app.py

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

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
from gliner import GLiNER


import streamlit as st
import pandas as pd
from PyPDF2 import PdfReader
from gliner import GLiNER

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

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

def process_documents(job_description_key, file_uploader_key, title):
    txt = st.text_area(f"Job description for {title}", key=job_description_key)
    job_description_series = pd.Series([txt], name="Text")
    st.dataframe(job_description_series)

    uploaded_files = st.file_uploader(
        f"Choose PDF file(s) for candidate profiles for {title}", type="pdf", key=file_uploader_key, 
    )

    all_extracted_data = []
    if uploaded_files:
        model = GLiNER.from_pretrained("urchade/gliner_base")
        labels = ["person", "country", "organization", "time", "role"]
        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()

                entities = model.predict_entities(text_data, labels)
                entity_dict = {}
                for label in labels:
                    entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
                data = {"Text": text_data, **entity_dict}
                all_extracted_data.append(data)
            except Exception as e:
                st.error(f"Error processing file {uploaded_file.name}: {e}")

        if all_extracted_data:
            df_entities = pd.DataFrame(all_extracted_data)
            st.subheader(f"Extracted Entities ({title}):")
            st.dataframe(df_entities)

            all_documents = [job_description_series.iloc[0]] + df_entities['Text'].tolist()
            vectorizer = TfidfVectorizer()
            tfidf_matrix = vectorizer.fit_transform(all_documents)
            tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
            st.subheader(f"TF-IDF Values ({title}):")
            st.dataframe(tfidf_df)

            cosine_sim_matrix = cosine_similarity(tfidf_matrix)
            cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
            st.subheader(f"Cosine Similarity Matrix ({title}):")
            st.dataframe(cosine_sim_df)

            st.subheader(f"Cosine Similarity Scores (Job Description for {title} vs. Resumes):")
            for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
                st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")

st.header("Analysis Set 1")
process_documents("text 1", "candidate 1", "Set 1")

st.divider()

st.header("Analysis Set 2")
process_documents("text 2", "candidate 2", "Set 2")