app.py

import os
import argparse
import logging
import pickle
import threading
import time
import warnings
from datetime import datetime, timedelta
from collections import defaultdict
import csv 

# Suppress warnings for cleaner output
warnings.filterwarnings('ignore', category=FutureWarning)
warnings.filterwarnings('ignore', category=UserWarning, module='umap')
warnings.filterwarnings('ignore', category=UserWarning, module='sklearn')

import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
import cartopy.crs as ccrs
import cartopy.feature as cfeature
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots

from sklearn.manifold import TSNE
from sklearn.cluster import DBSCAN, KMeans
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from scipy.interpolate import interp1d
import statsmodels.api as sm
import requests
import tempfile
import shutil
import xarray as xr

# NEW: Advanced ML imports
try:
    import umap.umap_ as umap
    UMAP_AVAILABLE = True
except ImportError:
    UMAP_AVAILABLE = False
    print("UMAP not available - clustering features limited")

# Optional CNN imports with robust error handling
CNN_AVAILABLE = False
try:
    # Set environment variables before importing TensorFlow
    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'  # Suppress TensorFlow warnings
    import tensorflow as tf
    from tensorflow.keras import layers, models
    # Test if TensorFlow actually works
    tf.config.set_visible_devices([], 'GPU')  # Disable GPU to avoid conflicts
    CNN_AVAILABLE = True
    print("TensorFlow successfully loaded - CNN features enabled")
except Exception as e:
    CNN_AVAILABLE = False
    print(f"TensorFlow not available - CNN features disabled: {str(e)[:100]}...")

try:
    import cdsapi
    CDSAPI_AVAILABLE = True
except ImportError:
    CDSAPI_AVAILABLE = False

import tropycal.tracks as tracks

# -----------------------------
# Configuration and Setup
# -----------------------------
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)

# Remove argument parser to simplify startup
DATA_PATH = '/tmp/typhoon_data' if 'SPACE_ID' in os.environ else tempfile.gettempdir()

# Ensure directory exists and is writable
try:
    os.makedirs(DATA_PATH, exist_ok=True)
    # Test write permissions
    test_file = os.path.join(DATA_PATH, 'test_write.txt')
    with open(test_file, 'w') as f:
        f.write('test')
    os.remove(test_file)
    logging.info(f"Data directory is writable: {DATA_PATH}")
except Exception as e:
    logging.warning(f"Data directory not writable, using temp dir: {e}")
    DATA_PATH = tempfile.mkdtemp()
    logging.info(f"Using temporary directory: {DATA_PATH}")

# Update file paths
ONI_DATA_PATH = os.path.join(DATA_PATH, 'oni_data.csv')
TYPHOON_DATA_PATH = os.path.join(DATA_PATH, 'processed_typhoon_data.csv')
MERGED_DATA_CSV = os.path.join(DATA_PATH, 'merged_typhoon_era5_data.csv')

# IBTrACS settings
BASIN_FILES = {
    'EP': 'ibtracs.EP.list.v04r01.csv',
    'NA': 'ibtracs.NA.list.v04r01.csv',
    'WP': 'ibtracs.WP.list.v04r01.csv'
}
IBTRACS_BASE_URL = 'https://www.ncei.noaa.gov/data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r01/access/csv/'
LOCAL_IBTRACS_PATH = os.path.join(DATA_PATH, 'ibtracs.WP.list.v04r01.csv')
CACHE_FILE = os.path.join(DATA_PATH, 'ibtracs_cache.pkl')
CACHE_EXPIRY_DAYS = 1

# -----------------------------
# ENHANCED: Color Maps and Standards with TD Support
# -----------------------------
# Enhanced color mapping with TD support (for Plotly)
enhanced_color_map = {
    'Unknown': 'rgb(200, 200, 200)',
    'Tropical Depression': 'rgb(128, 128, 128)',  # Gray for TD
    'Tropical Storm': 'rgb(0, 0, 255)',
    'C1 Typhoon': 'rgb(0, 255, 255)',
    'C2 Typhoon': 'rgb(0, 255, 0)',
    'C3 Strong Typhoon': 'rgb(255, 255, 0)',
    'C4 Very Strong Typhoon': 'rgb(255, 165, 0)',
    'C5 Super Typhoon': 'rgb(255, 0, 0)'
}

# Matplotlib-compatible color mapping (hex colors)
matplotlib_color_map = {
    'Unknown': '#C8C8C8',
    'Tropical Depression': '#808080',  # Gray for TD
    'Tropical Storm': '#0000FF',       # Blue
    'C1 Typhoon': '#00FFFF',          # Cyan
    'C2 Typhoon': '#00FF00',          # Green
    'C3 Strong Typhoon': '#FFFF00',   # Yellow
    'C4 Very Strong Typhoon': '#FFA500', # Orange
    'C5 Super Typhoon': '#FF0000'     # Red
}

def rgb_string_to_hex(rgb_string):
    """Convert 'rgb(r,g,b)' string to hex color for matplotlib"""
    try:
        # Extract numbers from 'rgb(r,g,b)' format
        import re
        numbers = re.findall(r'\d+', rgb_string)
        if len(numbers) == 3:
            r, g, b = map(int, numbers)
            return f'#{r:02x}{g:02x}{b:02x}'
        else:
            return '#808080'  # Default gray
    except:
        return '#808080'  # Default gray

def get_matplotlib_color(category):
    """Get matplotlib-compatible color for a storm category"""
    return matplotlib_color_map.get(category, '#808080')

