Sa-m's picture
Update app.py
cd5b6e7
"""
# MANIFESTO ANALYSIS
"""
##IMPORTING LIBRARIES
import random
import matplotlib.pyplot as plt
import nltk
from nltk.tokenize import word_tokenize,sent_tokenize
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from nltk.stem import WordNetLemmatizer
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
import io
from io import StringIO,BytesIO
import sys
import pandas as pd
import cv2
import re
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
from textblob import TextBlob
from PIL import Image
import os
import gradio as gr
from zipfile import ZipFile
import contractions
import unidecode
nltk.download('stopwords')
nltk.download('punkt')
nltk.download('wordnet')
nltk.download('words')
"""## PARSING FILES"""
#def Parsing(parsed_text):
#parsed_text=parsed_text.name
#raw_party =parser.from_file(parsed_text)
# raw_party = raw_party['content'],cache_examples=True
# return clean(raw_party)
def Parsing(parsed_text):
parsed_text=parsed_text.name
raw_party =textract.process(parsed_text, encoding='ascii',method='pdfminer')
return clean(raw_party)
#Added more stopwords to avoid irrelevant terms
stop_words = set(stopwords.words('english'))
stop_words.update('ask','much','thank','etc.', 'e', 'We', 'In', 'ed','pa', 'This','also', 'A', 'fu','To','5','ing', 'er', '2')
"""## PREPROCESSING"""
def clean_text(text):
'''
The function which returns clean text
'''
text = text.encode("ascii", errors="ignore").decode("ascii") # remove non-asciicharacters
text=unidecode.unidecode(text)# diacritics remove
text=contractions.fix(text) # contraction fix
text = re.sub(r"\n", " ", text)
text = re.sub(r"\n\n", " ", text)
text = re.sub(r"\t", " ", text)
text = re.sub(r"/ ", " ", text)
text = text.strip(" ")
text = re.sub(" +", " ", text).strip() # get rid of multiple spaces and replace with a single
text = [word for word in text.split() if word not in stop_words]
text = ' '.join(text)
return text
# text_Party=clean_text(raw_party)
def Preprocess(textParty):
'''
Removing special characters extra spaces
'''
text1Party = re.sub('[^A-Za-z0-9]+', ' ', textParty)
#Removing all stop words
pattern = re.compile(r'\b(' + r'|'.join(stopwords.words('english')) + r')\b\s*')
text2Party = pattern.sub('', text1Party)
# fdist_cong = FreqDist(word_tokens_cong)
return text2Party
'''
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 conc(text_Party,strng):
word_tokens_party = word_tokenize(text_Party)
moby = Text(word_tokens_party)
resultList = []
for i in range(0,1):
save_stdout = sys.stdout
result = StringIO()
sys.stdout = result
moby.concordance(strng,lines=4,width=82)
sys.stdout = save_stdout
s=result.getvalue().splitlines()
return result.getvalue()
def get_all_phases_containing_tar_wrd(target_word, tar_passage, left_margin = 10, right_margin = 10,numLins=4):
"""
Function to get all the phases that contain the target word in a text/passage tar_passage.
Workaround to save the output given by nltk Concordance function
str target_word, str tar_passage int left_margin int right_margin --> list of str
left_margin and right_margin allocate the number of words/pununciation before and after target word
Left margin will take note of the beginning of the text
"""
## Create list of tokens using nltk function
tokens = nltk.word_tokenize(tar_passage)
## Create the text of tokens
text = nltk.Text(tokens)
## Collect all the index or offset position of the target word
c = nltk.ConcordanceIndex(text.tokens, key = lambda s: s.lower())
## Collect the range of the words that is within the target word by using text.tokens[start;end].
## The map function is use so that when the offset position - the target range < 0, it will be default to zero
concordance_txt = ([text.tokens[list(map(lambda x: x-5 if (x-left_margin)>0 else 0,[offset]))[0]:offset+right_margin] for offset in c.offsets(target_word)])
## join the sentences for each of the target phrase and return it
result = [''.join([x.replace("Y","")+' ' for x in con_sub]) for con_sub in concordance_txt][:-1]
result=result[:numLins+1]
res='\n\n'.join(result)
return res
def normalize(d, target=1.0):
raw = sum(d.values())
factor = target/raw
return {key:value*factor for key,value in d.items()}
def fDistance(text2Party):
'''
Most frequent words search
'''
word_tokens_party = word_tokenize(text2Party) #Tokenizing
fdistance = FreqDist(word_tokens_party).most_common(10)
mem={}
for x in fdistance:
mem[x[0]]=x[1]
return normalize(mem)
def fDistancePlot(text2Party,plotN=15):
'''
Most Frequent Words Visualization
'''
word_tokens_party = word_tokenize(text2Party) #Tokenizing
fdistance = FreqDist(word_tokens_party)
plt.title('Frequency Distribution')
plt.axis('off')
plt.figure(figsize=(4,3))
fdistance.plot(plotN)
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img1 = Image.open(buf)
plt.clf()
return img1
def DispersionPlot(textParty):
'''
Dispersion PLot
'''
word_tokens_party = word_tokenize(textParty) #Tokenizing
moby = Text(word_tokens_party)
fdistance = FreqDist(word_tokens_party)
word_Lst=[]
