app.py

import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

uploaded_files = st.file_uploader(
    "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type = "pdf"
)

all_resumes = []  # Store the text content of each PDF

for uploaded_file in uploaded_files:
    try:
        pdf_reader = PdfReader(uploaded_file)
        text_data = ""
        for page in pdf_reader.pages:
            text_data += page.extract_text()
        resumes = pd.Series(text_data, index=['Candidate profile'])
        st.dataframe(resumes)

        for index, resume in enumerate(resumes):
            st.write(f"Candidate profile: {index}, Resume: {resume}")



        
    except Exception as e:
        st.error(f"Error processing {uploaded_file.name}: {e}")

if all_resumes:
    # Initialize the TF-IDF vectorizer
    vectorizer = TfidfVectorizer()

    # Fit and transform the text data
    tfidf_matrix = vectorizer.fit_transform(all_resumes)

    # Calculate the cosine similarity matrix
    cosine_sim = cosine_similarity(tfidf_matrix)

    st.subheader("Cosine Similarity Matrix")
    st.dataframe(cosine_sim)
elif uploaded_files:
    st.info("Please upload at least two PDF files to calculate cosine similarity.")