actual Labels

app.py

@@ -3,8 +3,6 @@ import fitz
 import os
 import re
 from joblib import load
-from sklearn.feature_extraction.text import TfidfVectorizer
-
 
 def extract_text_from_pdf(file_path):
     text = ""
@@ -27,14 +25,24 @@ def load_model():
     model = load('Resume_Screening.joblib') 
     return model
 
-vectorizer=load('Word_Vec_Resume.joblib')
+vectorizer = load('Word_Vec_Resume.joblib')
+actual_labels = [
+    "Advocate", "Arts", "Automation Testing", "Blockchain", "Business Analyst", 
+    "Civil Engineer", "Data Science", "Database", "DevOps Engineer", "DotNet Developer", 
+    "ETL Developer", "Electrical Engineering", "HR", "Hadoop", "Health and fitness", 
+    "Java Developer", "Mechanical Engineer", "Network Security Engineer", "Operations Manager", 
+    "PMO", "Python Developer", "SAP Developer", "Sales", "Testing", "Web Designing"
+]
+
 def predict(file_path):
     text = extract_text_from_pdf(file_path)
     text = preprocess_text(text)
     text_vectorized = vectorizer.transform([text])
     model = load_model()
     result = model.predict(text_vectorized)
-    return result[0]
+    actual_result = [actual_labels[label] for label in result]
+    result=actual_result[0]
+    return result
 
 iface = gr.Interface(
     fn=predict,
@@ -42,4 +50,4 @@ iface = gr.Interface(
     outputs="text"  
 )
 
-iface.launch()
+iface.launch()

reuirements.txt

@@ -4,4 +4,5 @@ PyMuPDF
 fitz
 os
 re
-sci-kit-learn
+sci-kit-learn
+python=`