Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import re | |
| import h5py | |
| import pdfminer | |
| from pdfminer.high_level import extract_text | |
| import pytesseract | |
| from pdf2image import convert_from_path | |
| from tensorflow.keras.models import load_model | |
| from tensorflow.keras.preprocessing.text import Tokenizer | |
| from tensorflow.keras.preprocessing.sequence import pad_sequences | |
| from sklearn.preprocessing import LabelEncoder | |
| def cleanResume(resumeText): | |
| 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 | |
| def pdf_to_text(file): | |
| text = extract_text(file) | |
| if not text.strip(): # If PDF text extraction fails, use OCR | |
| images = convert_from_path(file) | |
| text = "\n".join([pytesseract.image_to_string(img) for img in images]) | |
| return text | |
| import h5py | |
| def fix_h5_model(): | |
| with h5py.File("deeprank_model_v2.h5", "r+") as f: | |
| if "model_config" in f.attrs: | |
| model_config = f.attrs["model_config"] | |
| # Ensure model_config is a string before replacing | |
| if isinstance(model_config, bytes): | |
| model_config = model_config.decode("utf-8") | |
| updated_config = model_config.replace('"time_major": false', "") | |
| # Store the updated config back as bytes | |
| f.attrs.modify("model_config", updated_config.encode("utf-8")) | |
| def load_deeprank_model(): | |
| fix_h5_model() | |
| return load_model('deeprank_model_v2.h5') | |
| def predict_category(resumes_data, selected_category, max_sequence_length, model, tokenizer, label): | |
| resumes_df = pd.DataFrame(resumes_data) | |
| resumes_text = resumes_df['ResumeText'].values | |
| tokenized_text = tokenizer.texts_to_sequences(resumes_text) | |
| padded_text = pad_sequences(tokenized_text, maxlen=max_sequence_length) | |
| predicted_probs = model.predict(padded_text) | |
| 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) | |
| ranks = [{'Rank': rank + 1, 'FileName': row['FileName']} for rank, (idx, row) in enumerate(resumes_df_sorted.iterrows())] | |
| return ranks | |
| def main(): | |
| st.title("Resume Ranking App") | |
| st.write("Upload resumes and select a category to rank them based on their relevance.") | |
| model = load_deeprank_model() | |
| df = pd.read_csv('UpdatedResumeDataSet.csv') | |
| df['cleaned'] = df['Resume'].apply(cleanResume) | |
| label = LabelEncoder() | |
| df['Category'] = label.fit_transform(df['Category']) | |
| text = df['cleaned'].values | |
| tokenizer = Tokenizer() | |
| tokenizer.fit_on_texts(text) | |
| max_sequence_length = 500 | |
| uploaded_files = st.file_uploader("Upload Resumes (PDFs)", type=["pdf"], accept_multiple_files=True) | |
| if uploaded_files: | |
| resumes_data = [] | |
| for file in uploaded_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", list(label.classes_)) | |
| if st.button("Rank Resumes"): | |
| if resumes_data and selected_category: | |
| ranks = predict_category(resumes_data, selected_category, max_sequence_length, model, tokenizer, label) | |
| st.write(pd.DataFrame(ranks)) | |
| else: | |
| st.error("Please upload valid resumes and select a valid category.") | |
| if __name__ == '__main__': | |
| main() | |