Update app.py

app.py

@@ -1,8 +1,15 @@
 import streamlit as st
 import pandas as pd
 import transformers
+import re
+import postt
+from postt import postcor
 from transformers import  pipeline, TokenClassificationPipeline, BertForTokenClassification , AutoTokenizer , TextClassificationPipeline , AutoModelForSequenceClassification
 
+
+
+
+
 st.header("Knowledge extraction on Endocrine disruptors")
 st.write("This tool lets you extract relation triples concerning interactions between: endocrine disrupting chemicals, hormones, receptors and cancers.")
 st.write("It is the result of an end of studies project within ESI school and dedicated to biomedical researchers looking to extract precise information about the subject without digging into long publications.")
@@ -217,16 +224,30 @@ if submit and len(x) != 0:
   
   
   edccan = []
-  
+  edccanbis = []
   
   for i in range(len(outrelbl)):
     if outrelbl[i] != "other":
-      edccan += [[lstSentEnc[i],lstSentEnt[i][0]+" ["+lstSentbilbl[i][0][2:]+"]", lstSentEnt[i][1]+" ["+lstSentbilbl[i][1][2:]+"]",outrelbl[i][:-7]]]
+      edccanbis += [[lstSentEnt[i][0], lstSentEnt[i][1], outrelbl[i][:-7], lstSentEnc[i], lstSentbilbl[i]]]
+      #edccan += [[lstSentEnc[i],lstSentEnt[i][0]+" ["+lstSentbilbl[i][0][2:]+"]", lstSentEnt[i][1]+" ["+lstSentbilbl[i][1][2:]+"]",outrelbl[i][:-7]]]
+      
+  edccanbis = postcor(edccanbis[3:])
+  
+  
+  for e in edccanbis:
+    edccan += [[e[3],e[0]+" ["+e[-1][0][2:]+"]", e[1]+" ["+e[-1][1][2:]+"]",e[2][:-7]]]
    
   edccandf = pd.DataFrame(edccan, columns= ["Sentence", "Entity 1", "Entity 2", "Relation"] )
   
   
   st.table(edccandf)
+  csv = edccandf.to_csv(index=False).encode('utf-8')
+  st.download_button(
+       label="Download data as CSV",
+       data=csv,
+       file_name='Relation_triples.csv',
+       mime='text/csv',
+   )