Spaces:

abhisheky127
/

Fold_TransactionClassification

Sleeping

App Files Files Community

Fold_TransactionClassification / app.py

abhisheky127

Update app.py

0d4640f about 3 years ago

Raw History Blame Contribute Delete

3.62 kB

import gradio as gr
import re
from transformers import pipeline
# from googlesearch import search
import requests
from bs4 import BeautifulSoup

def get_google_description(keyword):
    query = keyword
    results = search(query, num_results=1, lang='en')

    for result in results:
        description = get_description_from_url(result)
        if description:
            return description

    return keyword

def get_description_from_url(url):
    response = requests.get(url, timeout=10)
    soup = BeautifulSoup(response.text, 'html.parser')
    description_tag = soup.find('meta', {'name': 'description'})

    if description_tag:
        return description_tag.get('content')

    return None


title = "Fold: Contextual Tag Recommendation System"
description = "powered by bart-large-mnli, made by @abhisheky127"

classifier = pipeline("zero-shot-classification",
                      model="facebook/bart-large-mnli")





#define a function to process your input and output
def zero_shot(doc, candidates):
    given_labels = candidates.split(",")
    given_labels = list(map(str.strip, given_labels))
    doc = preprocess(doc)
    print(doc)
    dictionary = classifier(doc, given_labels)
    labels = dictionary['labels']
    scores = dictionary['scores']
    return dict(zip(labels, scores))

def preprocess(text):
    # Remove digits
    cleaned_text = re.sub(r'\d', '', text)
    
    # Remove special characters except spaces and letters
    cleaned_text = re.sub(r'[^a-zA-Z\s]', ' ', cleaned_text)
    
    # Remove extra spaces
    cleaned_text = re.sub(r'\s+', ' ', cleaned_text).strip()
    
    # Convert to uppercase
    cleaned_text = cleaned_text.upper()
    
    # Remove unwanted words
    words_to_remove = ["MPS", "POS", "BIL", "ONL", "BANGALORE", "PVT", "LTD", "INDIA", "LT", "XXXXXXXXXXXX"]
    cleaned_text = " ".join([word for word in cleaned_text.split() if word not in words_to_remove])
    
    # Convert to lowercase
    cleaned_text = cleaned_text.lower()

    # cleaned_text = get_google_description(cleaned_text)
    
    return cleaned_text


#create input and output objects
#input object1
input1 = gr.Textbox(label="Text")

#input object 2
input2 = gr.Textbox(label="Labels")

#output object
output = gr.Label(label="Output")

#example object
transactions_and_tags = [
    ["MPS/TRUFFLES/202303261700/034587/Bangalore", "Medical, Food, Shopping, Subscription, Travel"],
    ["MPS/TACO BELL/202304012247/108300/BANGALORE", "Medical, Food, Shopping, Subscription, Travel"],
    ["POS XXXXXXXXXXXX0001 APOLLO PHARMACY", "Medical, Food, Shopping, Subscription, Travel"],
    ["BIL/ONL/000471093694/1MG Techno/X7ZRUSVLURFQZO", "Medical, Food, Shopping, Subscription, Travel"],
    ["POS XXXXXXXXXXXX1111 DECATHLON SPORTS", "Medical, Food, Shopping, Subscription, Travel"],
    ["POS XXXXXXXXXXXX1111 WWW AMAZON IN", "Medical, Food, Shopping, Subscription, Travel"],
    ["ME DC SI XXXXXXXXXXXX1111 SPOTIFY SI", "Medical, Food, Shopping, Subscription, Travel"],
    ["POS/NETFLIX/1140920002/100623/17:25", "Medical, Food, Shopping, Subscription, Travel"],
    ["POS XXXXXXXXXXXX1110 MAKEMYTRIP INDIA", "Medical, Food, Shopping, Subscription, Travel"],
    ["BIL/ONL/000691178015/IRCTC Serv/XZZBX91LTCY1AZ", "Medical, Food, Shopping, Subscription, Travel"]
]

#create interface
gui = gr.Interface(title=title,
                   description=description,
                   fn=zero_shot,
                   inputs=[input1, input2],
                   outputs=[output],
                   examples=transactions_and_tags
                  )

