Upload app.py

app.py

@@ -0,0 +1,365 @@
+# -*- coding: utf-8 -*-
+"""MatchingGenerator.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1drOrBUfaj_UMytwxar_keRWNm5ScaBi7
+"""
+
+from textwrap3 import wrap
+
+text = """A Lion lay asleep in the forest, his great head resting on his paws. A timid little Mouse came upon him unexpectedly, and in her fright and haste to
+get away, ran across the Lion's nose. Roused from his nap, the Lion laid his huge paw angrily on the tiny creature to kill her.  "Spare me!" begged
+the poor Mouse. "Please let me go and some day I will surely repay you."  The Lion was much amused to think that a Mouse could ever help him. But he
+was generous and finally let the Mouse go.  Some days later, while stalking his prey in the forest, the Lion was caught in the toils of a hunter's
+net. Unable to free himself, he filled the forest with his angry roaring. The Mouse knew the voice and quickly found the Lion struggling in the net.
+Running to one of the great ropes that bound him, she gnawed it until it parted, and soon the Lion was free.  "You laughed when I said I would repay
+you," said the Mouse. "Now you see that even a Mouse can help a Lion." """
+for wrp in wrap(text, 150):
+  print (wrp)
+print ("\n")
+
+import torch
+from transformers import T5ForConditionalGeneration,T5Tokenizer
+summary_model = T5ForConditionalGeneration.from_pretrained('t5-base')
+summary_tokenizer = T5Tokenizer.from_pretrained('t5-base')
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+summary_model = summary_model.to(device)
+
+import random
+import numpy as np
+
+def set_seed(seed: int):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+
+set_seed(42)
+
+import nltk
+# nltk.download('punkt')
+# nltk.download('brown')
+# nltk.download('wordnet')
+from nltk.corpus import wordnet as wn
+from nltk.tokenize import sent_tokenize
+
+def postprocesstext (content):
+  final=""
+  for sent in sent_tokenize(content):
+    sent = sent.capitalize()
+    final = final +" "+sent
+  return final
+
+
+def summarizer(text,model,tokenizer):
+  text = text.strip().replace("\n"," ")
+  text = "summarize: "+text
+  # print (text)
+  max_len = 512
+  encoding = tokenizer.encode_plus(text,max_length=max_len, pad_to_max_length=False,truncation=True, return_tensors="pt").to(device)
+
+  input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]
+
+  outs = model.generate(input_ids=input_ids,
+                                  attention_mask=attention_mask,
+                                  early_stopping=True,
+                                  num_beams=3,
+                                  num_return_sequences=1,
+                                  no_repeat_ngram_size=2,
+                                  min_length = 75,
+                                  max_length=300)
+
+
+  dec = [tokenizer.decode(ids,skip_special_tokens=True) for ids in outs]
+  summary = dec[0]
+  summary = postprocesstext(summary)
+  summary= summary.strip()
+
+  return summary
+
+
+summarized_text = summarizer(text,summary_model,summary_tokenizer)
+
+
+print ("\noriginal Text >>")
+for wrp in wrap(text, 150):
+  print (wrp)
+print ("\n")
+print ("Summarized Text >>")
+for wrp in wrap(summarized_text, 150):
+  print (wrp)
+print ("\n")
+
+total = 10
+
+"""# **Answer Span Extraction (Keywords and Noun Phrases)**"""
+
+import nltk
+nltk.download('stopwords')
+from nltk.corpus import stopwords
+import string
+import pke
+import traceback
+
+
+def get_nouns_multipartite(content):
+    out=[]
+    try:
+        # extractor = spacy.load("en_core_web_sm")
+        extractor = pke.unsupervised.MultipartiteRank()
+
+        extractor.load_document(input=content,language='en')
+
+        #    not contain punctuation marks or stopwords as candidates.
+        pos = {'PROPN','NOUN'}
+        #pos = {'PROPN','NOUN'}
+        stoplist = list(string.punctuation)
+        stoplist += ['-lrb-', '-rrb-', '-lcb-', '-rcb-', '-lsb-', '-rsb-']
+        stoplist += stopwords.words('english')
+        # extractor.candidate_selection(pos=pos, stoplist=stoplist)
+        extractor.candidate_selection(pos=pos)
+        # 4. build the Multipartite graph and rank candidates using random walk,
+        #    alpha controls the weight adjustment mechanism, see TopicRank for
+        #    threshold/method parameters.
