Update app.py

app.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 """
 Updated on 09/13/2023
+
 """
 
 import streamlit as st
@@ -85,7 +86,7 @@ with st.form(key="my_form"):
                                   'checkpoint_path': './vocab/bioformer-cased-v1.0/bioformer-cased-v1.0-model.ckpt-2000000',
                                   'vocab_path': './vocab/bioformer-cased-v1.0/vocab.txt'}
 
-                    modelfile = './vocab/bioformer.h5'
+                    modelfile = './vocab/bioformer_fyeco.h5'
 
                 elif model == '2':
                     vocabfiles = {'labelfile': './dict_new_hpo/lable.vocab',
@@ -99,6 +100,19 @@ with st.form(key="my_form"):
 
                     modelfile='./vocab/bioformer_p5n5_b64_1e-5_95_hponew3.h5'
 
+                elif model == '3':
+                    vocabfiles = {'labelfile': './dict_new_sympo/lable.vocab',
+                                  'config_path': './vocab/bioformer-cased-v1.0/bert_config.json',
+                                  'checkpoint_path': './vocab/bioformer-cased-v1.0/bioformer-cased-v1.0-model.ckpt-2000000',
+                                  'vocab_path': './vocab/bioformer-cased-v1.0/vocab.txt'}
+
+                    ontfiles = {'dic_file': './dict_new_sympo/noabb_lemma.dic',
+                                'word_hpo_file': './dict_new_sympo/word_id_map.json',
+                                'hpo_word_file': './dict_new_sympo/id_word_map.json'}
+
+                    modelfile='./vocab/bioformer_sympo.h5'
+                    pass
+
                 biotag_dic=dic_ont(ontfiles)    
     
                 nn_model=bioTag_Bioformer(vocabfiles)
@@ -107,6 +121,7 @@ with st.form(key="my_form"):
 
             nn_model1, biotag_dic1 = load_model(model='1')
             nn_model2, biotag_dic2 = load_model(model='2')
+            nn_model3, biotag_dic3 = load_model(model='3')
 
         else:
             @st.cache_resource
@@ -193,10 +208,9 @@ para_set={
 st.markdown("")
 st.markdown("## ⏳ Tagging results:")
 with st.spinner('Wait for tagging...'):
-
     tag_result1=bioTag(doc,biotag_dic1,nn_model1,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])
     tag_result2=bioTag(doc,biotag_dic2,nn_model2,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])
-
+    tag_result3=bioTag(doc,biotag_dic3,nn_model3,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])
 
 st.markdown('<font style="color: rgb(128, 128, 128);">Move the mouse over the entity to display the id.</font>', unsafe_allow_html=True)
 # print('dic...........:',biotag_dic.keys())
@@ -208,8 +222,9 @@ entity_end=0
 
 # poid_counts = []
 
-hpoid_count1={}
+hpoid_count1= {}
 hpoid_count2 = {}
+hpoid_count3 = {}
 
 tag_display = {}
 
@@ -256,6 +271,28 @@ if len(tag_result2) >= 0:
 
     flag = True
 
+if len(tag_result3) >= 0:
+    entity_end = 0
+    for ele in tag_result3:
+        entity_start = int(ele[0])
+        #html_results += doc[entity_end:entity_start]
+        entity_end = int(ele[1])
+        entity_id = ele[2]
+        entity_score = ele[3]
+        tag_display[entity_start] = (entity_end, entity_id, "3")
+        text_results += ele[0] + '\t' + ele[1] + '\t' + doc[entity_start:entity_end] + '\t' + ele[2] + '\t' + format(
+            float(ele[3]), '.2f') + '\n'
+
+        if entity_id not in hpoid_count3.keys():
+            hpoid_count3[entity_id] = 1
+        else:
+            hpoid_count3[entity_id] += 1
+
+       # html_results += '<font style="background-color: rgb(255, 0, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
+    #html_results += doc[entity_end:]
+
+    flag = True
+
 if not flag:
     html_results = doc
 else:
@@ -273,11 +310,13 @@ else:
             html_results += '<font style="background-color: rgb(255, 204, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
         elif type == "2":
             html_results += '<font style="background-color: rgb(255, 0, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
+        elif type == "3":
+            html_results += '<font style="background-color: rgb(102, 255, 178)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
+
     html_results += doc[entity_end:]
     
     st.markdown('<table border="1"><tr><td>'+html_results+'</td></tr></table>', unsafe_allow_html=True)
 
-
 #table
 data_entity=[]
 for ele in hpoid_count1.keys():
@@ -296,6 +335,16 @@ for ele in hpoid_count2.keys():
     temp=[ele,term_name,hpoid_count2[ele]] #hpoid, term name, count
     data_entity.append(temp)
 
+for ele in hpoid_count3.keys():
+    segs=ele.split(';')
+    term_name=''
+    for seg in segs:
+        term_name+=biotag_dic3.hpo_word[seg][0]+';'
+    temp=[ele,term_name,hpoid_count3[ele]] #hpoid, term name, count
+    data_entity.append(temp)
+
+
+
 st.markdown("")
 st.markdown("")
 # st.markdown("## Table output:")