#display the interface
gui.launch(debug=True)

	import gradio as gr
	import re
	from transformers import pipeline
	# from googlesearch import search
	import requests
	from bs4 import BeautifulSoup

	def get_google_description(keyword):
	query = keyword
	results = search(query, num_results=1, lang='en')

	for result in results:
	description = get_description_from_url(result)
	if description:
	return description

	return keyword

	def get_description_from_url(url):
	response = requests.get(url, timeout=10)
	soup = BeautifulSoup(response.text, 'html.parser')
	description_tag = soup.find('meta', {'name': 'description'})

	if description_tag:
	return description_tag.get('content')

	return None


	title = "Fold: Contextual Tag Recommendation System"
	description = "powered by bart-large-mnli, made by @abhisheky127"

	classifier = pipeline("zero-shot-classification",
	model="facebook/bart-large-mnli")





	#define a function to process your input and output
	def zero_shot(doc, candidates):
	given_labels = candidates.split(",")
	given_labels = list(map(str.strip, given_labels))
	doc = preprocess(doc)
	print(doc)
	dictionary = classifier(doc, given_labels)
	labels = dictionary['labels']
	scores = dictionary['scores']
	return dict(zip(labels, scores))

	def preprocess(text):
	# Remove digits
	cleaned_text = re.sub(r'\d', '', text)

	# Remove special characters except spaces and letters
	cleaned_text = re.sub(r'[^a-zA-Z\s]', ' ', cleaned_text)

	# Remove extra spaces
	cleaned_text = re.sub(r'\s+', ' ', cleaned_text).strip()

	# Convert to uppercase
	cleaned_text = cleaned_text.upper()

	# Remove unwanted words
	words_to_remove = ["MPS", "POS", "BIL", "ONL", "BANGALORE", "PVT", "LTD", "INDIA", "LT", "XXXXXXXXXXXX"]
	cleaned_text = " ".join([word for word in cleaned_text.split() if word not in words_to_remove])

	# Convert to lowercase
	cleaned_text = cleaned_text.lower()

	# cleaned_text = get_google_description(cleaned_text)

	return cleaned_text


	#create input and output objects
	#input object1
	input1 = gr.Textbox(label="Text")

	#input object 2
	input2 = gr.Textbox(label="Labels")

	#output object
	output = gr.Label(label="Output")

	#example object
	transactions_and_tags = [
	["MPS/TRUFFLES/202303261700/034587/Bangalore", "Medical, Food, Shopping, Subscription, Travel"],
	["MPS/TACO BELL/202304012247/108300/BANGALORE", "Medical, Food, Shopping, Subscription, Travel"],
	["POS XXXXXXXXXXXX0001 APOLLO PHARMACY", "Medical, Food, Shopping, Subscription, Travel"],
	["BIL/ONL/000471093694/1MG Techno/X7ZRUSVLURFQZO", "Medical, Food, Shopping, Subscription, Travel"],
	["POS XXXXXXXXXXXX1111 DECATHLON SPORTS", "Medical, Food, Shopping, Subscription, Travel"],
	["POS XXXXXXXXXXXX1111 WWW AMAZON IN", "Medical, Food, Shopping, Subscription, Travel"],
	["ME DC SI XXXXXXXXXXXX1111 SPOTIFY SI", "Medical, Food, Shopping, Subscription, Travel"],
	["POS/NETFLIX/1140920002/100623/17:25", "Medical, Food, Shopping, Subscription, Travel"],
	["POS XXXXXXXXXXXX1110 MAKEMYTRIP INDIA", "Medical, Food, Shopping, Subscription, Travel"],
	["BIL/ONL/000691178015/IRCTC Serv/XZZBX91LTCY1AZ", "Medical, Food, Shopping, Subscription, Travel"]
	]

	#create interface
	gui = gr.Interface(title=title,
	description=description,
	fn=zero_shot,
	inputs=[input1, input2],
	outputs=[output],
	examples=transactions_and_tags
	)

	#display the interface
	gui.launch(debug=True)