# Cluster colors for route visualization
CLUSTER_COLORS = [
    '#FF6B6B', '#4ECDC4', '#45B7D1', '#96CEB4', '#FFEAA7',
    '#DDA0DD', '#98D8C8', '#F7DC6F', '#BB8FCE', '#85C1E9',
    '#F8C471', '#82E0AA', '#F1948A', '#85C1E9', '#D2B4DE'
]

# Original color map for backward compatibility
color_map = {
    'C5 Super Typhoon': 'rgb(255, 0, 0)',
    'C4 Very Strong Typhoon': 'rgb(255, 165, 0)',
    'C3 Strong Typhoon': 'rgb(255, 255, 0)',
    'C2 Typhoon': 'rgb(0, 255, 0)',
    'C1 Typhoon': 'rgb(0, 255, 255)',
    'Tropical Storm': 'rgb(0, 0, 255)',
    'Tropical Depression': 'rgb(128, 128, 128)'
}

atlantic_standard = {
    'C5 Super Typhoon': {'wind_speed': 137, 'color': 'Red', 'hex': '#FF0000'},
    'C4 Very Strong Typhoon': {'wind_speed': 113, 'color': 'Orange', 'hex': '#FFA500'},
    'C3 Strong Typhoon': {'wind_speed': 96, 'color': 'Yellow', 'hex': '#FFFF00'},
    'C2 Typhoon': {'wind_speed': 83, 'color': 'Green', 'hex': '#00FF00'},
    'C1 Typhoon': {'wind_speed': 64, 'color': 'Cyan', 'hex': '#00FFFF'},
    'Tropical Storm': {'wind_speed': 34, 'color': 'Blue', 'hex': '#0000FF'},
    'Tropical Depression': {'wind_speed': 0, 'color': 'Gray', 'hex': '#808080'}
}

taiwan_standard = {
    'Strong Typhoon': {'wind_speed': 51.0, 'color': 'Red', 'hex': '#FF0000'},
    'Medium Typhoon': {'wind_speed': 33.7, 'color': 'Orange', 'hex': '#FFA500'},
    'Mild Typhoon': {'wind_speed': 17.2, 'color': 'Yellow', 'hex': '#FFFF00'},
    'Tropical Depression': {'wind_speed': 0, 'color': 'Gray', 'hex': '#808080'}
}

# -----------------------------
# Utility Functions for HF Spaces
# -----------------------------

def safe_file_write(file_path, data_frame, backup_dir=None):
    """Safely write DataFrame to CSV with backup and error handling"""
    try:
        # Create directory if it doesn't exist
        os.makedirs(os.path.dirname(file_path), exist_ok=True)
        
        # Try to write to a temporary file first
        temp_path = file_path + '.tmp'
        data_frame.to_csv(temp_path, index=False)
        
        # If successful, rename to final file
        os.rename(temp_path, file_path)
        logging.info(f"Successfully saved {len(data_frame)} records to {file_path}")
        return True
        
    except PermissionError as e:
        logging.warning(f"Permission denied writing to {file_path}: {e}")
        if backup_dir:
            try:
                backup_path = os.path.join(backup_dir, os.path.basename(file_path))
                data_frame.to_csv(backup_path, index=False)
                logging.info(f"Saved to backup location: {backup_path}")
                return True
            except Exception as backup_e:
                logging.error(f"Failed to save to backup location: {backup_e}")
        return False
        
    except Exception as e:
        logging.error(f"Error saving file {file_path}: {e}")
        # Clean up temp file if it exists
        temp_path = file_path + '.tmp'
        if os.path.exists(temp_path):
            try:
                os.remove(temp_path)
            except:
                pass
        return False

def get_fallback_data_dir():
    """Get a fallback data directory that's guaranteed to be writable"""
    fallback_dirs = [
        tempfile.gettempdir(),
        '/tmp',
        os.path.expanduser('~'),
        os.getcwd()
    ]
    
    for directory in fallback_dirs:
        try:
            test_dir = os.path.join(directory, 'typhoon_fallback')
            os.makedirs(test_dir, exist_ok=True)
            test_file = os.path.join(test_dir, 'test.txt')
            with open(test_file, 'w') as f:
                f.write('test')
            os.remove(test_file)
            return test_dir
        except:
            continue
    
    # If all else fails, use current directory
    return os.getcwd()

# -----------------------------
# ONI and Typhoon Data Functions
# -----------------------------

def download_oni_file(url, filename):
    """Download ONI file with retry logic"""
    max_retries = 3
    for attempt in range(max_retries):
        try:
            response = requests.get(url, timeout=30)
            response.raise_for_status()
            with open(filename, 'wb') as f:
                f.write(response.content)
            return True
        except Exception as e:
            logging.warning(f"Attempt {attempt + 1} failed to download ONI: {e}")
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)  # Exponential backoff
            else:
                logging.error(f"Failed to download ONI after {max_retries} attempts")
                return False

def convert_oni_ascii_to_csv(input_file, output_file):
    """Convert ONI ASCII format to CSV"""
    data = defaultdict(lambda: [''] * 12)
    season_to_month = {'DJF':12, 'JFM':1, 'FMA':2, 'MAM':3, 'AMJ':4, 'MJJ':5,
                       'JJA':6, 'JAS':7, 'ASO':8, 'SON':9, 'OND':10, 'NDJ':11}
    
    try:
        with open(input_file, 'r') as f:
            lines = f.readlines()[1:]  # Skip header
            for line in lines:
                parts = line.split()
                if len(parts) >= 4:
                    season, year, anom = parts[0], parts[1], parts[-1]
                    if season in season_to_month:
                        month = season_to_month[season]
                        if season == 'DJF':
                            year = str(int(year)-1)
                        data[year][month-1] = anom
        
