app.py

import streamlit as st
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.multiclass import OneVsRestClassifier
from sklearn.neighbors import KNeighborsClassifier
import re
import pickle
import pdfminer
from pdfminer.high_level import extract_text

def cleanResume(resumeText):
    # Your existing cleanResume function remains unchanged
    resumeText = re.sub('http\S+\s*', ' ', resumeText)
    resumeText = re.sub('RT|cc', ' ', resumeText)
    resumeText = re.sub('#\S+', '', resumeText)
    resumeText = re.sub('@\S+', '  ', resumeText)
    resumeText = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', resumeText)
    resumeText = re.sub(r'[^\x00-\x7f]',r' ', resumeText)
    resumeText = re.sub('\s+', ' ', resumeText)
    return resumeText

df = pd.read_csv('UpdatedResumeDataSet.csv')
df['cleaned'] = df['Resume'].apply(lambda x: cleanResume(x))
label = LabelEncoder()
df['Category'] = label.fit_transform(df['Category'])
text = df['cleaned'].values
target = df['Category'].values
word_vectorizer = TfidfVectorizer(
    sublinear_tf=True,
    stop_words='english',
    max_features=1500)
word_vectorizer.fit(text)
WordFeatures = word_vectorizer.transform(text)
model = OneVsRestClassifier(KNeighborsClassifier())
model.fit(WordFeatures, target)

def pdf_to_text(file):
    # Use pdfminer.six to extract text from the PDF file
    text = extract_text(file)
    return text

def predict_category(resumes_data, selected_category):
    resumes_df = pd.DataFrame(resumes_data)
    resumes_features = word_vectorizer.transform(resumes_df['ResumeText'])
    predicted_probs = model.predict_proba(resumes_features)

    # Assign probabilities to respective job categories
    for i, category in enumerate(label.classes_):
        resumes_df[category] = predicted_probs[:, i]

    resumes_df_sorted = resumes_df.sort_values(by=selected_category, ascending=False)

    # Get the ranks for the selected category
    ranks = []
    for rank, (idx, row) in enumerate(resumes_df_sorted.iterrows()):
        rank = rank + 1
        file_name = row['FileName']
        ranks.append({'Rank': rank, 'FileName': file_name})

    return ranks

def main():
    st.title("Resume Ranking App")
    st.text("Upload resumes and select a category to rank them.")



    resumes_data = []
    selected_category = ""

    # Handle multiple file uploads
    files = st.file_uploader("Upload resumes", type=["pdf"], accept_multiple_files=True)
    if files:
        for file in files:
            text = cleanResume(pdf_to_text(file))
            resumes_data.append({'ResumeText': text, 'FileName': file.name})
        selected_category = st.selectbox("Select a category to rank by", label.classes_)

    if st.button("Rank Resumes"):
        if not resumes_data or not selected_category:
            st.warning("Please upload resumes and select a category to continue.")
        else:
            ranks = predict_category(resumes_data, selected_category)
            st.write(pd.DataFrame(ranks))

if __name__ == '__main__':
    main()