Update classify_abs.py

classify_abs.py

@@ -291,70 +291,69 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
             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) 
-    API_Loading = st.spinner("Gathering PubMed IDs...")
-    PMIDs_bar = st.progress(0)
-    for dz in searchterm_list:
-        term = ''
-        dz_words = dz.split()
-        for word in dz_words:
-            term += word + '%20'
-        query = term[:-3]
-
-        url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term='+query
-        r = requests.get(url)
-        root = ET.fromstring(r.content)
-
-        for result in root.iter('IdList'):
-            if len(pmids) >= maxResults:
-                break
-            pmidlist = [pmid.text for pmid in result.iter('Id')]
-            pmids.update(pmidlist)
-            PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
-
-        url = 'https://www.ebi.ac.uk/europepmc/webservices/rest/search?query='+query+'&resulttype=core'
-        r = requests.get(url)
-        root = ET.fromstring(r.content)
-
-        for result in root.iter('result'):
-            if len(pmids) >= maxResults:
-                break
-            pmidlist = [pmid.text for pmid in result.iter('id')]
-            if len(pmidlist) > 0:
-                pmid = pmidlist[0]
-                if pmid[0].isdigit():
-                    pmids.add(pmid)
-                    PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
-    PMIDs_bar.empty()
+    with st.spinner("Gathering PubMed IDs..."):
+        PMIDs_bar = st.progress(0)
+        for dz in searchterm_list:
+            term = ''
+            dz_words = dz.split()
+            for word in dz_words:
+                term += word + '%20'
+            query = term[:-3]
     
-    API_Loading = st.spinner("Found "+str(len(pmids))+" PMIDs. Gathering Abstracts and Filtering...")
-    abstracts_bar = st.progress(0)
-    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))
-
-    for pmid in pmids:
-        abstract = PMID_getAb(pmid)
-        if len(abstract)>5:
-            #do filtering here
-            if filtering == 'strict':
-                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))
-                        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))):
+            url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term='+query
+            r = requests.get(url)
+            root = ET.fromstring(r.content)
+    
+            for result in root.iter('IdList'):
+                if len(pmids) >= maxResults:
+                    break
+                pmidlist = [pmid.text for pmid in result.iter('Id')]
+                pmids.update(pmidlist)
+                PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
+    
+            url = 'https://www.ebi.ac.uk/europepmc/webservices/rest/search?query='+query+'&resulttype=core'
+            r = requests.get(url)
+            root = ET.fromstring(r.content)
+    
+            for result in root.iter('result'):
+                if len(pmids) >= maxResults:
+                    break
+                pmidlist = [pmid.text for pmid in result.iter('id')]
+                if len(pmidlist) > 0:
+                    pmid = pmidlist[0]
+                    if pmid[0].isdigit():
+                        pmids.add(pmid)
+                        PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
+        PMIDs_bar.empty()
+    
+    with st.spinner("Found "+str(len(pmids))+" PMIDs. Gathering Abstracts and Filtering..."):
+        abstracts_bar = st.progress(0)
+        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))
+    
+        for pmid in pmids:
+            abstract = PMID_getAb(pmid)
+            if len(abstract)>5:
+                #do filtering here
+                if filtering == 'strict':
+                    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))
+                            break
+                elif filtering =='none':
                     pmid_abs[pmid] = abstract
                     abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
-    abstracts_bar.empty()
-    API_Loading.empty()
+                
+                #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.empty()
     st.success('Found '+str(len(pmids))+' PMIDs. Gathered '+str(len(pmid_abs))+' Relevant Abstracts. Classifying and extracting epidemiology information...')
     
     return pmid_abs, (len(pmids),len(pmid_abs))