Update app.py

app.py

@@ -1,19 +1,9 @@
 # -*- coding: utf-8 -*-
 """
 # MANIFESTO ANALYSIS
-
-## IMPORTING LIBRARIES
 """
 
-# Commented out IPython magic to ensure Python compatibility.
-# %%capture
-# !pip install tika
-# !pip install clean-text
-# !pip install gradio
-
-# Commented out IPython magic to ensure Python compatibility.
-
-
+##IMPORTING LIBRARIES
 import random
 import matplotlib.pyplot as plt
 import nltk
@@ -21,14 +11,11 @@ from nltk.tokenize import word_tokenize,sent_tokenize
 from nltk.corpus import stopwords
 from nltk.stem.porter import PorterStemmer
 from nltk.stem import WordNetLemmatizer
-#import tika
-#from tika import parser
 from nltk.corpus import stopwords 
 from nltk.tokenize import word_tokenize
 from nltk.probability import FreqDist
 from cleantext import clean
 import textract
-
 import urllib.request
 import nltk.corpus  
 from nltk.text import Text
@@ -38,7 +25,6 @@ import sys
 import pandas as pd
 import cv2
 import re
-
 from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
 from textblob import TextBlob
 from PIL import Image
@@ -52,7 +38,6 @@ import unidecode
 nltk.download('stopwords')
 nltk.download('punkt')
 nltk.download('wordnet')
-nltk.download('averaged_perceptron_tagger')
 nltk.download('words')
 
 
@@ -111,10 +96,11 @@ def Preprocess(textParty):
 
 
 
-# Using Concordance,you can see each time a word is used, along with its 
-# immediate context. It can give you a peek into how a word is being used
-# at the sentence level and what words are used with it. 
-
+'''
+  Using Concordance, you can see each time a word is used, along with its 
+  immediate context. It can give you a peek into how a word is being used
+  at the sentence level and what words are used with it. 
+'''
 def concordance(text_Party,strng):
   word_tokens_party = word_tokenize(text_Party)
   moby = Text(word_tokens_party) 
@@ -136,7 +122,7 @@ def normalize(d, target=1.0):
 
 def fDistance(text2Party):
   '''
-  most frequent words search
+  Most frequent words search
   '''
   word_tokens_party = word_tokenize(text2Party) #Tokenizing
   fdistance = FreqDist(word_tokens_party).most_common(10)
@@ -188,7 +174,6 @@ def getAnalysis(score):
   else:
     return 'Positive'
 
-#http://library.bjp.org/jspui/bitstream/123456789/2988/1/BJP-Election-english-2019.pdf
 url = "http://library.bjp.org/jspui/bitstream/123456789/2988/1/BJP-Election-english-2019.pdf"
 path_input = "./Bjp_Manifesto_2019.pdf'"
 urllib.request.urlretrieve(url, filename=path_input)
@@ -216,8 +201,6 @@ def analysis(Manifesto,Search):
   plt.ylabel('Counts')
   plt.figure(figsize=(4,3))
   df['Analysis on Polarity'].value_counts().plot(kind ='bar')
-  #plt.savefig('./sentimentAnalysis.png')
-  #plt.clf()
   plt.tight_layout()
   buf = BytesIO()
   plt.savefig(buf)
@@ -227,8 +210,6 @@ def analysis(Manifesto,Search):
   
   plt.figure(figsize=(4,3))
   df['Analysis on Subjectivity'].value_counts().plot(kind ='bar')
-  #plt.savefig('sentimentAnalysis2.png')
-  #plt.clf()  
   plt.tight_layout()
   buf = BytesIO()
   plt.savefig(buf)
@@ -249,11 +230,6 @@ def analysis(Manifesto,Search):
   
   fdist_Party=fDistance(text_Party)
   img4=fDistancePlot(text_Party)
-
-  #img1=cv2.imread('/sentimentAnalysis.png')
-  #img2=cv2.imread('/wordcloud.png')
-  #img3=cv2.imread('/wordcloud.png')
-  #img4=cv2.imread('/distplot.png')
   
   searchRes=concordance(text_Party,Search)
   searChRes=clean(searchRes)
@@ -265,7 +241,6 @@ Search_txt=gr.inputs.Textbox()
 filePdf = gr.inputs.File()
 text = gr.outputs.Textbox(label='SEARCHED OUTPUT')
 mfw=gr.outputs.Label(label="Most Relevant Topics")
-# mfw2=gr.outputs.Image(label="Most Relevant Topics Plot")
 plot1=gr.outputs. Image(label='Sentiment Analysis')
 plot2=gr.outputs.Image(label='Subjectivity Analysis')
 plot3=gr.outputs.Image(label='Word Cloud')