In [1]:

    

from __future__ import division
import pymongo, pandas, random
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt


    

In [2]:

    

connection = pymongo.MongoClient('localhost', 27017)
communities = connection.database_names()

for db in ["gender", "admin", "local", "visualizations", "results"]:
    if db in communities:communities.remove(db)


    

In [3]:

    

columns = ['community', 'males','females','total_ident', 'total', 'prop_males', 'prop_females', 'prop_ident']
results = pandas.DataFrame(columns=columns)


    

In [4]:

    

for community in communities:
    community_db = connection[community]['statistics']
    
    cursor = community_db.find({'contributions_total': {'$gt':0}},
                               {u'_id': False, u'user_id':True, u'gender':True})
    
    df =  pandas.DataFrame(list(cursor))

    males = df.query('gender == "Male"')
    females = df.query('gender == "Female"')
    
    total = df.count()[0]
    males_count = males.count()[0]
    females_count = females.count()[0]
    total_ident = males_count + females_count


    result = {
        'community': community,
        'males': males_count,
        'females': females_count,
        'total': total,
        'total_ident': total_ident,
        'prop_males': males_count/total_ident,
        'prop_females': females_count/total_ident,
        'prop_ident': total_ident/total
    }
    
    results = results.append(result, ignore_index=True)


    

In [34]:

    

results.to_csv("/Users/milena/Desktop/proportions.csv")


    

In [6]:

    

results.median()


    

    
Out[6]:





males            499.000000
females           35.000000
total_ident      536.000000
total           1485.000000
prop_males         0.936200
prop_females       0.063800
prop_ident         0.366874
dtype: float64

In [14]:

    

communities = ["academia", "android", "anime", "apple", "askubuntu", "bicycles", "biology", "bitcoin", "chemistry", "chinese", "christianity", "codegolf", "codereview", "cogsci", "cooking", "crypto", "cs", "cstheory", "dba", "diy", "drupal", "dsp", "electronics", "ell", "english", "expressionengine", "fitness", "freelancing", "french", "gamedev", "gaming", "gardening", "genealogy", "german", "gis", "graphicdesign", "hermeneutics", "history", "islam", "japanese", "judaism", "linguistics", "magento", "math", "mathematica", "mathoverflow", "mechanics", "money", "movies", "music", "outdoors", "parenting", "philosophy", "photo", "physics", "pm", "productivity", "programmers", "quant", "raspberrypi", "rpg", "russian", "salesforce", "scicomp", "scifi", "security", "serverfault", "sharepoint", "skeptics", "sound", "spanish", "sqa", "stackapps", "stackoverflow", "stats", "superuser", "tex", "travel", "unix", "ux", "webapps", "webmasters", "wordpress", "workplace", "writers"]
category = ["life-arts", "technology", "culture-recreation", "technology", "technology", "culture-recreation", "science", "business", "science", "culture-recreation", "culture-recreation", "technology", "technology", "science", "life-arts", "technology", "science", "science", "technology", "life-arts", "technology", "technology", "technology", "culture-recreation", "culture-recreation", "technology", "life-arts", "professional", "culture-recreation", "technology", "culture-recreation", "life-arts", "life-arts", "culture-recreation", "technology", "life-arts", "culture-recreation", "culture-recreation", "culture-recreation", "culture-recreation", "culture-recreation", "science", "technology", "science", "technology", "science", "culture-recreation", "life-arts", "life-arts", "life-arts", "culture-recreation", "life-arts", "science", "life-arts", "science", "business", "life-arts", "technology", "business", "technology", "culture-recreation", "culture-recreation", "technology", "science", "life-arts", "technology", "technology", "technology", "culture-recreation", "technology", "culture-recreation", "technology", "technology", "technology", "science", "technology", "technology", "culture-recreation", "technology", "technology", "technology", "technology", "technology", "professional", "life-arts"]

cat = pandas.DataFrame({'community':communities, 'category':category})
temp = pandas.merge(cat, results, on='community')
temp.groupby(['category']).median()


    

    
Out[14]:






  

    

      

      
males
      
females
      
total_ident
      
total
      
prop_males
      
prop_females
      
prop_ident
    
    

      
category
      

      

      

      

      

      

      

    
  
  

    

      
business
      
609.0
      
29.0
      
649.0
      
1548.0
      
0.943662
      
0.056338
      
0.356268
    
    

      
culture-recreation
      
495.0
      
38.0
      
536.0
      
1399.0
      
0.918089
      
0.081911
      
0.366874
    
    

      
life-arts
      
788.0
      
70.0
      
840.0
      
2330.0
      
0.919052
      
0.080948
      
0.387854
    
    

      
professional
      
800.0
      
80.5
      
880.5
      
2382.0
      
0.897391
      
0.102609
      
0.379702
    
    

      
science
      
796.0
      
52.0
      
854.5
      
2253.5
      
0.931179
      
0.068821
      
0.368173
    
    

      
technology
      
2751.5
      
127.5
      
2907.5
      
7894.0
      
0.946982
      
0.053018
      
0.366328
    
  

In [ ]: