File size: 11,078 Bytes
4ea0ccb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
# -*- coding: utf-8 -*-
"""QuestionGenerator.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1k0AavzSaNYxe36bk65fsXWzC4xSSwo6X
"""

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


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)
  print ("\n\nNoun phrases",np)
  output="<b style='color:black;'>Answer the following short questions.</b><br><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 style='color:black;'>Q"+ str(i) + ") " + ques + "</b><br>"
    # output = output + "<br>"
    output = output + "<br>"
    i += 1
    
  output = output + "<br><b style='color:black;'>" + "Correct Answer Key:</b><br>"

  i=1
  for answer in np:
    output = output + "<b style='color:green;'>" + "Ans"+ str(i) + ": " +answer.capitalize()+  "</b>"
    output = output + "<br>"
    i += 1

  mycursor = mydb.cursor()
  timedate = datetime.datetime.now()

  sql = "INSERT INTO shorttexts (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)
  print ("\n\nNoun phrases",np)
  output="<b style='color:black;'>Answer the following short questions.</b><br><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 style='color:black;'>Q"+ str(i) + ") " + ques + "</b><br>"
    # output = output + "<br>"
    output = output + "<br>"
    i += 1
    
  output = output + "<br><b style='color:black;'>" + "Correct Answer Key:</b><br>"

  i=1
  for answer in np:
    output = output + "<b style='color:green;'>" + "Ans"+ str(i) + ": " +answer.capitalize()+  "</b>"
    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 shortfiles (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()
subject = gr.Textbox(placeholder="Enter subject/title here...", label="Text")
total = gr.Slider(1,10, value=1,step=1, label="Total Number Of Questions")


# output = gr.HTML( label="Question and Answers")

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)