app.py

import gradio as gr
import re
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from sklearn.feature_extraction.text import TfidfVectorizer

import joblib

import nltk

nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')


tfidf_vectorizer = joblib.load('tfidf_vectorizer.pkl')
classifier = joblib.load('classifier.pkl')

# Preprocess function
def preprocess_text(text):
    # Text Cleaning
    text = re.sub(r'[^\w\s]', '', text)

    # Tokenization
    tokens = word_tokenize(text)

    # Stop Word Removal
    stop_words = set(stopwords.words('english'))
    tokens = [token for token in tokens if token.lower() not in stop_words]

    # Lemmatization
    lemmatizer = WordNetLemmatizer()
    tokens = [lemmatizer.lemmatize(token) for token in tokens]

    # Join tokens back to text
    preprocessed_text = ' '.join(tokens)

    return preprocessed_text

# Gradio Function
def classify_threat(text):
    # Preprocess input text
    preprocessed_text = preprocess_text(text)
    
    # Convert to TF-IDF vector
    tfidf_text = tfidf_vectorizer.transform([preprocessed_text])
    # Predict threat
    threat = classifier.predict(tfidf_text)
    return threat[0]

# Create a Gradio interface
iface = gr.Interface(
    fn=classify_threat,
    inputs="text",
    outputs="text",
    title="Threat Classification",
    description="Enter a text description to classify the threat (e.g., oil, chemical).",
)

# Launch the interface
iface.launch()