app.py

import streamlit as st
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
from keyphrasetransformer import KeyPhraseTransformer
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import pandas as pd

kp = KeyPhraseTransformer()

@st.cache_resource
def load_model():
    model = SentenceTransformer('all-MiniLM-L6-v2')
    return model

def calculate_similarity(model, text1, text2):
    embedding1 = model.encode([text1])
    embedding2 = model.encode([text2])
    return cosine_similarity(embedding1, embedding2)[0][0]

def generate_wordcloud(text, title):
    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
    plt.figure(figsize=(10, 5))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.title(title)
    st.pyplot(plt)

st.title("Resume Analysis Assistant")

model = load_model()
# Set the font size for the "Paste the Job Description" text
st.markdown("<style>#fc1{font-size: 20px !important;}</style>", unsafe_allow_html=True)

jd = st.text_area("Paste the Job Description:", height=150)
resume = st.text_area("Paste Your the Resume:", height=150)

if st.button("GET MATCH SCORE & WORD CLOUD"):
    if jd and resume:
        jp = kp.get_key_phrases(jd)
        rp = kp.get_key_phrases(resume)

        # Generate word clouds for JD and Resume
        generate_wordcloud(' '.join(jp), 'Word Cloud for Job Description Keywords')
        generate_wordcloud(' '.join(rp), 'Word Cloud for Resume Keywords')

        score = calculate_similarity(model, jd, resume)
        # st.write(f"The match score is: {score}", )
        # Display the match score as a percentage
        score_percentage = f"{score * 100:.0f}%"

        st.write("The match score is:")
        st.write(score_percentage, key='match_score')

    else:
        st.write("Please enter both the job description and resume.", )

if st.button("GET KEYWORDS"):
    if jd and resume:
        jp = kp.get_key_phrases(jd)
        rp = kp.get_key_phrases(resume)

        # Find missing and matching keywords
        missing_keywords = set(jp) - set(rp)
        matching_keywords = set(jp) & set(rp)

        # Make sure all arrays have the same length
        max_length = max(len(jp), len(rp), len(matching_keywords), len(missing_keywords))

        jp += [''] * (max_length - len(jp))
        rp += [''] * (max_length - len(rp))
        matching_keywords = list(matching_keywords) + [''] * (max_length - len(matching_keywords))
        missing_keywords = list(missing_keywords) + [''] * (max_length - len(missing_keywords))

        # Display keywords in a table
        keywords_table_data = {
            'Keywords From Job Description': jp,
            'Keywords From Resume': rp,
            'Matching Keywords': matching_keywords,
            'Missing Keywords': missing_keywords
        }

        st.write("Keywords Overview:")
        st.table(pd.DataFrame(keywords_table_data))

    else:
        st.write("Please enter both the job description and resume.", )