app.py

"""
#App: NLP App with Streamlit
Credits: Streamlit Team, Marc Skov Madsen(For Awesome-streamlit gallery)
Description
This is a Natural Language Processing(NLP) Based App useful for basic NLP concepts such as follows;

+ Tokenization & Lemmatization using Spacy

+ Named Entity Recognition(NER) using SpaCy

+ Sentiment Analysis using TextBlob

+ Document/Text Summarization using Gensim/T5 for both Bangla and english

This is built with Streamlit Framework, an awesome framework for building ML and NLP tools.
Purpose
To perform basic and useful NLP task with Streamlit, Spacy, Textblob and Gensim
"""
# Core Pkgs
import os
#os.system('sudo apt-get install tesseract-ocr-eng')
#os.system('sudo apt-get install tesseract-ocr-ben')

#os.system('wget https://github.com/tesseract-ocr/tessdata/raw/main/ben.traineddata')
#os.system('gunzip ben.traineddata.gz ')
#os.system('sudo mv -v ben.traineddata /usr/local/share/tessdata/')
#os.system('pip install -q pytesseract')
import streamlit as st
import torch
from transformers import AutoTokenizer, AutoModelWithLMHead, GPT2LMHeadModel


# NLP Pkgs
from textblob import TextBlob 
import spacy
from gensim.summarization import summarize
import requests
import cv2
import numpy as np
import pytesseract
#pytesseract.pytesseract.tesseract_cmd = r"./Tesseract-OCR/tesseract.exe"
from PIL import Image
# Title
st.title("Streamlit NLP APP")
@st.experimental_singleton
def text_analyzer(my_text):
	nlp = spacy.load('en_core_web_sm')
	docx = nlp(my_text)
	# tokens = [ token.text for token in docx]
	allData = [('"Token":{},\n"Lemma":{}'.format(token.text,token.lemma_))for token in docx ]
	return allData
@st.experimental_singleton
def load_models():
    tokenizer = AutoTokenizer.from_pretrained('gpt2-large')
    model = GPT2LMHeadModel.from_pretrained('gpt2-large')
    return tokenizer, model
# Function For Extracting Entities
@st.experimental_singleton
def entity_analyzer(my_text):
	nlp = spacy.load('en_core_web_sm')
	docx = nlp(my_text)
	tokens = [ token.text for token in docx]
	entities = [(entity.text,entity.label_)for entity in docx.ents]
	allData = ['"Token":{},\n"Entities":{}'.format(tokens,entities)]
	return allData
def main():
	""" NLP Based App with Streamlit """
	st.markdown("""
    	#### Description
    	This is a Natural Language Processing(NLP) Based App useful for basic NLP task
         NER,Sentiment, Spell Corrections and Summarization
    	""")                         
	# Entity Extraction
	text = st.text_input("Type your text!")
	if st.checkbox("Show Named Entities"):
	   entity_result = entity_analyzer(text)
	   st.json(entity_result)
	# Sentiment Analysis
	if st.checkbox("Show Sentiment Analysis"):
	   blob = TextBlob(text)
	   result_sentiment = blob.sentiment
	   st.success(result_sentiment)
    #Text Corrections
	if st.checkbox("Spell Corrections"):
	   st.success(TextBlob(text).correct())
	if st.checkbox("Text Generation"):
		ok = st.button("Generate")
		tokenizer, model = load_models()
		if ok:
		    input_ids = tokenizer(text, return_tensors='pt').input_ids
		    st.text("Using Hugging Face Transformer, Contrastive Search ..")
		    output = model.generate(input_ids, max_length=128)
		    st.success(tokenizer.decode(output[0], skip_special_tokens=True))
	def change_photo_state():
		st.session_state["photo"]="done"
	st.subheader("Summary section, feed your image!")
	camera_photo = st.camera_input("Take a photo, Containing English or Bangla texts", on_change=change_photo_state)
	uploaded_photo = st.file_uploader("Upload Image, Containing English or Bangla texts",type=['jpg','png','jpeg'], on_change=change_photo_state)
	message = st.text_input("Or, drop your text here, only English text!")
	if "photo" not in st.session_state:
		st.session_state["photo"]="not done"

	if st.session_state["photo"]=="done" or message:
		if uploaded_photo:
			img = Image.open(uploaded_photo)
			img = img.save("img.png")
			img = cv2.imread("img.png")
			text = pytesseract.image_to_string(img, lang="ben") if st.checkbox("Mark here to see in Bangla for Bangla Images only") else pytesseract.image_to_string(img)
			st.success(text)
		if camera_photo:
			img = Image.open(camera_photo)
			img = img.save("img.png")
			img = cv2.imread("img.png")
			text = pytesseract.image_to_string(img, lang="ben") if st.checkbox("Mark here to see Bangla") else pytesseract.image_to_string(img)
			st.success(text)
		if uploaded_photo==None and camera_photo==None:
			#our_image=load_image("image.jpg")
			#img = cv2.imread("scholarly_text.jpg")
			text = message
		# Summarization
		if st.checkbox("Mark here, Text Summarization for English or Bangla!"):
			#st.subheader("Summarize Your Text for English and Bangla Texts!")
			#message = st.text_area("Enter the Text","Type please ..")
			#st.text("Using Gensim Summarizer ..")
			#st.success(mess)
			summary_result = summarize(text)
			st.success(summary_result)
		elif st.checkbox("Mark here, Better Text Summarization for English only!"):
			#st.title("Summarize Your Text for English only!")
			tokenizer = AutoTokenizer.from_pretrained('t5-base')
			model = AutoModelWithLMHead.from_pretrained('t5-base', return_dict=True)
			#st.text("Using Google T5 Transformer ..")
			inputs = tokenizer.encode("summarize: " + text,
						return_tensors='pt',
										max_length=512,
										truncation=True)
			summary_ids = model.generate(inputs, max_length=150, min_length=80, length_penalty=5., num_beams=2)
			summary = tokenizer.decode(summary_ids[0])
			st.success(summary)
	
	st.sidebar.subheader("About App")
	st.sidebar.subheader("By")
	st.sidebar.text("Soumen Sarker")

if __name__ == '__main__':
	main()