In [ ]:

    

from scipy import stats

help(stats.mannwhitneyu)


    

In [4]:

    

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


    

In [98]:

    

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

community = 'poker'
stats_db = client[community].statistics


    

In [99]:

    

cursor = stats_db.find({'contributions_total': {'$gt':0} },
                       {u'_id': False, u'questions_total': True, u'contributions_total':True,
                        u'comments_total': True, u'answers_total': True, u'gender':True})

df =  pd.DataFrame(list(cursor))


    

In [100]:

    

females = df.query("gender == 'Female' ")

males = df.query("gender == 'Male' ")


    

In [101]:

    

females_r = robjects.IntVector(list(females['questions_total']))
males_r = robjects.IntVector(list(males['questions_total']))


    

In [102]:

    

wilr = robjects.r['wilcox.test']
result = wilr(females_r,males_r, alternative="t", correct=True, exact=False)
# for x in wilr(females_r,males_r):
#     print x


    

In [103]:

    

print "p-value: " + str(result[2][0])


    

    




p-value: 0.0331963503815

In [ ]:

    

print result


    

In [ ]:

    

r = robjects.r