def getfactors (RL, articletype, cancer, short_cancer):
article_count = []
article_factors = []
hit_count = 0
miss_count = 0
bad_journals = []
columntitlecount = 'Paper count - ' + short_cancer + ' ' + articletype
columntitleIF = 'Impact factor - ' + short_cancer + ' ' + articletype
if articletype != 'All':
searchterm = "2008:2013 [DP] " + articletype + "[PT] "
else:
searchterm = "2008:2013 [DP] "
b = 0
while b < len(RL.Search_Term):
org = '(' + RL.iloc[b][1] + ') '
full_searchterm = org + searchterm + cancer
#print full_searchterm
try:
cancer_count = pmhits(full_searchterm)
except URLError:
try:
cancer_count = pmhits(full_searchterm)
except URLError:
pass
article_count.append(cancer_count)
#print cancer_count
cancer_factor = 0
if cancer_count > 0:
records = pubmedsearch(full_searchterm)
for record in records: #iterating over the records collected, get the journal for each and impact factor
TA = record.get('TA', '?')
TA = TA.upper()
TA = TA.replace('.', '')
factor = IFdict.get(TA)
try:
factor = float(factor)
cancer_factor = cancer_factor + factor #add this IF to the total IF for the organization
hit_count = hit_count + 1
except TypeError:
bad_journals.append(TA)
miss_count = miss_count + 1
else:
pass
#print cancer_factor
article_factors.append(cancer_factor)
b = b + 1
print sorted(list(set(bad_journals)))
print short_cancer
RL[columntitleIF] = article_factors
RL[columntitlecount] = article_count
RL.to_csv('C:\Users\JAG\USN-dz\RL_dz_pm_impacts_meshb.csv', sep = ',' , index = False)
return RL
def getfactors (articletype, cancer, short_cancer):
hit_count = 0
miss_count = 0
bad_journals = []
if articletype != 'All':
searchterm = "2008:2013 [DP] " + articletype + "[PT] "
else:
searchterm = "2008:2013 [DP] "
full_searchterm = searchterm + cancer
print full_searchterm
try:
cancer_count = pmhits(full_searchterm)
except URLError:
try:
cancer_count = pmhits(full_searchterm)
except URLError:
pass
records = pubmedsearch(full_searchterm, MAX_COUNT = 100000)
cancer_factor = 0
for record in records: #iterating over the records collected, get the journal for each and impact factor
TA = record.get('TA', '?')
TA = TA.upper()
TA = TA.replace('.', '')
factor = IFdict.get(TA)
try:
factor = float(factor)
cancer_factor = cancer_factor + factor #add this IF to the total IF for the organization
hit_count = hit_count + 1
except TypeError:
bad_journals.append(TA)
miss_count = miss_count + 1
print articletype
bad_journals = list(set(bad_journals))
print bad_journals
return (cancer_count,cancer_factor)
'''usnews wrangle
To wrangle complicated files with stacked information
'''
import pandas as pd
import numpy as np
import pubmedsearch as pm
List_path = 'C:\Users\JAG\USnewsy\RL-trials-5yr.csv'
Completed_path = 'C:\Users\JAG\USnewsy\RL-trials-5yr.csv'
# Read in the csv
RL = pd.read_csv(List_path, index_col=False, header = 0)
phase2 = []
phase3 = []
clinicaltrials = []
for institution in RL['Search_Term']:
p2 = pm.pmhits(institution + '[AD] 2008:2013 [DP] Clinical Trial, Phase II[PT] Cancer[MAJR]')
phase2.append(p2)
p3 = pm.pmhits(institution + '[AD] 2008:2013 [DP] Clinical Trial, Phase III[PT], Cancer[MAJR]')
phase3.append(p3)
ct = pm.pmhits(institution + '[AD] 2008:2013 [DP] Clinical Trial[PT], Cancer[MAJR]')
clinicaltrials.append(ct)
RL['Phase 2'] = phase2
RL['Phase 3'] = phase3
RL['Clinical Trials'] = clinicaltrials
RL.to_csv(Completed_path)