        # Write to CSV with safe write
        df = pd.DataFrame(data).T.reset_index()
        df.columns = ['Year','Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']
        df = df.sort_values('Year').reset_index(drop=True)
        
        return safe_file_write(output_file, df, get_fallback_data_dir())
        
    except Exception as e:
        logging.error(f"Error converting ONI file: {e}")
        return False

def update_oni_data():
    """Update ONI data with error handling"""
    url = "https://www.cpc.ncep.noaa.gov/data/indices/oni.ascii.txt"
    temp_file = os.path.join(DATA_PATH, "temp_oni.ascii.txt")
    input_file = os.path.join(DATA_PATH, "oni.ascii.txt")
    output_file = ONI_DATA_PATH
    
    try:
        if download_oni_file(url, temp_file):
            if not os.path.exists(input_file) or not os.path.exists(output_file):
                os.rename(temp_file, input_file)
                convert_oni_ascii_to_csv(input_file, output_file)
            else:
                os.remove(temp_file)
        else:
            # Create fallback ONI data if download fails
            logging.warning("Creating fallback ONI data")
            create_fallback_oni_data(output_file)
    except Exception as e:
        logging.error(f"Error updating ONI data: {e}")
        create_fallback_oni_data(output_file)

def create_fallback_oni_data(output_file):
    """Create minimal ONI data for testing"""
    years = range(2000, 2026)  # Extended to include 2025
    months = ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']
    
    # Create synthetic ONI data
    data = []
    for year in years:
        row = [year]
        for month in months:
            # Generate some realistic ONI values
            value = np.random.normal(0, 1) * 0.5
            row.append(f"{value:.2f}")
        data.append(row)
    
    df = pd.DataFrame(data, columns=['Year'] + months)
    safe_file_write(output_file, df, get_fallback_data_dir())

# -----------------------------
# FIXED: IBTrACS Data Loading
# -----------------------------

def download_ibtracs_file(basin, force_download=False):
    """Download specific basin file from IBTrACS"""
    filename = BASIN_FILES[basin]
    local_path = os.path.join(DATA_PATH, filename)
    url = IBTRACS_BASE_URL + filename
    
    # Check if file exists and is recent (less than 7 days old)
    if os.path.exists(local_path) and not force_download:
        file_age = time.time() - os.path.getmtime(local_path)
        if file_age < 7 * 24 * 3600:  # 7 days
            logging.info(f"Using cached {basin} basin file")
            return local_path
    
    try:
        logging.info(f"Downloading {basin} basin file from {url}")
        response = requests.get(url, timeout=60)
        response.raise_for_status()
        
        # Ensure directory exists
        os.makedirs(os.path.dirname(local_path), exist_ok=True)
        
        with open(local_path, 'wb') as f:
            f.write(response.content)
        logging.info(f"Successfully downloaded {basin} basin file")
        return local_path
    except Exception as e:
        logging.error(f"Failed to download {basin} basin file: {e}")
        return None

def examine_ibtracs_structure(file_path):
    """Examine the actual structure of an IBTrACS CSV file"""
    try:
        with open(file_path, 'r') as f:
            lines = f.readlines()
        
        # Show first 5 lines
        logging.info("First 5 lines of IBTrACS file:")
        for i, line in enumerate(lines[:5]):
            logging.info(f"Line {i}: {line.strip()}")
        
        # The first line contains the actual column headers
        # No need to skip rows for IBTrACS v04r01
        df = pd.read_csv(file_path, nrows=5)
        logging.info(f"Columns from first row: {list(df.columns)}")
        
        return list(df.columns)
    except Exception as e:
        logging.error(f"Error examining IBTrACS structure: {e}")
        return None

def load_ibtracs_csv_directly(basin='WP'):
    """Load IBTrACS data directly from CSV - FIXED VERSION"""
    filename = BASIN_FILES[basin]
    local_path = os.path.join(DATA_PATH, filename)
    
    # Download if not exists
    if not os.path.exists(local_path):
        downloaded_path = download_ibtracs_file(basin)
        if not downloaded_path:
            return None
    
    try:
        # First, examine the structure
        actual_columns = examine_ibtracs_structure(local_path)
        if not actual_columns:
            logging.error("Could not examine IBTrACS file structure")
            return None
        
        # Read IBTrACS CSV - DON'T skip any rows for v04r01
        # The first row contains proper column headers
        logging.info(f"Reading IBTrACS CSV file: {local_path}")
        df = pd.read_csv(local_path, low_memory=False)  # Don't skip any rows
        
        logging.info(f"Original columns: {list(df.columns)}")
        logging.info(f"Data shape before cleaning: {df.shape}")
        
        # Check which essential columns exist
        required_cols = ['SID', 'ISO_TIME', 'LAT', 'LON']
        available_required = [col for col in required_cols if col in df.columns]
        
        if len(available_required) < 2:
            logging.error(f"Missing critical columns. Available: {list(df.columns)}")
            return None
        
        # Clean and standardize the data with format specification
        if 'ISO_TIME' in df.columns:
            df['ISO_TIME'] = pd.to_datetime(df['ISO_TIME'], format='%Y-%m-%d %H:%M:%S', errors='coerce')
        
        # Clean numeric columns
        numeric_columns = ['LAT', 'LON', 'WMO_WIND', 'WMO_PRES', 'USA_WIND', 'USA_PRES']
        for col in numeric_columns:
            if col in df.columns:
                df[col] = pd.to_numeric(df[col], errors='coerce')
        
        # Filter out invalid/missing critical data
        valid_rows = df['LAT'].notna() & df['LON'].notna()
        df = df[valid_rows]
        
        # Ensure LAT/LON are in reasonable ranges
        df = df[(df['LAT'] >= -90) & (df['LAT'] <= 90)]
        df = df[(df['LON'] >= -180) & (df['LON'] <= 180)]
        
        # Add basin info if missing
        if 'BASIN' not in df.columns:
            df['BASIN'] = basin
        
        # Add default columns if missing
        if 'NAME' not in df.columns:
            df['NAME'] = 'UNNAMED'
        
        if 'SEASON' not in df.columns and 'ISO_TIME' in df.columns:
            df['SEASON'] = df['ISO_TIME'].dt.year
        
        logging.info(f"Successfully loaded {len(df)} records from {basin} basin")
        return df
        
    except Exception as e:
        logging.error(f"Error reading IBTrACS CSV file: {e}")
        return None

def load_ibtracs_data_fixed():
    """Fixed version of IBTrACS data loading"""
    ibtracs_data = {}
    
    # Try to load each basin, but prioritize WP for this application
    load_order = ['WP', 'EP', 'NA']
    
    for basin in load_order:
        try:
            logging.info(f"Loading {basin} basin data...")
            df = load_ibtracs_csv_directly(basin)
            
            if df is not None and not df.empty:
                ibtracs_data[basin] = df
                logging.info(f"Successfully loaded {basin} basin with {len(df)} records")
            else:
                logging.warning(f"No data loaded for basin {basin}")
                ibtracs_data[basin] = None
                
        except Exception as e:
            logging.error(f"Failed to load basin {basin}: {e}")
            ibtracs_data[basin] = None
    
    return ibtracs_data

def load_data_fixed(oni_path, typhoon_path):
    """Fixed version of load_data function"""
    # Load ONI data
    oni_data = pd.DataFrame({'Year': [], 'Jan': [], 'Feb': [], 'Mar': [], 'Apr': [], 
                           'May': [], 'Jun': [], 'Jul': [], 'Aug': [], 'Sep': [], 
                           'Oct': [], 'Nov': [], 'Dec': []})
    
    if not os.path.exists(oni_path):
        logging.warning(f"ONI data file not found: {oni_path}")
        update_oni_data()
    
    try:
        oni_data = pd.read_csv(oni_path)
        logging.info(f"Successfully loaded ONI data with {len(oni_data)} years")
    except Exception as e:
        logging.error(f"Error loading ONI data: {e}")
        update_oni_data()
        try:
            oni_data = pd.read_csv(oni_path)
        except Exception as e:
            logging.error(f"Still can't load ONI data: {e}")
    
    # Load typhoon data - NEW APPROACH
    typhoon_data = None
    
    # First, try to load from existing processed file
    if os.path.exists(typhoon_path):
        try:
            typhoon_data = pd.read_csv(typhoon_path, low_memory=False)
            # Ensure basic columns exist and are valid
            required_cols = ['LAT', 'LON']
            if all(col in typhoon_data.columns for col in required_cols):
                if 'ISO_TIME' in typhoon_data.columns:
                    typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
                logging.info(f"Loaded processed typhoon data with {len(typhoon_data)} records")
            else:
                logging.warning("Processed typhoon data missing required columns, will reload from IBTrACS")
                typhoon_data = None
        except Exception as e:
            logging.error(f"Error loading processed typhoon data: {e}")
            typhoon_data = None
    
    # If no valid processed data, load from IBTrACS
    if typhoon_data is None or typhoon_data.empty:
        logging.info("Loading typhoon data from IBTrACS...")
        ibtracs_data = load_ibtracs_data_fixed()
        
        # Combine all available basin data, prioritizing WP
        combined_dfs = []
        for basin in ['WP', 'EP', 'NA']:
            if basin in ibtracs_data and ibtracs_data[basin] is not None:
                df = ibtracs_data[basin].copy()
                df['BASIN'] = basin
                combined_dfs.append(df)
        
        if combined_dfs:
            typhoon_data = pd.concat(combined_dfs, ignore_index=True)
            # Ensure SID has proper format
            if 'SID' not in typhoon_data.columns and 'BASIN' in typhoon_data.columns:
                # Create SID from basin and other identifiers if missing
                if 'SEASON' in typhoon_data.columns:
                    typhoon_data['SID'] = (typhoon_data['BASIN'].astype(str) + 
                                         typhoon_data.index.astype(str).str.zfill(2) + 
                                         typhoon_data['SEASON'].astype(str))
                else:
                    typhoon_data['SID'] = (typhoon_data['BASIN'].astype(str) + 
                                         typhoon_data.index.astype(str).str.zfill(2) + 
                                         '2000')
            
            # Save the processed data for future use
            safe_file_write(typhoon_path, typhoon_data, get_fallback_data_dir())
            logging.info(f"Combined IBTrACS data: {len(typhoon_data)} total records")
        else:
            logging.error("Failed to load any IBTrACS basin data")
            # Create minimal fallback data
            typhoon_data = create_fallback_typhoon_data()
    
    # Final validation of typhoon data
    if typhoon_data is not None:
        # Ensure required columns exist with fallback values
        required_columns = {
            'SID': 'UNKNOWN',
            'ISO_TIME': pd.Timestamp('2000-01-01'),
            'LAT': 0.0,
            'LON': 0.0,
            'USA_WIND': np.nan,
            'USA_PRES': np.nan,
            'NAME': 'UNNAMED',
            'SEASON': 2000
        }
        
        for col, default_val in required_columns.items():
            if col not in typhoon_data.columns:
                typhoon_data[col] = default_val
                logging.warning(f"Added missing column {col} with default value")
        