for x in range(5):
word_Lst.append(fdistance.most_common(6)[x][0])
plt.axis('off')
plt.figure(figsize=(4,3))
plt.title('Dispersion Plot')
moby.dispersion_plot(word_Lst)
plt.plot(color="#EF6D6D")
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img = Image.open(buf)
plt.clf()
return img
def getSubjectivity(text):
'''
Create a function to get the polarity
'''
return TextBlob(text).sentiment.subjectivity
def getPolarity(text):
'''
Create a function to get the polarity
'''
return TextBlob(text).sentiment.polarity
def getAnalysis(score):
if score < 0:
return 'Negative'
elif score == 0:
return 'Neutral'
else:
return 'Positive'
def Original_Image(path):
img= cv2.imread(path)
img= cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
return img
def Image_Processed(path):
'''
Reading the image file
'''
img= cv2.imread(path)
img= cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
#Thresholding
ret, bw_img = cv2.threshold(img, 124, 255, cv2.THRESH_BINARY)
return bw_img
def word_cloud(orgIm,mask_img,text_Party_pr,maxWord=2000,colorGener=True,
contCol='white',bckColor='white'):
'''
#Generating word cloud
'''
mask =mask_img
# Create and generate a word cloud image:
wordcloud = WordCloud(max_words=maxWord, background_color=bckColor,
mask=mask,
colormap='nipy_spectral_r',
contour_color=contCol,
width=800, height=800,
margin=2,
contour_width=3).generate(text_Party_pr)
# create coloring from image
plt.axis("off")
if colorGener==True:
image_colors = ImageColorGenerator(orgIm)
plt.imshow(wordcloud.recolor(color_func= image_colors),interpolation="bilinear")
else:
plt.imshow(wordcloud)
def word_cloud_generator(parsed_text_name,text_Party):
parsed=parsed_text_name.lower()
if 'bjp' in parsed:
orgImg=Original_Image('bjpImg2.jpeg')
bwImg=Image_Processed('bjpImg2.jpeg')
plt.figure(figsize=(6,5))
word_cloud(orgImg,bwImg,text_Party,maxWord=3000,colorGener=True,
contCol='white', bckColor='black')
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img1 = Image.open(buf)
plt.clf()
return img1
elif 'congress' in parsed:
orgImg=Original_Image('congress3.jpeg')
bwImg=Image_Processed('congress3.jpeg')
plt.figure(figsize=(5,4))
word_cloud(orgImg,bwImg,text_Party,maxWord=3000,colorGener=True)
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img2 = Image.open(buf)
plt.clf()
return img2
#congrsMain.jpg
elif 'aap' in parsed:
orgImg=Original_Image('aapMain2.jpg')
bwImg=Image_Processed('aapMain2.jpg')
plt.figure(figsize=(5,4))
word_cloud(orgImg,bwImg,text_Party,maxWord=3000,colorGener=False,contCol='black')
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img3 = Image.open(buf)
plt.clf()
return img3
else :
wordcloud = WordCloud(max_words=2000, background_color="white",mode="RGB").generate(text_Party)
plt.figure(figsize=(5,5))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img4 = Image.open(buf)
plt.clf()
return img4
'''
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)
url="https://drive.google.com/uc?id=1BLCiy_BWilfVdrUH8kbO-44DJevwO5CG&export=download"
path_input = "./Aap_Manifesto_2019.pdf"
urllib.request.urlretrieve(url, filename=path_input)
url="https://drive.google.com/uc?id=1HVZvTtYntl0YKLnE0cwu0CvAIRhXOv60&export=download"
path_input = "./Congress_Manifesto_2019.pdf"
urllib.request.urlretrieve(url, filename=path_input)
'''
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=(4,3))
df['Analysis on Polarity'].value_counts().plot(kind ='bar',color="#FF9F45")
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img1 = Image.open(buf)
plt.clf()
plt.figure(figsize=(4,3))
df['Analysis on Subjectivity'].value_counts().plot(kind ='bar',color="#B667F1")
plt.tight_layout()
buf = BytesIO()
plt.savefig(buf)
buf.seek(0)
img2 = Image.open(buf)
plt.clf()
img3 = word_cloud_generator(Manifesto.name,text_Party)
fdist_Party=fDistance(text_Party)
img4=fDistancePlot(text_Party)
img5=DispersionPlot(text_Party)
#concordance(text_Party,Search)
searChRes=get_all_phases_containing_tar_wrd(Search,text_Party)
searChRes=searChRes.replace(Search,"\u0332".join(Search))
plt.close('all')
return searChRes,fdist_Party,img1,img2,img3,img4,img5
Search_txt= "text"
filePdf = "file"
text = gr.outputs.Textbox(label='Context Based Search')
mfw=gr.outputs.Label(label="Most Relevant Topics")
plot1=gr.outputs.Image(label='Sentiment Analysis')
plot2=gr.outputs.Image(label='Subjectivity Analysis')
plot3=gr.outputs.Image(label='Word Cloud')
plot4=gr.outputs.Image(label='Frequency Distribution')
plot5=gr.outputs.Image(label='Dispersion Plot')
io=gr.Interface(fn=analysis, inputs=[filePdf,Search_txt], outputs=[text,mfw,plot1,plot2,plot3,plot4,plot5], title='Manifesto Analysis',examples=[['Example/AAP_Manifesto_2019.pdf','government'],['Example/Bjp_Manifesto_2019.pdf','environment'],['Example/Congress_Manifesto_2019.pdf','safety']],theme='peach')
io.launch(debug=True,share=False)
#allow_screenshot=False,allow_flagging="never",
#examples=[['manifestos/Bjp_Manifesto_2019.pdf','modi'],['AAP_Manifesto_2019.pdf','delhi'],['manifestos/Congress_Manifesto_2019.pdf','safety']])