show_category

import pickle
import nltk
import pandas as pd
from pyresparser import ResumeParser
from nltk.tokenize import word_tokenize
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import os
import warnings
import json

def parse_csv(filename):
    try:
        data = ResumeParser(filename).get_extracted_data()

    except:
        pass
    return [data["skills"], data["degree"]]


def compute_cosine_similarity(file1, resumeSkills):
    text1 = pd.read_csv(file1)
    text1 = text1['Skills'].tolist()
    text1 = ' '.join(text1).lower()

    resumeSkills = ' '.join(resumeSkills).lower()

    vectorizer = TfidfVectorizer()
    tfidf_matrix = vectorizer.fit_transform([text1, resumeSkills])
    cosine_sim = cosine_similarity(tfidf_matrix[0], tfidf_matrix[1])[0][0]
    return cosine_sim


def calculate_degree_score(degree):
    if degree is None:
        return 0
    
    score = 0
    if "bachelor" in degree.lower() or "bsc" in degree.lower():
        score += 10
    if "master" in degree.lower() or "graduate" in degree.lower() or "msc" in degree.lower():
        score += 5

    return score


def ranking(file, user_input):

    # file = '/home/kamleshk/Mypartition/Spring_2023/Jazz_internshop_cvs/c.pdf'
    parsedCV = parse_csv(file)

    skills = parsedCV[0]
    degree = None

    if len(parsedCV) > 1 and parsedCV[1] is not None:
        degree = parsedCV[1][0]

    file_name = user_input + '.csv'
    skills_similarity = compute_cosine_similarity(file_name, skills)
    degree_score = calculate_degree_score(degree)

    final_score = skills_similarity*100 + degree_score
    return final_score


if __name__ == '__main__':


    # Filter or ignore specific warning categories
    warnings.filterwarnings("ignore", category=DeprecationWarning)
    warnings.filterwarnings("ignore", category=UserWarning)
    # Add more filters if needed



    with open('categories_dict.pkl', 'rb') as file:
        categories_dict = pickle.load(file)
        print(f'Possible Categories of the Resumes: {categories_dict.keys()}')

    user_input = input('Enter a category: ')

    pdf_list = categories_dict[user_input]

    directory_path = "INFORMATION-TECHNOLOGY"

    scored_files = []

    for file_name in pdf_list:
        file_path = os.path.join(directory_path, file_name)
        
        if os.path.isfile(file_path):
            score = ranking(file_path, user_input)
            
            if score is not None:
                scored_files.append((file_name, score))
            else:
                print(f"Warning: No score returned for {file_path}")
                continue

        else:
            print(f"{file_name} does not exist")

    scored_files.sort(key=lambda x: x[1], reverse=True)

    for i, (file_name, score) in enumerate(scored_files, 1):
        print(f"Rank {i}: {file_name} with score {score}")