Linux Git-Repository Analyse

In [6]:

    

import pandas as pd

git_log = pd.read_csv("../dataset/git_demo_timestamp_linux.gz")
git_log.head()


    

    
Out[6]:







  

    

      

      
timestamp
      
author
    
  
  

    

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

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

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

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

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

In [7]:

    

top10 = git_log.author.value_counts().head(10)
top10


    

    
Out[7]:





Linus Torvalds           24259
David S. Miller           9563
Mark Brown                6917
Takashi Iwai              6293
Al Viro                   6064
H Hartley Sweeten         5942
Ingo Molnar               5462
Mauro Carvalho Chehab     5384
Arnd Bergmann             5305
Greg Kroah-Hartman        4687
Name: author, dtype: int64

In [12]:

    

%matplotlib inline
top10.plot.pie(title="TOP 10 committer", label="", figsize=[7,7])


    

    
Out[12]:





<matplotlib.axes._subplots.AxesSubplot at 0x21281c339b0>






    

In [9]:

    

git_log.timestamp = pd.to_datetime(git_log.timestamp)
git_log.head()


    

    
Out[9]:







  

    

      

      
timestamp
      
author
    
  
  

    

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

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

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

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

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

In [10]:

    

git_log.timestamp.dt.hour.value_counts(sort=False).plot.bar()


    

    
Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x21281b06748>