+        extractor.candidate_weighting(alpha=1.1,
+                                      threshold=0.75,
+                                      method='average')
+        keyphrases = extractor.get_n_best(n=15)
+        
+
+        for val in keyphrases:
+            out.append(val[0])
+    except:
+        out = []
+        traceback.print_exc()
+
+    return out
+
+from flashtext import KeywordProcessor
+
+def get_keywords(originaltext,summarytext,total):
+  keywords = get_nouns_multipartite(originaltext)
+  print ("keywords unsummarized: ",keywords)
+  keyword_processor = KeywordProcessor()
+  for keyword in keywords:
+    keyword_processor.add_keyword(keyword)
+
+  keywords_found = keyword_processor.extract_keywords(summarytext)
+  keywords_found = list(set(keywords_found))
+  print ("keywords_found in summarized: ",keywords_found)
+
+  important_keywords =[]
+  for keyword in keywords:
+    if keyword in keywords_found:
+      important_keywords.append(keyword)
+
+  return important_keywords[:total]
+
+
+imp_keywords = get_keywords(text,summarized_text,total)
+print (imp_keywords)
+
+"""# **Question generation using T5**"""
+
+question_model = T5ForConditionalGeneration.from_pretrained('ramsrigouthamg/t5_squad_v1')
+question_tokenizer = T5Tokenizer.from_pretrained('ramsrigouthamg/t5_squad_v1')
+question_model = question_model.to(device)
+
+def get_question(context,answer,model,tokenizer):
+  text = "context: {} answer: {}".format(context,answer)
+  encoding = tokenizer.encode_plus(text,max_length=384, pad_to_max_length=False,truncation=True, return_tensors="pt").to(device)
+  input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]
+
+  outs = model.generate(input_ids=input_ids,
+                                  attention_mask=attention_mask,
+                                  early_stopping=True,
+                                  num_beams=5,
+                                  num_return_sequences=1,
+                                  no_repeat_ngram_size=2,
+                                  max_length=72)
+
+
+  dec = [tokenizer.decode(ids,skip_special_tokens=True) for ids in outs]
+
+
+  Question = dec[0].replace("question:","")
+  Question= Question.strip()
+  return Question
+
+# for wrp in wrap(summarized_text, 150):
+#   print (wrp)
+# print ("\n")
+
+# for answer in imp_keywords:
+#   ques = get_question(summarized_text,answer,question_model,question_tokenizer)
+#   print (ques)
+#   print (answer.capitalize())
+#   print ("\n")
+
+"""# **UI by using Gradio**"""
+
+import mysql.connector
+import datetime;
+
+mydb = mysql.connector.connect(
+  host="qtechdb-1.cexugk1h8rui.ap-northeast-1.rds.amazonaws.com",
+  user="admin",
+  password="F3v2vGWzb8vaniE3nqzi",
+  database="spring_social"
+)
+
+import gradio as gr
+import random
+
+context = gr.Textbox(lines=10, placeholder="Enter paragraph/content here...", label="Text")
+total = gr.Slider(1,10, value=1,step=1, label="Total Number Of Questions")
+subject = gr.Textbox(placeholder="Enter subject/title here...", label="Text")
+output = gr.Markdown(  label="Question and Answers")
+
+
+def generate_question_text(context,subject,total):
+  summary_text = summarizer(context,summary_model,summary_tokenizer)
+  for wrp in wrap(summary_text, 150):
+    print (wrp)
+  np =  get_keywords(context,summary_text,total)
+  random.shuffle(np)
+  print ("\n\nNoun phrases",np)
+
+  output="<b>Select/Match the correct answers to the given questions.</b><br/>"
+  answerlist=[]
+
+  for answer in np:
+    answerlist.append(answer)
+    random.shuffle(answerlist)   
+  print(answerlist)
+
+  for answer in answerlist:
+    output = output + "<b style='margin-right:30px;'>" + " "*5 +answer.capitalize()+  "</b>"
+  output = output + "<br/>" 
+
+  i=1
+  for answer in np:
+    ques = get_question(summary_text,answer,question_model,question_tokenizer)
+    # output= output + ques + "\n" + "Ans: "+answer.capitalize() + "\n\n"
+    output = output + "<b> Q "+ str(i) + ")  " + ques + "</b><br/>"
+    i += 1
+
+  output = output + "<br/><b>" + "Correct Answer Key:</b><br/>"
+
+  i=1
+  for answer in np:
+    # output= output + ques + "\n" + "Ans: "+answer.capitalize() + "\n\n"
+    output = output + "<b style='color:green;'>Ans "+ str(i) + ": " +answer.capitalize()+  "</b>"
+    # random.shuffle(output)
+    output = output + "<br/>" 
+    i += 1
+  
+  mycursor = mydb.cursor()
+  timedate = datetime.datetime.now()
+
+  sql = "INSERT INTO matchtexts (subject, input, output, timedate) VALUES (%s,%s, %s,%s)"
+  val = (subject, context, output, timedate)
+  mycursor.execute(sql, val)
+
+  mydb.commit()
+
+  print(mycursor.rowcount, "record inserted.")
