import streamlit as st
import pickle
import re
import nltk
from pypdf import PdfReader

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

model = pickle.load(open('model.pkl','rb'))
tfidfd = pickle.load(open('tfidf.pkl','rb'))

def clean_resume(resume_text):
    clean_text = re.sub('http\S+\s*', ' ', resume_text)
    clean_text = re.sub('RT|cc', ' ', clean_text)
    clean_text = re.sub('#\S+', '', clean_text)
    clean_text = re.sub('@\S+', '  ', clean_text)
    clean_text = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', clean_text)
    return clean_text
def main():
    st.title("Resume Screening App")
    uploaded_file = st.file_uploader('Upload Your Resume Here', type=['txt','pdf'])

    if uploaded_file is not None:
        try:
            reader = PdfReader(uploaded_file)
            page = reader.pages[0]
            text = page.extract_text()
        except :
            st.write("sorry file cannot be read")

        cleaned_resume = clean_resume(text)
        input_features = tfidfd.transform([cleaned_resume])
        prediction_id = model.predict(input_features)[0]

        # Map category ID to category name
        category_mapping = {
            15: "Java Developer",
            23: "Testing",
            8: "DevOps Engineer",
            20: "Python Developer",
            24: "Web Designing",
            12: "HR",
            13: "Hadoop",
            3: "Blockchain",
            10: "ETL Developer",
            18: "Operations Manager",
            6: "Data Science",
            22: "Sales",
            16: "Mechanical Engineer",
            1: "Arts",
            7: "Database",
            11: "Electrical Engineering",
            14: "Health and fitness",
            19: "PMO",
            4: "Business Analyst",
            9: "DotNet Developer",
            2: "Automation Testing",
            17: "Network Security Engineer",
            21: "SAP Developer",
            5: "Civil Engineer",
            0: "Advocate",
        }

        category_name = category_mapping.get(prediction_id)
        st.write("The Predicted Category for your Resume is :", category_name)



# python main
if __name__ == "__main__":
    main()