        # Ensure data types
        if 'ISO_TIME' in typhoon_data.columns:
            typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
        typhoon_data['LAT'] = pd.to_numeric(typhoon_data['LAT'], errors='coerce')
        typhoon_data['LON'] = pd.to_numeric(typhoon_data['LON'], errors='coerce')
        typhoon_data['USA_WIND'] = pd.to_numeric(typhoon_data['USA_WIND'], errors='coerce')
        typhoon_data['USA_PRES'] = pd.to_numeric(typhoon_data['USA_PRES'], errors='coerce')
        
        # Remove rows with invalid coordinates
        typhoon_data = typhoon_data.dropna(subset=['LAT', 'LON'])
        
        logging.info(f"Final typhoon data: {len(typhoon_data)} records after validation")
    
    return oni_data, typhoon_data

def create_fallback_typhoon_data():
    """Create minimal fallback typhoon data - FIXED VERSION"""
    # Use proper pandas date_range instead of numpy
    dates = pd.date_range(start='2000-01-01', end='2025-12-31', freq='D')  # Extended to 2025
    storm_dates = dates[np.random.choice(len(dates), size=100, replace=False)]
    
    data = []
    for i, date in enumerate(storm_dates):
        # Create realistic WP storm tracks
        base_lat = np.random.uniform(10, 30)
        base_lon = np.random.uniform(130, 160)
        
        # Generate 20-50 data points per storm
        track_length = np.random.randint(20, 51)
        sid = f"WP{i+1:02d}{date.year}"
        
        for j in range(track_length):
            lat = base_lat + j * 0.2 + np.random.normal(0, 0.1)
            lon = base_lon + j * 0.3 + np.random.normal(0, 0.1)
            wind = max(25, 70 + np.random.normal(0, 20))
            pres = max(950, 1000 - wind + np.random.normal(0, 5))
            
            data.append({
                'SID': sid,
                'ISO_TIME': date + pd.Timedelta(hours=j*6),  # Use pd.Timedelta instead
                'NAME': f'FALLBACK_{i+1}',
                'SEASON': date.year,
                'LAT': lat,
                'LON': lon,
                'USA_WIND': wind,
                'USA_PRES': pres,
                'BASIN': 'WP'
            })
    
    df = pd.DataFrame(data)
    logging.info(f"Created fallback typhoon data with {len(df)} records")
    return df

def process_oni_data(oni_data):
    """Process ONI data into long format"""
    oni_long = oni_data.melt(id_vars=['Year'], var_name='Month', value_name='ONI')
    month_map = {'Jan':'01','Feb':'02','Mar':'03','Apr':'04','May':'05','Jun':'06',
                 'Jul':'07','Aug':'08','Sep':'09','Oct':'10','Nov':'11','Dec':'12'}
    oni_long['Month'] = oni_long['Month'].map(month_map)
    oni_long['Date'] = pd.to_datetime(oni_long['Year'].astype(str)+'-'+oni_long['Month']+'-01')
    oni_long['ONI'] = pd.to_numeric(oni_long['ONI'], errors='coerce')
    return oni_long

def process_typhoon_data(typhoon_data):
    """Process typhoon data"""
    if 'ISO_TIME' in typhoon_data.columns:
        typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
    typhoon_data['USA_WIND'] = pd.to_numeric(typhoon_data['USA_WIND'], errors='coerce')
    typhoon_data['USA_PRES'] = pd.to_numeric(typhoon_data['USA_PRES'], errors='coerce')
    typhoon_data['LON'] = pd.to_numeric(typhoon_data['LON'], errors='coerce')
    
    logging.info(f"Unique basins in typhoon_data: {typhoon_data['SID'].str[:2].unique()}")
    
    typhoon_max = typhoon_data.groupby('SID').agg({
        'USA_WIND':'max','USA_PRES':'min','ISO_TIME':'first','SEASON':'first','NAME':'first',
        'LAT':'first','LON':'first'
    }).reset_index()
    
    if 'ISO_TIME' in typhoon_max.columns:
        typhoon_max['Month'] = typhoon_max['ISO_TIME'].dt.strftime('%m')
        typhoon_max['Year'] = typhoon_max['ISO_TIME'].dt.year
    else:
        # Fallback if no ISO_TIME
        typhoon_max['Month'] = '01'
        typhoon_max['Year'] = typhoon_max['SEASON']
    
    typhoon_max['Category'] = typhoon_max['USA_WIND'].apply(categorize_typhoon_enhanced)
    return typhoon_max

def merge_data(oni_long, typhoon_max):
    """Merge ONI and typhoon data"""
    return pd.merge(typhoon_max, oni_long, on=['Year','Month'])

# -----------------------------
# ENHANCED: Categorization Functions
# -----------------------------

def categorize_typhoon_enhanced(wind_speed):
    """Enhanced categorization that properly includes Tropical Depressions"""
    if pd.isna(wind_speed):
        return 'Unknown'
    
    # Convert to knots if in m/s (some datasets use m/s)
    if wind_speed < 10:  # Likely in m/s, convert to knots
        wind_speed = wind_speed * 1.94384
    
