In [3]:

    

%matplotlib inline
import pandas as pd

df = pd.read_csv("../../../linux/git_demo_timestamp.csv", sep=";")
df.describe()


    

    
Out[3]:







  

    

      

      
timestamp_local
      
author
    
  
  

    

      
count
      
723214
      
723213
    
    

      
unique
      
691746
      
17877
    
    

      
top
      
2017-11-01 03:56:19
      
Linus Torvalds
    
    

      
freq
      
137
      
24259
    
  

In [5]:

    

df.author.value_counts().head(10).plot(kind='pie', figsize=(8,8))


    

    
Out[5]:





<matplotlib.axes._subplots.AxesSubplot at 0x26331d22518>






    

In [9]:

    

df['ts'] = pd.to_datetime(df.timestamp_local)
df.head()


    

    
Out[9]:







  

    

      

      
timestamp_local
      
author
      
timelocal_date
      
ts
    
  
  

    

      
0
      
2017-12-31 14:47:43
      
Linus Torvalds
      
2017-12-31 14:47:43
      
2017-12-31 14:47:43
    
    

      
1
      
2017-12-31 13:13:56
      
Linus Torvalds
      
2017-12-31 13:13:56
      
2017-12-31 13:13:56
    
    

      
2
      
2017-12-31 13:03:05
      
Linus Torvalds
      
2017-12-31 13:03:05
      
2017-12-31 13:03:05
    
    

      
3
      
2017-12-31 12:30:34
      
Linus Torvalds
      
2017-12-31 12:30:34
      
2017-12-31 12:30:34
    
    

      
4
      
2017-12-31 12:29:02
      
Linus Torvalds
      
2017-12-31 12:29:02
      
2017-12-31 12:29:02
    
  

In [13]:

    

df.ts.dt.hour.value_counts(sort=False).plot(kind='bar')


    

    
Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x26328e932b0>