app.py

import gradio as gr
import pickle
import docx
import PyPDF2
import re

# Load pre-trained model and TF-IDF vectorizer
svc_model = pickle.load(open('clf.pkl', 'rb'))  # Update with your model path
tfidf = pickle.load(open('tfidf.pkl', 'rb'))  # Update with your vectorizer path
le = pickle.load(open('encoder.pkl', 'rb'))  # Update with your encoder path

# Function to clean resume text
def clean_resume(txt):
    clean_text = re.sub('http\S+\s', ' ', txt)
    clean_text = re.sub('RT|cc', ' ', clean_text)
    clean_text = re.sub('#\S+\s', ' ', clean_text)
    clean_text = re.sub('@\S+', '  ', clean_text)
    clean_text = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"""), ' ', clean_text)
    clean_text = re.sub(r'[^\x00-\x7f]', ' ', clean_text)
    clean_text = re.sub('\s+', ' ', clean_text)
    return clean_text

# Function to extract text from PDF
def extract_text_from_pdf(file):
    pdf_reader = PyPDF2.PdfReader(file)
    text = ''
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text

# Function to extract text from DOCX
def extract_text_from_docx(file):
    doc = docx.Document(file)
    text = ''
    for paragraph in doc.paragraphs:
        text += paragraph.text + '\n'
    return text

# Function to extract text from TXT
def extract_text_from_txt(file):
    try:
        text = file.read().decode('utf-8')
    except UnicodeDecodeError:
        text = file.read().decode('latin-1')
    return text

# Function to handle file upload and extraction
def handle_file_upload(uploaded_file):
    file_extension = uploaded_file.name.split('.')[-1].lower()
    if file_extension == 'pdf':
        text = extract_text_from_pdf(uploaded_file)
    elif file_extension == 'docx':
        text = extract_text_from_docx(uploaded_file)
    elif file_extension == 'txt':
        text = extract_text_from_txt(uploaded_file)
    else:
        raise ValueError("Unsupported file type. Please upload a PDF, DOCX, or TXT file.")
    return text

# Function to predict the category of a resume
def predict_category(file):
    try:
        resume_text = handle_file_upload(file)
        cleaned_text = clean_resume(resume_text)
        vectorized_text = tfidf.transform([cleaned_text])
        vectorized_text = vectorized_text.toarray()
        predicted_category = svc_model.predict(vectorized_text)
        predicted_category_name = le.inverse_transform(predicted_category)
        return f"Predicted Category: {predicted_category_name[0]}"
    except Exception as e:
        return f"Error: {str(e)}"

# Define Gradio interface
inputs = gr.File(label="Upload Resume (PDF, DOCX, TXT)")
outputs = gr.Textbox(label="Prediction")

interface = gr.Interface(fn=predict_category, inputs=inputs, outputs=outputs, title="Resume Classifier",
                         description="Upload your resume to predict its job category using an AI model.")

# Launch the interface
if __name__ == "__main__":
    interface.launch(share=True)