    # FIXED thresholds to include TD
    if wind_speed < 34:  # Below 34 knots = Tropical Depression
        return 'Tropical Depression'
    elif wind_speed < 64:  # 34-63 knots = Tropical Storm
        return 'Tropical Storm'
    elif wind_speed < 83:  # 64-82 knots = Category 1 Typhoon
        return 'C1 Typhoon'
    elif wind_speed < 96:  # 83-95 knots = Category 2 Typhoon
        return 'C2 Typhoon'
    elif wind_speed < 113:  # 96-112 knots = Category 3 Strong Typhoon
        return 'C3 Strong Typhoon'
    elif wind_speed < 137:  # 113-136 knots = Category 4 Very Strong Typhoon
        return 'C4 Very Strong Typhoon'
    else:  # 137+ knots = Category 5 Super Typhoon
        return 'C5 Super Typhoon'

# Original function for backward compatibility
def categorize_typhoon(wind_speed):
    """Original categorize typhoon function for backward compatibility"""
    return categorize_typhoon_enhanced(wind_speed)

def classify_enso_phases(oni_value):
    """Classify ENSO phases based on ONI value"""
    if isinstance(oni_value, pd.Series):
        oni_value = oni_value.iloc[0]
    if pd.isna(oni_value):
        return 'Neutral'
    if oni_value >= 0.5:
        return 'El Nino'
    elif oni_value <= -0.5:
        return 'La Nina'
    else:
        return 'Neutral'

# -----------------------------
# NEW: ADVANCED ML FEATURES WITH ROUTE VISUALIZATION
# -----------------------------

def extract_storm_features(typhoon_data):
    """Extract comprehensive features for clustering analysis"""
    # Group by storm ID to get storm-level features
    storm_features = typhoon_data.groupby('SID').agg({
        'USA_WIND': ['max', 'mean', 'std'],
        'USA_PRES': ['min', 'mean', 'std'],
        'LAT': ['mean', 'std', 'max', 'min'],
        'LON': ['mean', 'std', 'max', 'min'],
        'ISO_TIME': ['count']  # Track length
    }).reset_index()
    
    # Flatten column names
    storm_features.columns = ['SID'] + ['_'.join(col).strip() for col in storm_features.columns[1:]]
    
    # Add additional computed features
    storm_features['lat_range'] = storm_features['LAT_max'] - storm_features['LAT_min']
    storm_features['lon_range'] = storm_features['LON_max'] - storm_features['LON_min']
    storm_features['track_length'] = storm_features['ISO_TIME_count']
    
    # Add genesis location features
    genesis_data = typhoon_data.groupby('SID').first()[['LAT', 'LON', 'USA_WIND']]
    genesis_data.columns = ['genesis_lat', 'genesis_lon', 'genesis_intensity']
    storm_features = storm_features.merge(genesis_data, on='SID', how='left')
    
    # Add track shape features
    track_stats = []
    for sid in storm_features['SID']:
        storm_track = typhoon_data[typhoon_data['SID'] == sid].sort_values('ISO_TIME')
        if len(storm_track) > 2:
            # Calculate track curvature and direction changes
            lats = storm_track['LAT'].values
            lons = storm_track['LON'].values
            
            # Calculate bearing changes
            bearing_changes = []
            for i in range(1, len(lats)-1):
                # Simple bearing calculation
                dlat1 = lats[i] - lats[i-1]
                dlon1 = lons[i] - lons[i-1]
                dlat2 = lats[i+1] - lats[i]
                dlon2 = lons[i+1] - lons[i]
                
                angle1 = np.arctan2(dlat1, dlon1)
                angle2 = np.arctan2(dlat2, dlon2)
                change = abs(angle2 - angle1)
                bearing_changes.append(change)
            
            avg_curvature = np.mean(bearing_changes) if bearing_changes else 0
            total_distance = np.sum(np.sqrt((np.diff(lats)**2 + np.diff(lons)**2)))
            
            track_stats.append({
                'SID': sid,
                'avg_curvature': avg_curvature,
                'total_distance': total_distance
            })
        else:
            track_stats.append({
                'SID': sid,
                'avg_curvature': 0,
                'total_distance': 0
            })
    
    track_stats_df = pd.DataFrame(track_stats)
    storm_features = storm_features.merge(track_stats_df, on='SID', how='left')
    
    return storm_features

def perform_dimensionality_reduction(storm_features, method='umap', n_components=2):
    """Perform UMAP or t-SNE dimensionality reduction"""
    # Select numeric features for clustering
    feature_cols = [col for col in storm_features.columns if col != 'SID' and storm_features[col].dtype in ['float64', 'int64']]
    X = storm_features[feature_cols].fillna(0)
    
    # Standardize features
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)
    
    if method.lower() == 'umap' and UMAP_AVAILABLE:
        # UMAP parameters optimized for typhoon data - fixed warnings
        reducer = umap.UMAP(
            n_components=n_components,
            n_neighbors=15,
            min_dist=0.1,
            metric='euclidean',
            random_state=42,
            n_jobs=1  # Explicitly set to avoid warning
        )
    elif method.lower() == 'tsne':
        # t-SNE parameters
        reducer = TSNE(
            n_components=n_components,
            perplexity=min(30, len(X_scaled)//4),
            learning_rate=200,
            n_iter=1000,
            random_state=42
        )
    else:
        # Fallback to PCA if UMAP not available
        reducer = PCA(n_components=n_components, random_state=42)
    
    # Fit and transform
    embedding = reducer.fit_transform(X_scaled)
    
    return embedding, feature_cols, scaler

def cluster_storms(embedding, method='dbscan', eps=0.5, min_samples=3):
    """Cluster storms based on their embedding"""
    if method.lower() == 'dbscan':
        clusterer = DBSCAN(eps=eps, min_samples=min_samples)
    elif method.lower() == 'kmeans':
        clusterer = KMeans(n_clusters=5, random_state=42)
    else:
        raise ValueError("Method must be 'dbscan' or 'kmeans'")
    
    clusters = clusterer.fit_predict(embedding)
    return clusters

def create_advanced_clustering_visualization(storm_features, typhoon_data, method='umap', show_routes=True):
    """Create comprehensive clustering visualization with route display"""
    try:
        # Validate inputs
        if storm_features is None or storm_features.empty:
            raise ValueError("No storm features available for clustering")
            
        if typhoon_data is None or typhoon_data.empty:
            raise ValueError("No typhoon data available for route visualization")
        
        # Perform dimensionality reduction
        embedding, feature_cols, scaler = perform_dimensionality_reduction(storm_features, method)
        
        # Perform clustering
        cluster_labels = cluster_storms(embedding, 'dbscan')
        
        # Add clustering results to storm features
        storm_features_viz = storm_features.copy()
        storm_features_viz['cluster'] = cluster_labels
        storm_features_viz['dim1'] = embedding[:, 0]
        storm_features_viz['dim2'] = embedding[:, 1]
        
        # Merge with typhoon data for additional info
        storm_info = typhoon_data.groupby('SID').first()[['NAME', 'SEASON']].reset_index()
        storm_features_viz = storm_features_viz.merge(storm_info, on='SID', how='left')
        
        if show_routes:
            # Create subplot with both scatter plot and route map
            fig = make_subplots(
                rows=1, cols=2,
                subplot_titles=(
                    f'Storm Clustering using {method.upper()}',
                    'Clustered Storm Routes'
                ),
                specs=[[{"type": "scatter"}, {"type": "geo"}]],
                column_widths=[0.5, 0.5]
            )
            
            # Add clustering scatter plot
            unique_clusters = sorted(storm_features_viz['cluster'].unique())
            for i, cluster in enumerate(unique_clusters):
                cluster_data = storm_features_viz[storm_features_viz['cluster'] == cluster]
                color = CLUSTER_COLORS[i % len(CLUSTER_COLORS)] if cluster != -1 else '#CCCCCC'
                cluster_name = f'Cluster {cluster}' if cluster != -1 else 'Noise'
                
                fig.add_trace(
                    go.Scatter(
                        x=cluster_data['dim1'],
                        y=cluster_data['dim2'],
                        mode='markers',
                        marker=dict(color=color, size=8),
                        name=cluster_name,
                        hovertemplate=(
                            '<b>%{customdata[0]}</b><br>'
                            'Season: %{customdata[1]}<br>'
                            'Max Wind: %{customdata[2]:.0f} kt<br>'
                            'Min Pressure: %{customdata[3]:.0f} hPa<br>'
                            'Track Length: %{customdata[4]:.0f} points<br>'
                            '<extra></extra>'
                        ),
                        customdata=np.column_stack((
                            cluster_data['NAME'].fillna('UNNAMED'),
                            cluster_data['SEASON'].fillna(2000),
                            cluster_data['USA_WIND_max'].fillna(0),
                            cluster_data['USA_PRES_min'].fillna(1000),
                            cluster_data['track_length'].fillna(0)
                        ))
                    ),
                    row=1, col=1
                )
            
            # Add route map
            for i, cluster in enumerate(unique_clusters):
                if cluster == -1:  # Skip noise for route visualization
                    continue
                    
                cluster_storm_ids = storm_features_viz[storm_features_viz['cluster'] == cluster]['SID'].tolist()
                color = CLUSTER_COLORS[i % len(CLUSTER_COLORS)]
                
                for j, sid in enumerate(cluster_storm_ids[:10]):  # Limit to 10 storms per cluster for performance
                    try:
                        storm_track = typhoon_data[typhoon_data['SID'] == sid].sort_values('ISO_TIME')
                        if len(storm_track) > 1:
                            storm_name = storm_track['NAME'].iloc[0] if pd.notna(storm_track['NAME'].iloc[0]) else 'UNNAMED'
                            
                            fig.add_trace(
                                go.Scattergeo(
                                    lon=storm_track['LON'],
                                    lat=storm_track['LAT'],
                                    mode='lines+markers',
                                    line=dict(color=color, width=2),
                                    marker=dict(color=color, size=4),
                                    name=f'C{cluster}: {storm_name}' if j == 0 else None,
                                    showlegend=(j == 0),
                                    hovertemplate=(
                                        f'<b>{storm_name}</b><br>'
                                        'Lat: %{lat:.1f}°<br>'
                                        'Lon: %{lon:.1f}°<br>'
                                        f'Cluster: {cluster}<br>'
                                        '<extra></extra>'
                                    )
                                ),
                                row=1, col=2
                            )
                    except Exception as track_error:
                        print(f"Error adding track for storm {sid}: {track_error}")
                        continue
            
            # Update layout
            fig.update_layout(
                title_text="Advanced Storm Clustering Analysis with Route Visualization",
                showlegend=True
            )
            
            # Update geo layout
            fig.update_geos(
                projection_type="natural earth",
                showland=True,
                landcolor="LightGray",
                showocean=True,
                oceancolor="LightBlue",
                showcoastlines=True,
                coastlinecolor="Gray",
                center=dict(lat=20, lon=140),
                row=1, col=2
            )
            
