In [1]:

    

import pandas as pd
import networkx as nx
%matplotlib inline


    

In [28]:

    

def authors_full(path):
    authors = pd.read_csv(path + '/author-churn.csv', parse_dates=True, index_col='author')
    authors = authors / authors.sum()

    summary = pd.read_csv(path + '/summary.csv', parse_dates=True)
    main_dev = pd.read_csv(path + '/main-dev.csv', parse_dates=True)
    dev = main_dev[['main-dev', 'ownership']].groupby('main-dev').sum()  / summary['value'][2]
    dev = dev / dev.sum()
    dev = dev.reset_index()
    dev.columns = ['author', 'ownership']
    dev = dev.set_index('author')

    communication = pd.read_csv('data/communication.csv')
    G=nx.from_pandas_dataframe(communication, 'author', 'peer', ['strength'])
    page_rank = pd.DataFrame.from_dict(nx.pagerank(G, weight='strength'), orient='index')
    page_rank.columns = ['page_rank']

    summary = pd.read_csv(path + '/summary.csv', parse_dates=True)
    refactoring_main_dev = pd.read_csv(path + '/refactoring-main-dev.csv', parse_dates=True)
    refactoring_dev = refactoring_main_dev[['main-dev', 'ownership']].groupby('main-dev').sum()  / summary['value'][2]
    refactoring_dev = refactoring_dev / refactoring_dev.sum()
    refactoring_dev = refactoring_dev.reset_index()
    refactoring_dev.columns = ['author', 'refactoring_ownership']
    refactoring_dev = refactoring_dev.set_index('author')

    return pd.concat([dev, refactoring_dev, page_rank, authors], axis='author').fillna(0)


    

In [29]:

    

data_dir = 'data/repos/'
authors_full(data_dir + 'golang/go').corr()


    

    




/home/janisz/anaconda2/lib/python2.7/site-packages/networkx/generators/stochastic.py:56: UserWarning: zero out-degree for node Sagar Mehta
  warnings.warn('zero out-degree for node %s' % u)
/home/janisz/anaconda2/lib/python2.7/site-packages/networkx/generators/stochastic.py:56: UserWarning: zero out-degree for node Sebastian Geller
  warnings.warn('zero out-degree for node %s' % u)
/home/janisz/anaconda2/lib/python2.7/site-packages/networkx/generators/stochastic.py:56: UserWarning: zero out-degree for node gaopeng
  warnings.warn('zero out-degree for node %s' % u)






    
Out[29]:






  

    

      

      
ownership
      
refactoring_ownership
      
page_rank
      
added
      
deleted
      
commits
    
  
  

    

      
ownership
      
1.000000
      
0.991027
      
-0.023155
      
0.982815
      
0.974970
      
0.995055
    
    

      
refactoring_ownership
      
0.991027
      
1.000000
      
-0.020705
      
0.976302
      
0.974796
      
0.993721
    
    

      
page_rank
      
-0.023155
      
-0.020705
      
1.000000
      
-0.023367
      
-0.019477
      
-0.022695
    
    

      
added
      
0.982815
      
0.976302
      
-0.023367
      
1.000000
      
0.984127
      
0.981833
    
    

      
deleted
      
0.974970
      
0.974796
      
-0.019477
      
0.984127
      
1.000000
      
0.983187
    
    

      
commits
      
0.995055
      
0.993721
      
-0.022695
      
0.981833
      
0.983187
      
1.000000
    
  

In [30]:

    

authors_full(data_dir + 'apache/mesos').corr()


    

    
Out[30]:






  

    

      

      
ownership
      
refactoring_ownership
      
page_rank
      
added
      
deleted
      
commits
    
  
  

    

      
ownership
      
1.000000
      
0.999671
      
-0.037384
      
0.999555
      
0.999526
      
0.996993
    
    

      
refactoring_ownership
      
0.999671
      
1.000000
      
-0.037875
      
0.999130
      
0.999171
      
0.996994
    
    

      
page_rank
      
-0.037384
      
-0.037875
      
1.000000
      
-0.038207
      
-0.036503
      
-0.048193
    
    

      
added
      
0.999555
      
0.999130
      
-0.038207
      
1.000000
      
0.999932
      
0.996552
    
    

      
deleted
      
0.999526
      
0.999171
      
-0.036503
      
0.999932
      
1.000000
      
0.995808
    
    

      
commits
      
0.996993
      
0.996994
      
-0.048193
      
0.996552
      
0.995808
      
1.000000
    
  

In [ ]: