Create app.py

app.py

@@ -0,0 +1,384 @@
+import streamlit as st
+from transformers import pipeline
+import re
+
+import requests
+
+API_URL = "https://api-inference.huggingface.co/models/microsoft/prophetnet-large-uncased-squad-qg"
+headers = {"Authorization": "Bearer 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"}
+
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+
+#-----------------------------------------------------------
+
+API_URL_evidence ="https://api-inference.huggingface.co/models/google/flan-t5-xxl"
+headers_evidence = {"Authorization": "Bearer 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"}
+
+def query_evidence(payload):
+	response = requests.post(API_URL_evidence, headers=headers_evidence, json=payload)
+	return response.json()
+
+#-----------------------------------------------------------
+claim_text=st.text_area("Enter your claim:")
+
+evidence_text=st.text_area("Enter your evidence:")
+
+import pandas as pd
+import numpy as np
+from allennlp.predictors.predictor import Predictor
+import allennlp_models.tagging
+predictor = Predictor.from_path("/kaggle/input/vitc-sampled-evidence/structured-prediction-srl-bert")
+
+#---------------------------------------------------------------
+def claim(text):
+    df = pd.DataFrame({'claim' : [text]})
+    def srl_allennlp(sent):
+      try:
+        #result = predictor.predict(sentence=sent)['verbs'][0]['description']
+        #result = predictor.predict(sentence=sent)['verbs'][0]['tags']
+        result = predictor.predict(sentence=sent)
+        return(result)
+      except IndexError: 
+        pass
+      #return(predictor.predict(sentence=sent))
+
+    df['allennlp_srl'] = df['claim'].apply(lambda x: srl_allennlp(x))
+
+    df['number_of_verbs'] = ''
+    df['verbs_group'] = ''
+    df['words'] = ''
+    df['verbs'] = ''
+    df['modified'] =''
+
+    col1 = df['allennlp_srl']
+    for i in range(len(col1)):
+      num_verb = len(col1[i]['verbs'])
+      df['number_of_verbs'][i] = num_verb
+      df['verbs_group'][i] = col1[i]['verbs']
+      df['words'][i] = col1[i]['words']
+
+      x=[]
+      for verb in range(len(col1[i]['verbs'])):
+        x.append(col1[i]['verbs'][verb]['verb'])
+      df['verbs'][i] = x
+
+      verb_dict ={}
+      desc = []
+      for j in range(len(col1[i]['verbs'])):
+        string = (col1[i]['verbs'][j]['description'])
+        string = string.replace("ARG0", "who")
+        string = string.replace("ARG1", "what")
+        string = string.replace("ARGM-TMP", "when")
+        string = string.replace("ARGM-LOC", "where")
+        string = string.replace("ARGM-CAU", "why")
+        desc.append(string)
+        verb_dict[col1[i]['verbs'][j]['verb']]=string
+      df['modified'][i] = verb_dict
+
+
+    #----------FOR COLUMN "WHO"------------#
+    df['who'] = ''
+    for j in range(len(df['modified'])):
+      val_list = []
+      val_string = ''
+      for k,v in df['modified'][j].items():
+        # print(type(v))
+        val_list.append(v)
+
+      who = []
+      for indx in range(len(val_list)):
+        val_string = val_list[indx]
+        pos = val_string.find("who: ")
+        substr = ''
+
+        if pos != -1:
+          for i in range(pos+5, len(val_string)):
+            if val_string[i] == "]":
+              break
+            else:
+              substr = substr + val_string[i]
+        else:
+          substr = None
+        who.append(substr)
+
+      df['who'][j] = who
+
+    #----------FOR COLUMN "WHAT"------------#
+    df['what'] = ''
+    for j in range(len(df['modified'])):
+      val_list = []
+      val_string = ''
+      for k,v in df['modified'][j].items():
+        # print(type(v))
+        val_list.append(v)
+
+      what = []
+      for indx in range(len(val_list)):
+        val_string = val_list[indx]
+        pos = val_string.find("what: ")
+        substr = ''
+
+        if pos != -1:
+          for i in range(pos+6, len(val_string)):
+            if val_string[i] == "]":
+              break
+            else:
+              substr = substr + val_string[i]
+        else:
+          substr = None
+        what.append(substr)
+
+      df['what'][j] = what
+
+    #----------FOR COLUMN "WHY"------------#
+    df['why'] = ''
+    for j in range(len(df['modified'])):
+      val_list = []
+      val_string = ''
+      for k,v in df['modified'][j].items():
+        # print(type(v))
+        val_list.append(v)
+
+      why = []
+      for indx in range(len(val_list)):
+        val_string = val_list[indx]
+        pos = val_string.find("why: ")
+        substr = ''
+
+        if pos != -1:
+          for i in range(pos+5, len(val_string)):
+            if val_string[i] == "]":
+              break
+            else:
+              substr = substr + val_string[i]
+        else:
+          substr = None
+        why.append(substr)
+
+      df['why'][j] = why
+
+     #----------FOR COLUMN "WHEN"------------#
+    df['when'] = ''
+    for j in range(len(df['modified'])):
+      val_list = []
+      val_string = ''
+      for k,v in df['modified'][j].items():
+        # print(type(v))
+        val_list.append(v)
+
+      when = []
+      for indx in range(len(val_list)):
+        val_string = val_list[indx]
+        pos = val_string.find("when: ")
+        substr = ''
+
+        if pos != -1:
+          for i in range(pos+6, len(val_string)):
+            if val_string[i] == "]":
+              break
+            else:
+              substr = substr + val_string[i]
+        else:
+          substr = None
+        when.append(substr)
+
+      df['when'][j] = when
+
+
+    #----------FOR COLUMN "WHERE"------------#
+    df['where'] = ''
+    for j in range(len(df['modified'])):
+      val_list = []
+      val_string = ''
+      for k,v in df['modified'][j].items():
+        # print(type(v))
+        val_list.append(v)
+
+      where = []
+      for indx in range(len(val_list)):
+        val_string = val_list[indx]
+        pos = val_string.find("where: ")
+        substr = ''
+
+        if pos != -1:
+          for i in range(pos+7, len(val_string)):
+            if val_string[i] == "]":
+              break
+            else:
+              substr = substr + val_string[i]
+        else:
+          substr = None
+        where.append(substr)
+
+      df['where'][j] = where
+
+    data=df[["claim","who","what","why","when","where"]].copy()    
+    import re
+    def remove_trail_comma(text):
+        x = re.sub(",\s*$", "", text)
+        return x
+
+
+    data['claim']=data['claim'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+    data['claim']=data['claim'].apply(lambda x: str(x).replace('[','').replace(']','')) 
+
+
+
+    data['who']=data['who'].apply(lambda x: str(x).replace(" 's","'s"))
+    data['who']=data['who'].apply(lambda x: str(x).replace("s ’","s’"))
+    data['who']=data['who'].apply(lambda x: str(x).replace(" - ","-"))
+    data['who']=data['who'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+#     data['who']=data['who'].apply(lambda x: str(x).replace('"','').replace('"',''))
+    data['who']=data['who'].apply(lambda x: str(x).replace('[','').replace(']','')) 
+    data['who']=data['who'].apply(lambda x: str(x).rstrip(','))
+    data['who']=data['who'].apply(lambda x: str(x).lstrip(','))
+    data['who']=data['who'].apply(lambda x: str(x).replace('None,','').replace('None','')) 
+    data['who']=data['who'].apply(remove_trail_comma)
+
+
+
+    data['what']=data['what'].apply(lambda x: str(x).replace(" 's","'s"))
+    data['what']=data['what'].apply(lambda x: str(x).replace("s ’","s’"))
+    data['what']=data['what'].apply(lambda x: str(x).replace(" - ","-"))
+    data['what']=data['what'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+#     data['what']=data['what'].apply(lambda x: str(x).replace('"','').replace('"',''))
+    data['what']=data['what'].apply(lambda x: str(x).replace('[','').replace(']','')) 
+    data['what']=data['what'].apply(lambda x: str(x).rstrip(','))
+    data['what']=data['what'].apply(lambda x: str(x).lstrip(','))
+    data['what']=data['what'].apply(lambda x: str(x).replace('None,','').replace('None','')) 
+    data['what']=data['what'].apply(remove_trail_comma)
+
+    data['why']=data['why'].apply(lambda x: str(x).replace(" 's","'s"))
+    data['why']=data['why'].apply(lambda x: str(x).replace("s ’","s’"))
+    data['why']=data['why'].apply(lambda x: str(x).replace(" - ","-"))
+    data['why']=data['why'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+#     data['why']=data['why'].apply(lambda x: str(x).replace('"','').replace('"',''))
+    data['why']=data['why'].apply(lambda x: str(x).replace('[','').replace(']',''))
+    data['why']=data['why'].apply(lambda x: str(x).rstrip(','))
+    data['why']=data['why'].apply(lambda x: str(x).lstrip(','))
+    data['why']=data['why'].apply(lambda x: str(x).replace('None,','').replace('None','')) 
+    data['why']=data['why'].apply(remove_trail_comma)
+
+    data['when']=data['when'].apply(lambda x: str(x).replace(" 's","'s"))
+    data['when']=data['when'].apply(lambda x: str(x).replace("s ’","s’"))
+    data['when']=data['when'].apply(lambda x: str(x).replace(" - ","-"))
+    data['when']=data['when'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+#     data['when']=data['when'].apply(lambda x: str(x).replace('"','').replace('"',''))
+    data['when']=data['when'].apply(lambda x: str(x).replace('[','').replace(']',''))
+    data['when']=data['when'].apply(lambda x: str(x).rstrip(','))
+    data['when']=data['when'].apply(lambda x: str(x).lstrip(','))
+    data['when']=data['when'].apply(lambda x: str(x).replace('None,','').replace('None','')) 
+    data['when']=data['when'].apply(remove_trail_comma)
+
+    data['where']=data['where'].apply(lambda x: str(x).replace(" 's","'s"))
+    data['where']=data['where'].apply(lambda x: str(x).replace("s ’","s’"))
+    data['where']=data['where'].apply(lambda x: str(x).replace(" - ","-"))
+    data['where']=data['where'].apply(lambda x: str(x).replace('\'','').replace('\'',''))
+#     data['where']=data['where'].apply(lambda x: str(x).replace('"','').replace('"',''))
+    data['where']=data['where'].apply(lambda x: str(x).replace('[','').replace(']','')) 
+    data['where']=data['where'].apply(lambda x: str(x).rstrip(','))
+    data['where']=data['where'].apply(lambda x: str(x).lstrip(','))
+    data['where']=data['where'].apply(lambda x: str(x).replace('None,','').replace('None','')) 
+    data['where']=data['where'].apply(remove_trail_comma)
+    return data
+#-------------------------------------------------------------------------
+def split_ws(input_list):
+    import re
+    output_list = []
+    for item in input_list:
+        split_item = re.findall(r'[^",]+|"[^"]*"', item)
+        output_list += split_item
+    result = [x.strip() for x in output_list]
+    return result
+
+#--------------------------------------------------------------------------    
+def gen_qq(df):
+    w_list=["who","when","where","what","why"]
+    ans=[]
+    cl=[]
+    ind=[]
+    ques=[]
+    evid=[]
+    for index,value in enumerate(w_list):
+        for i,row in df.iterrows():
+            srl=df[value][i]
+            claim=df['claim'][i]
+            evidence_text=df['evidence'][i]
+            answer= split_ws(df[value])
+            try:
+                if len(srl.split())>0 and len(srl.split(","))>0:
+                    for j in range(0,len(answer)):
+                        FACT_TO_GENERATE_QUESTION_FROM = f"""{answer[j]} [SEP] {claim}"""
+                        question_ids = query({"inputs":FACT_TO_GENERATE_QUESTION_FROM, 
+                                  "num_beams":5, 
+                                  "early_stopping":True})
+                        #print("claim : {}".format(claim))
+                        #print("answer : {}".format(answer[j]))
+                        #print("question : {}".format(question_ids[0]['generated_text']))
+                        ind.append(i)
+                        cl.append(claim)
+                        ans.append(answer[j])
+                        ques.append(question_ids[0]['generated_text'].capitalize())
+                        evid.append(evidence_text)
+                        #print("-----------------------------------------")
+            except:
+                pass
+    return cl,ques,ans,evid
+#------------------------------------------------------------    
+def qa_evidence(final_data):
+    ans=[]
+    cl=[]
+    #ind=[]
+    ques=[]
+    evi=[]
+    srl_ans=[]
+
+
+    for i,row in final_data.iterrows():
+        question=final_data['gen_question'][i]
+        evidence=final_data['evidence'][i]
+        claim=final_data['actual_claim'][i]
+        srl_answer=final_data['actual_answer'][i]
+        #index=df["index"][i]
+
+        input_evidence = f"question: {question} context: {evidence}"
+
+        answer = query_evidence({
+            "inputs":input_evidence,
+            "truncation":True})
+
+        #ind.append(index)
+        cl.append(claim)
+        ans.append(answer[0]["generated_text"])
+        ques.append(question)
+        evi.append(evidence)
+        srl_ans.append(srl_answer)
+
+        #print(f"""index: {index}""")
+#         print(f"""evidence: {evidence}""")
+#         print(f"""claim: {claim}""")
+#         print(f"""Question: {question}""")
+#         print(f"""Answer: {answer}""")
+#         print(f"""SRL Answer: {srl_answer}""")
+#         print("------------------------------------")
+#     return list(zip(cl,ques,srl_ans)),list(zip(evi,ques,ans))
+#     return cl,ques
+    return list(zip(ques,srl_ans)),list(zip(ques,ans))
+
+#------------------------------------------------------------  
+
+if claim_text:
+    if evidence_text:
+        df=claim(claim_text)
+        df["evidence"]=evidence_text
+        actual_claim,gen_question,actual_answer,evidence=gen_qq(df)
+        final_data=pd.DataFrame([actual_claim,gen_question,actual_answer,evidence]).T
+        final_data.columns=["actual_claim","gen_question","actual_answer","evidence"]
+        a,b=qa_evidence(final_data)
+#         qa_evidence(final_data)
+#         st.json(qa_evidence(final_data))
+        st.json({'QA pair from claim':[{"Question": qu, "Answer": an} for qu, an in a],
+                'QA pair from evidence':[{"Question": qu, "Answer": an} for qu, an in b]})