Update app.py

app.py

@@ -2,18 +2,19 @@ import re
 import PyPDF2
 import gradio as gr
 from transformers import pipeline
+from collections import Counter
 
-# Load the Hugging Face NER model pipeline
+# Load the Hugging Face NER pipeline
 ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", tokenizer="dslim/bert-base-NER", aggregation_strategy="simple")
 
 def clean_resume_text(text):
     """Clean resume text by removing unwanted characters and formatting."""
-    text = re.sub(r'http\S+', ' ', text)  # Remove URLs
-    text = re.sub(r'#\S+', '', text)      # Remove hashtags
-    text = re.sub(r'@\S+', ' ', text)     # Remove mentions
-    text = re.sub(r'[^\w\s]', ' ', text)  # Remove punctuation
-    text = re.sub(r'[^\x00-\x7f]', ' ', text)  # Remove non-ASCII characters
-    return re.sub(r'\s+', ' ', text).strip()  # Normalize whitespace
+    text = re.sub(r'http\S+', ' ', text)
+    text = re.sub(r'#\S+', '', text)
+    text = re.sub(r'@\S+', ' ', text)
+    text = re.sub(r'[^\w\s]', ' ', text)
+    text = re.sub(r'[^\x00-\x7f]', ' ', text)
+    return re.sub(r'\s+', ' ', text).strip()
 
 def extract_resume_text(file):
     """Extract raw text from uploaded PDF file."""
@@ -25,54 +26,63 @@ def extract_resume_text(file):
             if page_text:
                 text += page_text + " "
         if not text.strip():
-            return "Error: No text extracted from PDF."
-        return text
+            return None, "Error: No text extracted from PDF."
+        return text, None
     except Exception as e:
-        return f"Error reading PDF: {str(e)}"
+        return None, f"Error reading PDF: {str(e)}"
+
+def classify_resume(entities):
+    """Classify resume based on dominant entity types."""
+    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']
+
+    dominant_org = Counter(orgs).most_common(1)
+    dominant_loc = Counter(locs).most_common(1)
+    dominant_job = Counter(jobs).most_common(1)
+
+    return {
+        "Main_Organization": dominant_org[0][0] if dominant_org else "Unknown",
+        "Main_Location": dominant_loc[0][0] if dominant_loc else "Unknown",
+        "Possible_Job/Field": dominant_job[0][0] if dominant_job else "General"
+    }
+
+def extract_entities_from_pdfs(files):
+    """Process multiple resumes, extract entities, and classify."""
+    summary = {}
+
+    for file in files:
+        file_name = file.name.split("/")[-1]
+        resume_text, error = extract_resume_text(file)
+
+        if error:
+            summary[file_name] = {"error": error}
+            continue
+
+        cleaned_text = clean_resume_text(resume_text)
+        entities = ner_pipeline(cleaned_text)
 
-def extract_entities_from_pdf(file):
-    """Main processing function: Extracts and cleans text, runs NER, and returns structured data."""
-    try:
-        resume_text = extract_resume_text(file)
-        if resume_text.startswith("Error"):
-            return {"error": resume_text}
-        
-        entities = ner_pipeline(resume_text)
-        
         result = {
-            "Persons": [],
-            "Organizations": [],
-            "Locations": [],
-            "Other": []
+            "Persons": list({e["word"] for e in entities if e["entity_group"] == "PER"}),
+            "Organizations": list({e["word"] for e in entities if e["entity_group"] == "ORG"}),
+            "Locations": list({e["word"] for e in entities if e["entity_group"] == "LOC"}),
+            "Other": list({e["word"] for e in entities if e["entity_group"] not in ["PER", "ORG", "LOC"]}),
+            "Cleaned_Text": cleaned_text,
+            "Classification": classify_resume(entities)
         }
 
-        for entity in entities:
-            label = entity.get("entity_group")
-            word = entity.get("word")
-            if label == "PER":
-                result["Persons"].append(word)
-            elif label == "ORG":
-                result["Organizations"].append(word)
-            elif label == "LOC":
-                result["Locations"].append(word)
-            else:
-                result["Other"].append(word)
+        summary[file_name] = result
 
-        result["Cleaned_Text"] = clean_resume_text(resume_text)
-        return result
-
-    except Exception as e:
-        return {"error": f"Exception during processing: {str(e)}"}
+    return summary
 
-# Gradio interface
+# Gradio UI
 iface = gr.Interface(
-    fn=extract_entities_from_pdf,
-    inputs=gr.File(file_types=[".pdf"]),
-    outputs=gr.JSON(),
-    title="🧹 Resume Cleaner & Entity Extractor",
-    description="Upload a PDF resume. The app will clean the text and extract entities like Person, Organization, and Location using a Hugging Face NER model."
+    fn=extract_entities_from_pdfs,
+    inputs=gr.File(file_types=[".pdf"], label="Upload Resumes (PDF)", file_count="multiple"),
+    outputs=gr.JSON(label="Resume Classification & Entity Summary"),
+    title="📂 Multi-Resume Entity Extractor & Classifier",
+    description="Upload multiple PDF resumes. This tool extracts text, identifies key entities, and classifies each resume by organizations, locations, and possible job/field."
 )
 
-# Launch
 if __name__ == "__main__":
     iface.launch()