Spaces:
Running
Running
File size: 3,104 Bytes
67d85c4 3635259 312d081 67d85c4 3635259 67d85c4 3635259 312d081 3635259 67d85c4 3635259 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import pandas as pd
import numpy as np
import re
import pickle
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
def load_deeprank_model():
return load_model('deeprank_model.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():
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)
vocab_size = len(tokenizer.word_index) + 1
num_classes = len(label.classes_)
max_sequence_length = 500
resumes_data = []
files = input("Enter the paths of resumes (comma-separated): ").split(',')
for file in files:
text = cleanResume(pdf_to_text(file.strip()))
resumes_data.append({'ResumeText': text, 'FileName': file.strip()})
print("Available categories:", list(label.classes_))
selected_category = input("Select a category to rank by: ")
if not resumes_data or selected_category not in label.classes_:
print("Error: Invalid input. Please provide valid resumes and select a valid category.")
else:
ranks = predict_category(resumes_data, selected_category, max_sequence_length, model, tokenizer, label)
print(pd.DataFrame(ranks))
if __name__ == '__main__':
main()
|