Update classify_abs.py

classify_abs.py

@@ -290,7 +290,7 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
         else:
             searchterm_list = list(searchterm_list)
     #maxResults is multiplied by a little bit because sometimes the results returned is more than maxResults
-    percent_by_step = 1/(maxResults*1.05) 
+    percent_by_step = 1/maxResults
     with st.spinner("Gathering PubMed IDs..."):
         PMIDs_bar = st.progress(0)
         for dz in searchterm_list:
@@ -328,7 +328,7 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
     
     with st.spinner("Found "+str(len(pmids))+" PMIDs. Gathering Abstracts and Filtering..."):
         abstracts_bar = st.progress(0)
-        percent_by_step = 1/(maxResults)
+        percent_by_step = 1/maxResults
         if filtering !='none' or filtering !='strict':
             filter_terms = set(searchterm_list).union(set(str(re.sub(',','',' '.join(searchterm_list))).split()).difference(STOPWORDS))
     
@@ -340,23 +340,22 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
                     uncased_ab = abstract.lower()
                     for term in searchterm_list:
                         if term.lower() in uncased_ab:
-                            pmid_abs[pmid] = abstract
-                            abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
+                            pmid_abs[pmid] = abstract                            
                             break
                 elif filtering =='none':
                     pmid_abs[pmid] = abstract
-                    abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
-                
                 #Default filtering is 'lenient'.
                 else:
                     #Else and if are separated for readability and to better understand logical flow.
                     if set(filter_terms).intersection(set(word_tokenize(abstract))):
                         pmid_abs[pmid] = abstract
-                        abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
+            abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
         abstracts_bar.empty()
-    st.success('Found '+str(len(pmids))+' PMIDs. Gathered '+str(len(pmid_abs))+' Relevant Abstracts. Classifying and extracting epidemiology information...')
+    found = len(pmids)
+    relevant = len(pmid_abs)
+    st.success('Found '+str(found)+' PMIDs. Gathered '+str(relevant)+' Relevant Abstracts. Classifying and extracting epidemiology information...')
     
-    return pmid_abs, (len(pmids),len(pmid_abs))
+    return pmid_abs, (found, relevant)
 
 # Generate predictions for a PubMed Id
 # nlp: en_core_web_lg