Update app.py

app.py

@@ -4,14 +4,29 @@ import gradio as gr
 from transformers import pipeline
 from collections import Counter
 
-# Load NER pipeline for entity extraction
+# Load NER pipeline
 ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", tokenizer="dslim/bert-base-NER", aggregation_strategy="simple")
 
 # Load Job Category Classifier
 text_classifier = pipeline("text-classification", model="serbog/distilbert-jobCategory_410k")
 
+# Mapping from category code to readable label
+CATEGORY_MAP = {
+    "C1": "Engineering",
+    "C2": "Information Technology",
+    "C3": "Sales & Marketing",
+    "C4": "Accounting & Finance",
+    "C5": "Healthcare",
+    "D1": "Education",
+    "D2": "Human Resources",
+    "E1": "Operations & Logistics",
+    "E2": "Legal",
+    "F1": "Customer Support",
+    "Other": "General / Undefined"
+}
+
 def clean_resume_text(text):
-    """Clean text by removing URLs, punctuation, non-ASCII chars."""
+    """Clean text by removing unwanted characters and formatting."""
     text = re.sub(r'http\S+', ' ', text)
     text = re.sub(r'#\S+', '', text)
     text = re.sub(r'@\S+', ' ', text)
@@ -35,7 +50,7 @@ def extract_resume_text(file):
         return None, f"Error reading PDF: {str(e)}"
 
 def classify_resume_ner(entities):
-    """Classify by extracting key orgs and locations from NER output."""
+    """Basic rule-based NER classification using ORG, LOC, MISC."""
     orgs = [e['word'] for e in entities if e['entity_group'] == 'ORG']
     locs = [e['word'] for e in entities if e['entity_group'] == 'LOC']
     jobs = [e['word'] for e in entities if e['entity_group'] == 'MISC']
@@ -51,12 +66,11 @@ def classify_resume_ner(entities):
     }
 
 def process_resumes(files):
-    """Process multiple resumes with NER and classification."""
+    """Extract entities and show classification based on NER."""
     all_results = {}
     for file in files:
         file_name = file.name.split("/")[-1]
         resume_text, error = extract_resume_text(file)
-
         if error:
             all_results[file_name] = {"error": error}
             continue
@@ -76,7 +90,7 @@ def process_resumes(files):
     return all_results
 
 def classify_resumes_with_model(files):
-    """Use job category model to predict the field/role."""
+    """Use job category model to classify resume into readable job field."""
     predictions = {}
     for file in files:
         file_name = file.name.split("/")[-1]
@@ -85,26 +99,30 @@ def classify_resumes_with_model(files):
             predictions[file_name] = {"error": error}
             continue
         cleaned_text = clean_resume_text(resume_text)
-        result = text_classifier(cleaned_text[:512])  # Truncate if too long
+        result = text_classifier(cleaned_text[:512])  # Truncate for safety
+        raw_label = result[0]['label']
+        readable_label = CATEGORY_MAP.get(raw_label, "Unknown")
+
         predictions[file_name] = {
-            "Predicted Job Category": result[0]['label'].replace("_", " ").title(),
+            "Predicted Job Category": readable_label,
+            "Raw Label": raw_label,
             "Confidence Score": round(result[0]['score'], 4)
         }
     return predictions
 
 # Gradio Interface
 with gr.Blocks(title="Resume Analyzer") as demo:
-    gr.Markdown("## 📂 Multi-Resume Entity Extractor & Job Category Classifier\nUpload multiple PDF resumes. This tool uses NER to extract info and a job classification model to predict job field/category.")
+    gr.Markdown("## 📂 Multi-Resume Entity Extractor & Job Classifier\nUpload multiple PDF resumes. This tool extracts entities using NER and predicts the job field using a trained classifier model.")
 
     with gr.Row():
-        file_input = gr.File(file_types=[".pdf"], label="Upload Resumes (PDF)", file_count="multiple")
+        file_input = gr.File(file_types=[".pdf"], label="Upload Resume PDFs", file_count="multiple")
 
     with gr.Row():
-        extract_button = gr.Button("🔍 Extract Entities")
-        classify_button = gr.Button("🧠 Predict Job Category")
+        extract_button = gr.Button("🔍 Extract Entities (NER)")
+        classify_button = gr.Button("🧠 Predict Job Category (Model)")
 
-    output_entities = gr.JSON(label="Entity Results & NER Classification")
-    output_class = gr.JSON(label="Predicted Job Category (Model)")
+    output_entities = gr.JSON(label="NER Results & Classification")
+    output_class = gr.JSON(label="Model-Predicted Job Category")
 
     extract_button.click(fn=process_resumes, inputs=[file_input], outputs=[output_entities])
     classify_button.click(fn=classify_resumes_with_model, inputs=[file_input], outputs=[output_class])