app.py

import gradio as gr
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import numpy as np
from scipy.special import softmax
import csv
import urllib.request

# Preprocess text (username and link placeholders)
def preprocess(text):
    new_text = []
    for t in text.split(" "):
        t = '@user' if t.startswith('@') and len(t) > 1 else t
        t = 'http' if t.startswith('http') else t
        new_text.append(t)
    return " ".join(new_text)

def classify_text(text):
    # Tasks: emoji, emotion, hate, irony, offensive, sentiment
    # stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
    task = 'emoji'
    MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
    tokenizer = AutoTokenizer.from_pretrained(MODEL)

    # Download label mapping
    labels = []
    mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt"
    with urllib.request.urlopen(mapping_link) as f:
        html = f.read().decode('utf-8').split("\n")
        csvreader = csv.reader(html, delimiter='\t')
        labels = [row[1] for row in csvreader if len(row) > 1]

    # Load model
    model = AutoModelForSequenceClassification.from_pretrained(MODEL)

    text = preprocess(text)
    encoded_input = tokenizer(text, return_tensors='pt')
    output = model(**encoded_input)
    scores = output.logits[0].detach().numpy()
    scores = softmax(scores)

    ranking = np.argsort(scores)
    ranking = ranking[::-1]
    results = []
    for i in range(scores.shape[0]):
        label = labels[ranking[i]]
        score = scores[ranking[i]]
        result = f"{i+1}) {label} {np.round(float(score), 4)}"
        results.append(result)
    
    return results

iface = gr.Interface(
    fn=classify_text,
    inputs="text",
    outputs="text",
    title="Text Classification",
    description="Classify the text into different categories.",
    example="Looking forward to Christmas"
)

iface.launch()