+  
+  return output
+
+iface = gr.Interface(
+  fn=generate_question_text, 
+  inputs=[context,subject, total], 
+  outputs=output, css=".gradio-container {background-image: url('file=blue.jpg')}",
+  allow_flagging="manual",flagging_options=["Save Data"])
+  
+# iface.launch(debug=True, share=True)
+
+def generate_question(context,subject,total):
+  summary_text = summarizer(context,summary_model,summary_tokenizer)
+  for wrp in wrap(summary_text, 150):
+    print (wrp)
+  np =  get_keywords(context,summary_text,total)
+  random.shuffle(np)
+  print ("\n\nNoun phrases",np)
+
+  output="<b>Select/Match the correct answers to the given questions.</b><br/>"
+  answerlist=[]
+
+  for answer in np:
+    answerlist.append(answer)
+    random.shuffle(answerlist)   
+  print(answerlist)
+
+  for answer in answerlist:
+    output = output + "<b style='margin-right:30px;'>" + " "*5 +answer.capitalize()+  "</b>"
+  output = output + "<br/>" 
+
+  i=1
+  for answer in np:
+    ques = get_question(summary_text,answer,question_model,question_tokenizer)
+    # output= output + ques + "\n" + "Ans: "+answer.capitalize() + "\n\n"
+    output = output + "<b> Q "+ str(i) + ")  " + ques + "</b><br/>"
+    i += 1
+
+  output = output + "<br/><b>" + "Correct Answer Key:</b><br/>"
+
+  i=1
+  for answer in np:
+    # output= output + ques + "\n" + "Ans: "+answer.capitalize() + "\n\n"
+    output = output + "<b style='color:green;'>Ans "+ str(i) + ": " +answer.capitalize()+  "</b>"
+    # random.shuffle(output)
+    output = output + "<br/>" 
+    i += 1
+  
+  return output
+
+import glob
+import os.path
+import pandas as pd
+
+file =None
+
+def filecreate(x,subject,total):
+
+    with open(x.name) as fo:  
+      text = fo.read()
+    #   print(text)
+    generated = generate_question(text,subject, total)
+    
+    mycursor = mydb.cursor()
+    timedate= datetime.datetime.now()
+
+    sql = "INSERT INTO matchfiles (subject, input, output, timedate) VALUES (%s,%s, %s,%s)"
+    val = (subject, text, generated, timedate)
+    mycursor.execute(sql, val)
+
+    mydb.commit()
+
+    print(mycursor.rowcount, "record inserted.")
+
+    return generated
+
+# filecreate(file,2)
+
+import gradio as gr
+
+context = gr.HTML(label="Text")
+file = gr.File()
+total = gr.Slider(1,10, value=1,step=1, label="Total Number Of Questions")
+subject = gr.Textbox(placeholder="Enter subject/title here...", label="Text")
+
+fface = gr.Interface(  
+  fn=filecreate, 
+  inputs=[file,subject,total], 
+  outputs=context, 
+  css=".gradio-container {background-image: url('file=blue.jpg')}", 
+  allow_flagging="manual",flagging_options=["Save Data"])
+
+# fface.launch(debug=True, share=True)
+
+demo = gr.TabbedInterface([iface, fface], ["Text", "Upload File"], css=".gradio-container {background-image: url('file=blue.jpg')}")
+demo.launch(debug=True, share=True)