ATS_score.py

from sklearn.feature_extraction.text import TfidfVectorizer 
from sklearn.metrics.pairwise import cosine_similarity 
from sklearn.feature_extraction import _stop_words 
from convert import ExtractPDFText

def calculateATSscore(resume_data, job_description):
    stopwords = list(_stop_words.ENGLISH_STOP_WORDS)
    
    # Initialize TfidfVectorizer with stopwords
    vectorizer = TfidfVectorizer(stop_words=stopwords)
    
    # Fit and transform the job description and resume data
    vectors = vectorizer.fit_transform([job_description, resume_data])
    
    # Calculate cosine similarity
    similarity_matrix = cosine_similarity(vectors)
    
    # Extract the similarity value between job description (0th index) and resume (1st index)
    similarity_value = similarity_matrix[0][1]
    
    # Optionally print the similarity matrix (for debugging purposes)
    print("Cosine Similarity Matrix:", similarity_matrix)
    print("Calculated ATS Score:", similarity_value)
    
    return similarity_value