Spaces:
Sleeping
Sleeping
wzkariampuzha
commited on
Commit
•
26da213
1
Parent(s):
256dcea
Update classify_abs.py
Browse files- classify_abs.py +29 -28
classify_abs.py
CHANGED
@@ -291,6 +291,7 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
|
|
291 |
searchterm_list = list(searchterm_list)
|
292 |
#maxResults is multiplied by a little bit because sometimes the results returned is more than maxResults
|
293 |
percent_by_step = 1/(maxResults*1.05)
|
|
|
294 |
PMIDs_bar = st.progress(0)
|
295 |
for dz in searchterm_list:
|
296 |
term = ''
|
@@ -325,36 +326,36 @@ def streamlit_getAbs(searchterm_list:Union[List[str],List[int],str], maxResults:
|
|
325 |
PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
|
326 |
PMIDs_bar.empty()
|
327 |
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
|
336 |
-
|
337 |
-
|
338 |
-
|
339 |
-
|
340 |
-
|
341 |
-
|
342 |
-
pmid_abs[pmid] = abstract
|
343 |
-
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
344 |
-
break
|
345 |
-
elif filtering =='none':
|
346 |
-
pmid_abs[pmid] = abstract
|
347 |
-
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
348 |
-
|
349 |
-
#Default filtering is 'lenient'.
|
350 |
-
else:
|
351 |
-
#Else and if are separated for readability and to better understand logical flow.
|
352 |
-
if set(filter_terms).intersection(set(word_tokenize(abstract))):
|
353 |
pmid_abs[pmid] = abstract
|
354 |
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
355 |
-
|
356 |
-
|
357 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
358 |
|
359 |
return pmid_abs, (len(pmids),len(pmid_abs))
|
360 |
|
|
|
291 |
searchterm_list = list(searchterm_list)
|
292 |
#maxResults is multiplied by a little bit because sometimes the results returned is more than maxResults
|
293 |
percent_by_step = 1/(maxResults*1.05)
|
294 |
+
API_Loading = st.spinner("Gathering PubMed IDs...")
|
295 |
PMIDs_bar = st.progress(0)
|
296 |
for dz in searchterm_list:
|
297 |
term = ''
|
|
|
326 |
PMIDs_bar.progress(min(round(len(pmids)*percent_by_step,1),1.0))
|
327 |
PMIDs_bar.empty()
|
328 |
|
329 |
+
API_Loading = st.spinner("Found "+str(len(pmids))+" PMIDs. Gathering Abstracts and Filtering...")
|
330 |
+
abstracts_bar = st.progress(0)
|
331 |
+
percent_by_step = 1/(maxResults)
|
332 |
+
if filtering !='none' or filtering !='strict':
|
333 |
+
filter_terms = set(searchterm_list).union(set(str(re.sub(',','',' '.join(searchterm_list))).split()).difference(STOPWORDS))
|
334 |
+
|
335 |
+
for pmid in pmids:
|
336 |
+
abstract = PMID_getAb(pmid)
|
337 |
+
if len(abstract)>5:
|
338 |
+
#do filtering here
|
339 |
+
if filtering == 'strict':
|
340 |
+
uncased_ab = abstract.lower()
|
341 |
+
for term in searchterm_list:
|
342 |
+
if term.lower() in uncased_ab:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
343 |
pmid_abs[pmid] = abstract
|
344 |
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
345 |
+
break
|
346 |
+
elif filtering =='none':
|
347 |
+
pmid_abs[pmid] = abstract
|
348 |
+
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
349 |
+
|
350 |
+
#Default filtering is 'lenient'.
|
351 |
+
else:
|
352 |
+
#Else and if are separated for readability and to better understand logical flow.
|
353 |
+
if set(filter_terms).intersection(set(word_tokenize(abstract))):
|
354 |
+
pmid_abs[pmid] = abstract
|
355 |
+
abstracts_bar.progress(min(round(len(pmid_abs)*percent_by_step,1),1.0))
|
356 |
+
abstracts_bar.empty()
|
357 |
+
API_Loading.empty()
|
358 |
+
st.success('Found '+str(len(pmids))+' PMIDs. Gathered '+str(len(pmid_abs))+' Relevant Abstracts. Classifying and extracting epidemiology information...')
|
359 |
|
360 |
return pmid_abs, (len(pmids),len(pmid_abs))
|
361 |
|