In [1]:

    

from __future__ import division
from scipy import stats
import random, pymongo
import sklearn.metrics as metrics
import matplotlib.pyplot as plt
import pandas as pd
import rpy2.robjects as robjects

%matplotlib inline


    

    




During startup - Warning messages:
1: Setting LC_COLLATE failed, using "C" 
2: Setting LC_TIME failed, using "C" 
3: Setting LC_MESSAGES failed, using "C" 
4: Setting LC_MONETARY failed, using "C" 

In [2]:

    

r = robjects.r


    

In [3]:

    

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

results_db = connection['results']['question_3']
cursor = results_db.find({}, {u'_id': False, u'community':True, 
                              u'frequency_pvalue':True})

stats_df = pd.DataFrame(list(cursor))


    

In [5]:

    

for index, row in stats_df.iterrows():
    community = row['community']
    community_db = connection[community]['statistics']
    cursor = community_db.find({'contributions_total': {'$gt':0}}, 
                                {u'_id': False, u'activity_freq':True, u'gender':True})

    df =  pd.DataFrame(list(cursor))
    females = df.query("gender == 'Female'")
    males = df.query("gender == 'Male'")
    
    frequency = r['wilcox.test'](robjects.FloatVector(list(females['activity_freq'])),
                                                          robjects.FloatVector(list(males['activity_freq'])),
                                                          alternative="g", correct=True, exact=False)[2][0]

    
    results_db.update({'community': community}, {'$set': {'frequency_pvalue_greater': frequency}})


    

In [ ]: