src/streamlit_app.py

import streamlit as st
import pandas as pd
import numpy as np
import plotly.graph_objects as go
import plotly.express as px
from pathlib import Path
import pickle
import gdown
import zipfile
import os

# Page config
st.set_page_config(
    page_title="Skills-Based Job Matching System",
    page_icon="💼",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Custom CSS (your existing CSS here)
st.markdown("""
<style>
    .main-header {
        font-size: 2.5rem;
        color: #1e40af;
        font-weight: bold;
        margin-bottom: 0.5rem;
    }
    .sub-header {
        font-size: 1.2rem;
        color: #64748b;
        margin-bottom: 2rem;
    }
    .skill-badge {
        display: inline-block;
        padding: 0.25rem 0.75rem;
        margin: 0.25rem;
        border-radius: 1rem;
        font-size: 0.875rem;
        font-weight: 500;
    }
    .skill-match {
        background-color: #dcfce7;
        color: #166534;
    }
    .skill-missing {
        background-color: #fee2e2;
        color: #991b1b;
    }
    .match-score {
        font-size: 2rem;
        font-weight: bold;
        color: #1e40af;
    }
</style>
""", unsafe_allow_html=True)

# ============================================
# GOOGLE DRIVE SETUP
# ============================================
@st.cache_resource
def download_from_gdrive():
    """Download and extract project data from Google Drive"""
    
    # REPLACE THIS with your Google Drive file ID
    GDRIVE_FILE_ID = "1mUUvKpFX1usIpLu-dSiYc-F6Zogfw95o"
    
    # File paths
    zip_path = "project_data.zip"
    
    # Check if data already exists
    data_exists = (
        Path("data/processed_jobs.parquet").exists() and 
        Path("models").exists()
    )
    
    if data_exists:
        return True, "Data already loaded"
    
    try:
        # Download from Google Drive
        st.info("📥 Downloading data from Google Drive (1.2GB)...")
        st.info("This is a one-time download and will be cached. Please wait...")
        
        url = f"https://drive.google.com/uc?id={GDRIVE_FILE_ID}"
        
        # Create progress bar
        progress_bar = st.progress(0)
        status_text = st.empty()
        
        def show_progress(current, total):
            if total > 0:
                progress = int((current / total) * 100)
                progress_bar.progress(min(progress, 100))
                status_text.text(f"Downloading: {progress}% ({current/1024/1024:.1f}MB / {total/1024/1024:.1f}MB)")
        
        # Download with progress
        output = gdown.download(url, zip_path, quiet=False)
        
        if output is None:
            return False, "Failed to download. Please check if Google Drive link is public."
        
        progress_bar.progress(100)
        status_text.text("Download complete!")
        
        # Extract zip file
        st.info("📦 Extracting files...")
        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
            # Get total files for progress
            total_files = len(zip_ref.filelist)
            extract_progress = st.progress(0)
            
            for i, file in enumerate(zip_ref.filelist):
                zip_ref.extract(file, ".")
                extract_progress.progress((i + 1) / total_files)
        
        # Clean up
        os.remove(zip_path)
        
        return True, "✓ Data downloaded and ready!"
        
    except Exception as e:
        return False, f"Error: {str(e)}\n\nPlease ensure:\n1. Google Drive link is set to 'Anyone with the link'\n2. File ID is correct\n3. File is not corrupted"

# Download data first
download_success, download_message = download_from_gdrive()

if not download_success:
    st.error("❌ Failed to load data")
    st.error(download_message)
    st.info("""
    **Setup Instructions:**
    1. Upload your 1.2GB zip file to Google Drive
    2. Right-click → Get link → Set to "Anyone with the link"
    3. Copy the file ID from the link
    4. Update GDRIVE_FILE_ID in the code
    
    Example link: `https://drive.google.com/file/d/1a2b3c4d5e6f7g8h9i0j/view`
    File ID: `1a2b3c4d5e6f7g8h9i0j`
    """)
    st.stop()
else:
    st.success(download_message)

# ============================================
# YOUR EXISTING CODE CONTINUES HERE
# ============================================

# Initialize session state
if 'user_profile' not in st.session_state:
    st.session_state.user_profile = {
        'skills': [],
        'experience_level': 2,
        'min_salary': 0,
        'city': '',
        'state': '',
        'remote_only': False,
        'company_size': -1,
        'benefits': []
    }

if 'search_results' not in st.session_state:
    st.session_state.search_results = None

if 'selected_job' not in st.session_state:
    st.session_state.selected_job = None

# Import your modules (make sure they're in the zip)
try:
    from skill_extractor import SkillExtractor
    from ranking_pipeline import RankingPipeline
except ImportError as e:
    st.error(f"Error importing modules: {e}")
    st.info("Make sure skill_extractor.py and ranking_pipeline.py are in your zip file")
    st.stop()

# Cache data loading
@st.cache_resource
def load_models_and_data():
    """Load all models and data."""
    try:
        # Load processed data
        jobs_df = pd.read_parquet('data/processed_jobs.parquet')
        
        # Initialize pipeline
        pipeline = RankingPipeline(model_dir='models')
        pipeline.jobs_df = jobs_df
        pipeline.load_indices()
        pipeline.load_ltr_model()
        
        # Load skill extractor
        skill_extractor = SkillExtractor()
        
        return pipeline, jobs_df, skill_extractor
    except Exception as e:
        st.error(f"Error loading models: {e}")
        raise e

try:
    pipeline, jobs_df, skill_extractor = load_models_and_data()
    data_loaded = True
except Exception as e:
    st.error(f"Error loading data: {e}")
    st.info("Please check that your zip file contains:")
    st.code("""
    ├── data/
    │   └── processed_jobs.parquet
    ├── models/
    │   └── (your model files)
    ├── skill_extractor.py
    └── ranking_pipeline.py
    """)
    data_loaded = False
    st.stop()

# ============================================
# REST OF YOUR EXISTING APP CODE
# ============================================

# Sidebar - User Profile
with st.sidebar:
    st.markdown("### 👤 User Profile")
    
    # Skills input
    st.markdown("#### Skills")
    all_skills = skill_extractor.get_all_skills() if data_loaded else []
    
    selected_skills = st.multiselect(
        "Select your skills",
        options=all_skills,
        default=st.session_state.user_profile['skills'],
        help="Start typing to search skills"
    )
    st.session_state.user_profile['skills'] = selected_skills
    
    # ... (rest of your sidebar code)

# Main content
st.markdown('<h1 class="main-header">💼 Skills-Based Job Matching System</h1>', unsafe_allow_html=True)
st.markdown('<p class="sub-header">Find your perfect job match using AI-powered ranking</p>', unsafe_allow_html=True)

# ... (rest of your existing code)