age_to_plug = 0
else:
age_to_plug = int(formatted_res_age)
#print ">", age_to_plug
age_list_.append(age_to_plug)
age_to_plug=0
formatted_res_age=''
tupToRet =(age_list_, country_list_)
return tupToRet
print "Started at: ", utility.giveTimeStamp()
reputationList = preProcessQuestionInfo(getReputations(), 'REP')
print "******************************"
### Reputation
print "Count of users with reputation"
print len(reputationList)
print "Reputation stats:"
st_ = utility.giveStat(reputationList)
print st_
lh_threhold=st_[3]
# high reputation
high_users = preProcessQuestionInfo(getHighUsers(lh_threhold), 'Id')
high_users.sort()
print "Count of highly reputed users"
convert fitted matrix to pandas dataframe: not using CSV, dumping list of strings as pickle in line#80
'''
# df_ = utility.dumpTransformedTokenMatrixToCSV(transformed_features, feature_names, reproc_dump_output_file)
# print df_.shape
# print 'Dumping completed ...'
'''
and then call prediction module
'''
tokenization_predictor.performPrediction(iterDumpDir, all_features, labels,
feature_names,
count_vec_flag_param)
print "=" * 100
if __name__ == '__main__':
print "Started at", utility.giveTimeStamp()
print "-" * 125
dir2save = '/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/output/'
# dataset_file="/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/dataset/MIRANTIS_FULL_DATASET.csv"
# reproc_dump_output_file= '/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/reproc/TFIDF_MIR.dump'
# theCompleteCategFile='/Users/akond/Documents/AkondOneDrive/OneDrive/IaC-Defect-Categ-Project/output/Mirantis_Categ_For_DB.csv'
# reproc_dump_output_file= '/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/reproc/TFIDF_MIR.csv'
# dataset_file="/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/dataset/SYNTHETIC_MOZ_FULL_DATASET.csv"
# reproc_dump_output_file= '/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/reproc/TFIDF_MOZILLA.dump'
# theCompleteCategFile='/Users/akond/Documents/AkondOneDrive/OneDrive/IaC-Defect-Categ-Project/output/Mozilla.Final.Categ.csv'
# reproc_dump_output_file= '/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/reproc/TFIDF_MOZILLA.csv'
# dataset_file="/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/dataset/SYNTHETIC_OPENSTACK_FULL_DATASET.csv"
# reproc_dump_output_file='/Users/akond/Documents/AkondOneDrive/OneDrive/stvr/reproc/TFIDF_OPENSTACK.dump'
if val_=='':
countto_ret = 0.0
else:
countto_ret= float(val_)
return countto_ret
def getIssueReportsList(author_id_param_list):
resultantIssueReportList = []
for author_id_ in author_id_param_list:
issue_report_count = preProcessCount(getIssueReportFromDB(author_id_))
resultantIssueReportList.append(issue_report_count)
return resultantIssueReportList
print "Starting at:", utility.giveTimeStamp()
allTheFemales = preProcessauthorIDs(getAllFemaleAuthors())
print "Identified females:",len(allTheFemales)
allTheMales = preProcessauthorIDs(getAllMaleAuthors())
print "Identified males:",len(allTheMales)
issue_reports_for_females = getIssueReportsList(allTheFemales)
status=utility.dumpContent(issue_reports_for_females, 'F_ALL')
print "Dumped a file of {} bytes".format(status)
print "Total Female reports",sum(issue_reports_for_females)
issue_reports_for_males = getIssueReportsList(allTheMales)
status=utility.dumpContent(issue_reports_for_males, 'M_ALL')
print "Dumped a file of {} bytes".format(status)
print "Total Male reports",sum(issue_reports_for_males)
print "Ending at:", utility.giveTimeStamp()