Update app.py

app.py

@@ -11,7 +11,10 @@ from nltk.tokenize import sent_tokenize
 from fin_readability_sustainability import BERTClass, do_predict
 import pandas as pd
 import en_core_web_sm
-
+from fincat_utils import extract_context_words
+from fincat_utils import bert_embedding_extract
+import pickle
+lr_clf = pickle.load(open("lr_clf_FiNCAT.pickle",'rb'))
 
 nlp = en_core_web_sm.load()
 nltk.download('punkt')
@@ -37,6 +40,35 @@ def get_sustainability(text):
   return highlight
 #SUSTAINABILITY ENDS
 
+#CLAIM STARTS
+def score_fincat(txt):
+  li = []
+  highlight = []
+  txt = " " + txt + " "
+  k = ''
+  for word in txt.split():
+    if any(char.isdigit() for char in word):
+      if word[-1] in ['.', ',', ';', ":", "-", "!", "?", ")", '"', "'"]:
+        k = word[-1]
+        word = word[:-1]
+      st = txt.index(" " + word + k + " ")+1
+      k = ''
+      ed = st + len(word)
+      x = {'paragraph' : txt, 'offset_start':st, 'offset_end':ed}
+      context_text = extract_context_words(x)
+      features = bert_embedding_extract(context_text, word)
+      prediction = lr_clf.predict(features.reshape(1, 768))
+      prediction_probability = '{:.4f}'.format(round(lr_clf.predict_proba(features.reshape(1, 768))[:,1][0], 4))
+      highlight.append((word, '    In-claim' if prediction==1 else 'Out-of-Claim'))
+      li.append([word,'    In-claim' if prediction==1 else 'Out-of-Claim', prediction_probability])
+    else:
+      highlight.append((word, '    '))
+  headers = ['numeral', 'prediction', 'probability']
+  dff = pd.DataFrame(li)
+  dff.columns = headers
+  return highlight, dff
+
+
 ##Summarization
 summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY") 
 def summarize_text(text):
@@ -93,8 +125,8 @@ def quad(query,file):
     #resp = summarizer(answer)
     #stext = resp[0]['summary_text']
     
-    
-    return answer,summarize_text(answer),fin_ner(answer),get_sustainability(answer),fls(answer)           
+    highlight,dff=score_fincat(answer)
+    return answer,summarize_text(answer),highlight,dff,fin_ner(answer),get_sustainability(answer),fls(answer)           
                 
                    
 # b6 = gr.Button("Get Sustainability")
@@ -104,7 +136,7 @@ def quad(query,file):
 #iface = gr.Interface(fn=get_sustainability, inputs="textbox", title="CONBERT",description="SUSTAINABILITY TOOL", outputs=gr.HighlightedText(), allow_flagging="never")
 #iface.launch()
 
-iface = gr.Interface(fn=quad, inputs=[gr.inputs.Textbox(label='SEARCH QUERY'),gr.inputs.File(label='TXT FILE')], title="CONBERT",description="SUSTAINABILITY TOOL",article='Article', outputs=[gr.outputs.Textbox(label='Answer'),gr.outputs.Textbox(label='Summary'),gr.HighlightedText(label='NER'),gr.HighlightedText(label='SUSTAINABILITY'),gr.HighlightedText(label='FLS')], allow_flagging="never")
+iface = gr.Interface(fn=quad, inputs=[gr.inputs.Textbox(label='SEARCH QUERY'),gr.inputs.File(label='TXT FILE')], title="CONBERT",description="SUSTAINABILITY TOOL",article='Article', outputs=[gr.outputs.Textbox(label='Answer'),gr.outputs.Textbox(label='Summary'),"highlight","data frame",gr.HighlightedText(label='NER'),gr.HighlightedText(label='SUSTAINABILITY'),gr.HighlightedText(label='FLS')], allow_flagging="never")
 
 
 iface.launch()