示问题
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei']
#
from datetime import datetime
import calendar
#画图的
import seaborn as sn

#2.数据采集/查看和处理
  #2.1数据读取
bikedata = pd.read_csv('train.csv')
bikedata.describe()

	season	holiday	workingday	casual	registered	count
count	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000	10886.000000
mean	2.506614	0.028569	0.680875	36.021955	155.552177	191.574132
std	1.116174	0.166599	0.466159	49.960477	151.039033	181.144454
min	1.000000	0.000000	0.000000	0.000000	0.000000	1.000000
25%	2.000000	0.000000	0.000000	4.000000	36.000000	42.000000
50%	3.000000	0.000000	1.000000	17.000000	118.000000	145.000000
75%	4.000000	0.000000	1.000000	49.000000	222.000000	284.000000
max	4.000000	1.000000	1.000000	367.000000	886.000000	977.000000

  #2.2数据查看
print(bikedata.shape)       #查看数据大小
print(bikedata.head())      #查看前5行数据
print(bikedata.dtypes)      #查看数据类型

(10886, 7)
        datetime  season  holiday  workingday  casual  registered  count
0  2011/1/1 0:00       1        0           0       3          13     16
1  2011/1/1 1:00       1        0           0       8          32     40
2  2011/1/1 2:00       1        0           0       5          27     32
3  2011/1/1 3:00       1        0           0       3          10     13
4  2011/1/1 4:00       1        0           0       0           1      1
datetime      object
season         int64
holiday        int64
workingday     int64
casual         int64
registered     int64
count          int64
dtype: object

  #2.3数据提取
    #2.3.1提取年月日                 #Series的apply方法对每个值调用函数
bikedata['date'] = bikedata.datetime.apply(lambda x:x.split()[0])
print(bikedata.head())

        datetime  season  holiday  workingday  casual  registered  count  \
0  2011/1/1 0:00       1        0           0       3          13     16   
1  2011/1/1 1:00       1        0           0       8          32     40   
2  2011/1/1 2:00       1        0           0       5          27     32   
3  2011/1/1 3:00       1        0           0       3          10     13   
4  2011/1/1 4:00       1        0           0       0           1      1   

       date  
0  2011/1/1  
1  2011/1/1  
2  2011/1/1  
3  2011/1/1  
4  2011/1/1  

    #2.3.2提取小时
bikedata['hour'] = bikedata.datetime.apply(lambda x:x.split()[1].split(':')[0])
print(bikedata.head())

        datetime  season  holiday  workingday  casual  registered  count  \
0  2011/1/1 0:00       1        0           0       3          13     16   
1  2011/1/1 1:00       1        0           0       8          32     40   
2  2011/1/1 2:00       1        0           0       5          27     32   
3  2011/1/1 3:00       1        0           0       3          10     13   
4  2011/1/1 4:00       1        0           0       0           1      1   

       date hour  
0  2011/1/1    0  
1  2011/1/1    1  
2  2011/1/1    2  
3  2011/1/1    3  
4  2011/1/1    4  

      #2.3.3在年月日的基础上提取星期几（格式化字符串）
bikedata['weekday']=bikedata.date.apply(lambda dateString:calendar.day_name[datetime.strptime(dateString,'%Y/%m/%d').weekday()])
print(bikedata.head())

        datetime  season  holiday  workingday  casual  registered  count  \
0  2011/1/1 0:00       1        0           0       3          13     16   
1  2011/1/1 1:00       1        0           0       8          32     40   
2  2011/1/1 2:00       1        0           0       5          2