Merge branch 'IT17100908' into 'QA_RELEASE'

It17100908

See merge request !19

LectureSummarizingApp/Summary.py

-
-import spacy
-
 from spacy.lang.pt.stop_words import STOP_WORDS
 from sklearn.feature_extraction.text import CountVectorizer
 import pt_core_news_sm
 
+
+# Reading the file
 nlp = pt_core_news_sm.load()
 with open("audioToText01.txt", "r", encoding="utf-8") as f:
     text = " ".join(f.readlines())
 
 doc = nlp(text)
 
+#calculating the word frequency
 corpus = [sent.text.lower() for sent in doc.sents ]
 cv = CountVectorizer(stop_words=list(STOP_WORDS))
 cv_fit=cv.fit_transform(corpus)
@@ -18,6 +18,7 @@ word_list = cv.get_feature_names()
 count_list = cv_fit.toarray().sum(axis=0)
 word_frequency = dict(zip(word_list,count_list))
 
+
 val=sorted(word_frequency.values())
 higher_word_frequencies = [word for word,freq in word_frequency.items() if freq in val[-3:]]
 print("\nWords with higher frequencies: ", higher_word_frequencies)
@@ -26,6 +27,7 @@ higher_frequency = val[-1]
 for word in word_frequency.keys():
     word_frequency[word] = (word_frequency[word]/higher_frequency)
 
+#calculating sentence rank and taking top ranked sentences for the summary
 sentence_rank={}
 for sent in doc.sents:
     for word in sent :

LectureSummarizingApp/Summary01.txt

+What is OOP OBJECT ORIENTED PROGRAMMING is a programming concept that works on the principles of abstraction, encapsulation, inheritance, and polymorphism. The basic concept of OOPs is to create objects, re-use them throughout the program, and manipulate these objects to get results. Object Oriented Programming popularly known as OOP, is used in a modern programming language like Java OBJECT ORIENTED PROGRAMMING is a programming concept that works on the principles of abstraction, encapsulation, inheritance and polymorphism the basic concept of OOPs is to create objects re-use them in the program and manipulate these objects to get results Object Oriented Programming popularly known as OOP, is used in programming language like Java. Core OOPS concepts are as follow. While the methods may be performed with these cars are driving, reverse, braking etc. next is Object An object can be defined as an instance of a class, and there can be multiple instances of a class in a program.
\ No newline at end of file

LectureSummarizingApp/api.py

@@ -9,7 +9,7 @@ from LectureSummarizingApp.serializer import LectureAudioSerializer, LectureAudi
 from . import speech_to_text as stt
 
 
-# this API will retrieve lecture audio details
+# APIs used in Lecture Summarizing Component
 class LectureAudioAPI(APIView):
 
     def get(self, request):

LectureSummarizingApp/models.py

-# from django.db import models
 from djongo import models
 
-# Create your models here.
+# Models used in Lecture Summarization Component
 from FirstApp.MongoModels import Lecturer, Subject
 
 

LectureSummarizingApp/serializer.py

@@ -4,6 +4,7 @@ from FirstApp.serializers import LecturerSerializer, SubjectSerializer
 from . models import *
 
 
+#serializers used in Lecture Summarizing Component
 class LectureAudioSerializer(serializers.ModelSerializer):
 
     lecturer = LecturerSerializer()
@@ -23,7 +24,6 @@ class LectureAudioNoiseRemovedSerializer(serializers.ModelSerializer):
 
 
 class LectureSpeechToTextSerializer(serializers.ModelSerializer):
-    # lecture_speech_to_text_id = LectureAudioNoiseRemovedSerializer()
     lecture_audio_id = LectureAudioSerializer()
 
     class Meta:
@@ -32,7 +32,6 @@ class LectureSpeechToTextSerializer(serializers.ModelSerializer):
 
 
 class LectureAudioSummarySerializer(serializers.ModelSerializer):
-    # lecture_audio_noise_removed_id = LectureSpeechToTextSerializer()
     lecture_audio_id = LectureAudioSerializer()
 
     class Meta:
@@ -41,10 +40,8 @@ class LectureAudioSummarySerializer(serializers.ModelSerializer):
 
 
 class LectureNoticesSerializer(serializers.ModelSerializer):
-    # lecture_audio_noise_removed_id = LectureSpeechToTextSerializer()
     lecture_audio_id = LectureAudioSerializer()
 
     class Meta:
-        # model = LectureAudioSummary
         model = LectureNotices
         fields = '__all__'
\ No newline at end of file

LectureSummarizingApp/speech_to_text.py

@@ -4,17 +4,17 @@ import os
 
 def speech_to_text(video_name):
 
+#calling the Recognizer()
     r = sr.Recognizer()
 
     BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-
     VIDEO_PATH = os.path.join(BASE_DIR, "lectures\\{}".format(video_name))
 
     with sr.AudioFile(VIDEO_PATH) as source:
         audio = r.listen(source)
-        file = open('audioToText01.txt', 'w')
+        file = open('audioToText01.txt', 'w') #open file
         try:
-            text = r.recognize_google(audio)
+            text = r.recognize_google(audio) #Convert using google recognizer
             file.write(text)
         except:
             file.write('error')

LectureSummarizingApp/urls.py

@@ -5,27 +5,12 @@ from django.conf.urls import url
 from . import api
 
 router = routers.DefaultRouter()
-# router.register(r'^register', views.register)
 
 urlpatterns = [
     path('lecture', views.summarization),
-    # path('', views.hello),
-    # path('login', views.login),
-    # path('register', views.register),
-    # path('404', views.view404),
-    # path('blank', views.blank),
-    # path('buttons', views.buttons),
-    # path('cards', views.cards),
-    # path('charts', views.charts),
-    # path('forgot-password', views.forget_password),
-    # # path('webcam', views.webcam),
-    # path('template', views.template),
-    # path('base', views.base),
-    # path('child', views.child),
-    # path('lecture-video', views.lecVideo),
-    # # path('Video', views.hello)
-
-    # API to retrieve activity recognition
+
+
+    # API to retrieve lecture summarizing details
     url(r'^lecture-audio/$', api.LectureAudioAPI.as_view()),
 
     url(r'^lecture-audio-noise-removed/$', api.audioNoiseRemovedList.as_view()),
@@ -36,15 +21,6 @@ urlpatterns = [
 
     url(r'^lecture-notices/$', api.lectureNoticeList.as_view()),
 
-    # # API to retrieve audio analysis
-    # url(r'^get-audio-analysis', api.GetLectureAudioAnalysis.as_view()),
-    #
-    # # API to retrieve lecture audio text
-    # url(r'^get-lecture-audio-text', api.LectureAudioTextAPI.as_view()),
-    #
-    # # test API
-    # url(r'^test-api', api.TestAPI.as_view()),
-
     path('api-auth/', include('rest_framework.urls', namespace='rest_framework'))
 
 ]

LectureSummarizingApp/views.py

-from django.contrib.auth.decorators import login_required
-from django.http import HttpResponse
 from django.shortcuts import get_object_or_404, render
 from rest_framework.views import APIView
 from rest_framework.response import Response
@@ -9,7 +7,7 @@ from .serializer import LectureAudioSerializer, LectureAudioNoiseRemovedSerializ
     LectureSpeechToTextSerializer, LectureNoticesSerializer
 
 
-# Create your views here.
+# Views used in Lecture Summarization
 
 def summarization(request):