Update app.py

app.py

@@ -142,42 +142,93 @@ def fDistance(text2Party):
     mem[x[0]]=x[1]
   return normalize(mem)
 
-def fDistancePlot(text2Party,plotN=20):
+def fDistancePlot(text2Party,plotN=30):
   '''
-  most frequent words visualisation
+  most frequent words visualization
   '''
   word_tokens_party = word_tokenize(text2Party) #Tokenizing
   fdistance = FreqDist(word_tokens_party)
-  return fdistance.plot(20)
+  plt.figure(figsize=(4,6))
+  fdistance.plot(plotN)
+  plt.savefig('distplot.png')
+  plt.clf()
 
 
 
-## UI INTERFACE
+def getSubjectivity(text):
+   return TextBlob(text).sentiment.subjectivity
+
+# Create a function to get the polarity
+def getPolarity(text):
+   return  TextBlob(text).sentiment.polarity
+  
+  
+def getAnalysis(score):
+  if score < 0:
+    return 'Negative'
+  elif score == 0:
+    return 'Neutral'
+  else:
+    return 'Positive'
+
+
 
 def analysis(Manifesto,Search):
   raw_party = Parsing(Manifesto)
   text_Party=clean_text(raw_party)
   text_Party= Preprocess(text_Party)
+
+  df = pd.DataFrame(raw_party.split('\n'), columns=['Content'])
+  df['Subjectivity'] = df['Content'].apply(getSubjectivity)
+  df['Polarity'] = df['Content'].apply(getPolarity)
+  df['Analysis on Polarity'] = df['Polarity'].apply(getAnalysis)
+  df['Analysis on Subjectivity'] = df['Subjectivity'].apply(getAnalysis)
+  plt.title('Sentiment Analysis')
+  plt.xlabel('Sentiment')
+  plt.ylabel('Counts')
+  plt.figure(figsize=(4,6))
+  df['Analysis on Polarity'].value_counts().plot(kind ='bar')
+  plt.savefig('sentimentAnalysis.png')
+  plt.clf()
+  
+  plt.figure(figsize=(4,6))
+  df['Analysis on Subjectivity'].value_counts().plot(kind ='bar')
+  plt.savefig('sentimentAnalysis2.png')
+  plt.clf()  
+  
+  wordcloud = WordCloud(max_words=2000, background_color="white",mode="RGB").generate(text_Party)
+  plt.figure(figsize=(4,3))
+  plt.imshow(wordcloud, interpolation="bilinear")
+  plt.axis("off")
+  plt.savefig('wordcloud.png')
+  plt.clf()  
+  
   fdist_Party=fDistance(text_Party)
+  fDistancePlot(text_Party)
+
+  img1=cv2.imread('../sentimentAnalysis.png')
+  img2=cv2.imread('../wordcloud.png')
+  img3=cv2.imread('../sentimentAnalysis2.png')
+  img4=cv2.imread('../distplot.png')
+  
   searchRes=concordance(text_Party,Search)
   searChRes=clean(searchRes)
-  # searChRes=searchRes.replace(Search,f"\u0332{Search}\u0332 ")
   searChRes=searchRes.replace(Search,"\u0332".join(Search))
-  return fdist_Party,searChRes
+  return searChRes,fdist_Party,img4,img1,img2,img3
 
   
 Search_txt=gr.inputs.Textbox()   
 filePdf = gr.inputs.File()
 text = gr.outputs.Textbox(label='SEARCHED OUTPUT')
-mfw=gr.outputs.Label(label="Most Relevant topics in manifesto")
-
-gr.Interface(fn=analysis, inputs=[filePdf,Search_txt], outputs=[mfw,text], title='Manifesto Analysis').launch(debug=False,share=True)
-
-
-
-
-
-
+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='Word Cloud')
+plot3=gr.outputs.Image(label='Subjectivity')
+plot4=gr.outputs.Image(label='Frequency Distribution')
+
+io=gr.Interface(fn=analysis, inputs=[filePdf,Search_txt], outputs=[text,mfw,plot4,plot1,plot2,plot3], title='Manifesto Analysis')
+io.launch(debug=False,share=True)