Update epi_pipeline.py

epi_pipeline.py

@@ -73,7 +73,7 @@ def search_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:int
         query = term[:-3]
 
         ## get pmid results from searching for disease name through PubMed API
-        url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term='+query+"&retmax="+str(maxResults)
+        url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term='+query+"&retmax="+str(int(maxResults/len(searchterm_list)))
         r = requests.get(url)
         root = ET.fromstring(r.content)
 
@@ -129,7 +129,8 @@ def search_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:int
             #do filtering here
             if filtering == 'strict':
                 uncased_ab = abstract.lower()
-                for term in searchterm_list:
+                #Reversing the list hopefully cuts down on the number of if statements bc the search terms are ordered longest to shortest and shorter terms are more likely to be in the abstract
+                for term in reversed(searchterm_list):
                     if term.lower() in uncased_ab:
                         pmid_abs[pmid] = abstract
                         break
@@ -169,7 +170,7 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
             for word in dz_words:
                 term += word + '%20'
             query = term[:-3]
-    
+            #dividing by the len( of the search_ter
             url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term='+query+"&retmax="+str(int(maxResults/len(searchterm_list)))
             r = requests.get(url)
             root = ET.fromstring(r.content)
@@ -208,7 +209,8 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
                 #do filtering here
                 if filtering == 'strict':
                     uncased_ab = abstract.lower()
-                    for term in searchterm_list:
+                    #Reversing the list hopefully cuts down on the number of if statements bc the search terms are ordered longest to shortest and shorter terms are more likely to be in the abstract
+                    for term in reversed(searchterm_list):
                         if term.lower() in uncased_ab:
                             pmid_abs[pmid] = abstract                            
                             break