Create app.py

app.py

@@ -0,0 +1,187 @@
+import gradio as gr
+from transformers import pipeline
+import pandas as pd
+import spacy
+import re
+from pathlib import Path
+import PyPDF2
+import docx
+import json
+
+# Load models
+nlp = spacy.load("en_core_web_sm")
+keyword_extractor = pipeline("token-classification", model="jean-baptiste/roberta-large-ner-english")
+classifier = pipeline("text-classification", model="microsoft/MiniLM-L12-H384-uncased")
+
+def extract_text_from_resume(file):
+    file_path = file.name
+    text = ""
+    
+    if file_path.endswith('.pdf'):
+        with open(file_path, 'rb') as pdf_file:
+            pdf_reader = PyPDF2.PdfReader(pdf_file)
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+    
+    elif file_path.endswith('.docx'):
+        doc = docx.Document(file_path)
+        for paragraph in doc.paragraphs:
+            text += paragraph.text + '\n'
+    
+    elif file_path.endswith('.txt'):
+        with open(file_path, 'r', encoding='utf-8') as txt_file:
+            text = txt_file.read()
+            
+    return text.strip()
+
+def extract_information(text):
+    doc = nlp(text)
+    
+    entities = {
+        "skills": [],
+        "education": [],
+        "experience": [],
+        "contact": []
+    }
+    
+    # Extract skills (using a predefined list of common skills)
+    common_skills = ["python", "java", "javascript", "sql", "machine learning", "data analysis"]
+    text_lower = text.lower()
+    entities["skills"] = [skill for skill in common_skills if skill in text_lower]
+    
+    # Extract education
+    education_keywords = ["university", "college", "bachelor", "master", "phd", "degree"]
+    for sent in doc.sents:
+        if any(keyword in sent.text.lower() for keyword in education_keywords):
+            entities["education"].append(sent.text.strip())
+    
+    # Extract experience
+    experience_keywords = ["experience", "work", "job", "position", "role"]
+    for sent in doc.sents:
+        if any(keyword in sent.text.lower() for keyword in experience_keywords):
+            entities["experience"].append(sent.text.strip())
+    
+    # Extract contact information
+    email_pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
+    phone_pattern = r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b'
+    
+    emails = re.findall(email_pattern, text)
+    phones = re.findall(phone_pattern, text)
+    
+    entities["contact"] = emails + phones
+    
+    return entities
+
+def analyze_resume(text, entities):
+    scores = {
+        "completeness": 0,
+        "skills_match": 0,
+        "formatting": 0,
+        "keyword_optimization": 0
+    }
+    
+    # Completeness score
+    score_components = 0
+    if entities["skills"]: score_components += 1
+    if entities["education"]: score_components += 1
+    if entities["experience"]: score_components += 1
+    if entities["contact"]: score_components += 1
+    scores["completeness"] = (score_components / 4) * 100
+    
+    # Skills match score
+    desired_skills = ["python", "java", "javascript", "sql", "machine learning"]
+    matched_skills = sum(1 for skill in entities["skills"] if skill in desired_skills)
+    scores["skills_match"] = (matched_skills / len(desired_skills)) * 100
+    
+    # Formatting score
+    formatting_score = 0
+    if len(text.split('\n')) > 5: formatting_score += 20
+    if len(text) > 200: formatting_score += 20
+    if any(char.isupper() for char in text): formatting_score += 20
+    if re.search(r'\b\d{4}\b', text): formatting_score += 20
+    if len(re.findall(r'[.!?]', text)) > 3: formatting_score += 20
+    scores["formatting"] = formatting_score
+    
+    # Keyword optimization score
+    keywords = keyword_extractor(text[:512])
+    scores["keyword_optimization"] = min(len(keywords) * 10, 100)
+    
+    return scores
+
+def generate_recommendations(scores, entities):
+    recommendations = []
+    
+    if scores["completeness"] < 75:
+        recommendations.append("📋 Add more sections to your resume to improve completeness.")
+        if not entities["skills"]:
+            recommendations.append("- Add a skills section")
+        if not entities["education"]:
+            recommendations.append("- Add education details")
+        if not entities["experience"]:
+            recommendations.append("- Add work experience")
+        if not entities["contact"]:
+            recommendations.append("- Add contact information")
+    
+    if scores["skills_match"] < 60:
+        recommendations.append("\n💡 Consider adding more relevant skills:")
+        recommendations.append("- Focus on technical skills like Python, Java, SQL")
+        recommendations.append("- Include both hard and soft skills")
+    
+    if scores["formatting"] < 80:
+        recommendations.append("\n📑 Improve resume formatting:")
+        recommendations.append("- Use clear section headings")
+        recommendations.append("- Include dates for experiences")
+        recommendations.append("- Use bullet points for better readability")
+    
+    if scores["keyword_optimization"] < 70:
+        recommendations.append("\n🔍 Optimize keywords usage:")
+        recommendations.append("- Use more industry-specific terms")
+        recommendations.append("- Include action verbs")
+        recommendations.append("- Mention specific technologies and tools")
+    
+    return "\n".join(recommendations)
+
+def process_resume(file):
+    text = extract_text_from_resume(file)
+    entities = extract_information(text)
+    scores = analyze_resume(text, entities)
+    recommendations = generate_recommendations(scores, entities)
+    
+    return scores, recommendations
+
+def create_interface():
+    with gr.Blocks() as app:
+        gr.Markdown("""
+        # Resume Analyzer and Optimizer
+        Upload your resume to get personalized analysis and recommendations.
+        """)
+        
+        with gr.Row():
+            file_input = gr.File(
+                label="Upload Resume (PDF, DOCX, or TXT)",
+                file_types=["pdf", "docx", "txt"]
+            )
+            
+        with gr.Row():
+            analyze_button = gr.Button("Analyze Resume", variant="primary")
+            
+        with gr.Row():
+            with gr.Column():
+                score_output = gr.JSON(label="Analysis Scores")
+            with gr.Column():
+                recommendations_output = gr.Textbox(
+                    label="Recommendations",
+                    lines=10
+                )
+                
+        analyze_button.click(
+            fn=process_resume,
+            inputs=[file_input],
+            outputs=[score_output, recommendations_output]
+        )
+    
+    return app
+
+if __name__ == "__main__":
+    app = create_interface()
+    app.launch()