Update app.py

app.py

@@ -1,61 +1,79 @@
-import streamlit as st
 import pandas as pd
 import numpy as np
 import re
 import pickle
-import nltk
-from nltk.corpus import stopwords
+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
-
-nltk.download('stopwords')
-stop_words = set(stopwords.words('english'))
+from sklearn.preprocessing import LabelEncoder
 
 def cleanResume(resumeText):
-    resumeText = re.sub(r'http\S+\s*', ' ', resumeText)
-    resumeText = re.sub(r'RT|cc', ' ', resumeText)
-    resumeText = re.sub(r'#\S+', '', resumeText)
-    resumeText = re.sub(r'@\S+', ' ', resumeText)
-    resumeText = re.sub(r'[%s]' % re.escape("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"), ' ', resumeText)
+    resumeText = re.sub('http\S+\s*', ' ', resumeText)
+    resumeText = re.sub('RT|cc', ' ', resumeText)
+    resumeText = re.sub('#\S+', '', resumeText)
+    resumeText = re.sub('@\S+', '  ', resumeText)
+    resumeText = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', resumeText)
     resumeText = re.sub(r'[^\x00-\x7f]', r' ', resumeText)
-    resumeText = re.sub(r'\s+', ' ', resumeText)
-    resumeText = ' '.join([word for word in resumeText.split() if word.lower() not in stop_words])
+    resumeText = re.sub('\s+', ' ', resumeText)
     return resumeText
 
-def load_resources():
-    with open('tokenizer.pkl', 'rb') as f:
-        tokenizer = pickle.load(f)
-    with open('label_encoder.pkl', 'rb') as f:
-        label_encoder = pickle.load(f)
-    model = load_model('deeprank_model_v2.h5')
-    return tokenizer, label_encoder, model
-
-def infer(text, tokenizer, label_encoder, model):
-    cleaned_text = cleanResume(text)
-    sequence = tokenizer.texts_to_sequences([cleaned_text])
-    padded_sequence = pad_sequences(sequence, maxlen=500)
-    prediction = model.predict(padded_sequence)
-    predicted_class = label_encoder.inverse_transform([np.argmax(prediction)])
-    return predicted_class[0]
-
-st.title("Resume Category Predictor")
-
-st.write("Upload a resume text file or enter text below to predict the job category.")
-
-uploaded_file = st.file_uploader("Upload Resume (TXT file)", type=["txt"])
-user_input = st.text_area("Or paste resume text here:")
-
-if uploaded_file is not None:
-    resume_text = uploaded_file.read().decode("utf-8")
-    st.session_state["resume_text"] = resume_text
-elif user_input:
-    resume_text = user_input
-    st.session_state["resume_text"] = resume_text
-else:
-    resume_text = ""
-
-if st.button("Predict Category") and resume_text:
-    tokenizer, label_encoder, model = load_resources()
-    prediction = infer(resume_text, tokenizer, label_encoder, model)
-    st.write(f"Predicted Category: **{prediction}**")
+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()