            # Update scatter plot axes
            fig.update_xaxes(title_text=f"{method.upper()} Dimension 1", row=1, col=1)
            fig.update_yaxes(title_text=f"{method.upper()} Dimension 2", row=1, col=1)
            
        else:
            # Simple scatter plot only
            fig = px.scatter(
                storm_features_viz,
                x='dim1',
                y='dim2',
                color='cluster',
                hover_data=['NAME', 'SEASON', 'USA_WIND_max', 'USA_PRES_min'],
                title=f'Storm Clustering using {method.upper()}',
                labels={
                    'dim1': f'{method.upper()} Dimension 1',
                    'dim2': f'{method.upper()} Dimension 2',
                    'cluster': 'Cluster'
                }
            )
        
        # Generate detailed cluster statistics
        try:
            cluster_stats = storm_features_viz.groupby('cluster').agg({
                'USA_WIND_max': ['mean', 'std', 'min', 'max'],
                'USA_PRES_min': ['mean', 'std', 'min', 'max'],
                'track_length': ['mean', 'std'],
                'genesis_lat': 'mean',
                'genesis_lon': 'mean',
                'total_distance': 'mean',
                'avg_curvature': 'mean',
                'SID': 'count'
            }).round(2)
            
            # Flatten column names for readability
            cluster_stats.columns = ['_'.join(col).strip() for col in cluster_stats.columns]
            
            stats_text = "ADVANCED CLUSTER ANALYSIS RESULTS\n" + "="*50 + "\n\n"
            
            for cluster in sorted(storm_features_viz['cluster'].unique()):
                if cluster == -1:
                    stats_text += f"NOISE POINTS: {cluster_stats.loc[-1, 'SID_count']} storms\n\n"
                    continue
                
                cluster_row = cluster_stats.loc[cluster]
                storm_count = int(cluster_row['SID_count'])
                
                stats_text += f"CLUSTER {cluster}: {storm_count} storms\n"
                stats_text += f"   Intensity: {cluster_row['USA_WIND_max_mean']:.1f} +/- {cluster_row['USA_WIND_max_std']:.1f} kt\n"
                stats_text += f"   Pressure: {cluster_row['USA_PRES_min_mean']:.1f} +/- {cluster_row['USA_PRES_min_std']:.1f} hPa\n"
                stats_text += f"   Track Length: {cluster_row['track_length_mean']:.1f} +/- {cluster_row['track_length_std']:.1f} points\n"
                stats_text += f"   Genesis Region: {cluster_row['genesis_lat']:.1f}°N, {cluster_row['genesis_lon']:.1f}°E\n"
                stats_text += f"   Avg Distance: {cluster_row['total_distance_mean']:.2f} degrees\n"
                stats_text += f"   Avg Curvature: {cluster_row['avg_curvature_mean']:.3f} radians\n\n"
            
            # Add feature importance summary
            stats_text += "CLUSTERING FEATURES USED:\n"
            stats_text += "   - Storm intensity (max/mean/std wind & pressure)\n"
            stats_text += "   - Track characteristics (length, curvature, distance)\n"
            stats_text += "   - Genesis location (lat/lon)\n"
            stats_text += "   - Geographic range (lat/lon span)\n"
            stats_text += f"   - Total features: {len(feature_cols)}\n\n"
            
            stats_text += f"ALGORITHM: {method.upper()} + DBSCAN clustering\n"
            stats_text += f"CLUSTERS FOUND: {len([c for c in storm_features_viz['cluster'].unique() if c != -1])}\n"
            
        except Exception as stats_error:
            stats_text = f"Error generating cluster statistics: {str(stats_error)}"
        
        return fig, stats_text, storm_features_viz
        
    except Exception as e:
        error_fig = go.Figure()
        error_fig.add_annotation(
            text=f"Error in clustering analysis: {str(e)}",
            xref="paper", yref="paper",
            x=0.5, y=0.5, xanchor='center', yanchor='middle',
            showarrow=False, font_size=16
        )
        return error_fig, f"Error in clustering: {str(e)}", None

# -----------------------------
# NEW: Optional CNN Implementation
# -----------------------------

def create_cnn_model(input_shape=(64, 64, 3)):
    """Create CNN model for typhoon intensity prediction from satellite images"""
    if not CNN_AVAILABLE:
        return None
    
    try:
        model = models.Sequential([
            # Convolutional layers
            layers.Conv2D(32, (3, 3), activation='relu', input_shape=input_shape),
            layers.MaxPooling2D((2, 2)),
            layers.Conv2D(64, (3, 3), activation='relu'),
            layers.MaxPooling2D((2, 2)),
            layers.Conv2D(64, (3, 3), activation='relu'),
            layers.MaxPooling2D((2, 2)),
            
            # Dense layers
            layers.Flatten(),
            layers.Dense(64, activation='relu'),
            layers.Dropout(0.5),
            layers.Dense(32, activation='relu'),
            
            # Output layer for intensity prediction
            layers.Dense(1, activation='linear')  # Regression for wind speed
        ])
        
        model.compile(
            optimizer='adam',
            loss='mean_squared_error',
            metrics=['mae']
        )
        
        return model
    except Exception as e:
        print(f"Error creating CNN model: {e}")
        return None

def simulate_cnn_prediction(lat, lon, month, oni_value):
    """Simulate CNN prediction with robust error handling"""
    try:
        if not CNN_AVAILABLE:
            # Provide a physics-based prediction when CNN is not available
            return simulate_physics_based_prediction(lat, lon, month, oni_value)
        
        # This would normally process satellite imagery
        # For demo purposes, we'll use a simple heuristic
        
        # Simulate environmental factors
        sst_anomaly = oni_value * 0.5  # Simplified SST relationship
        seasonal_factor = 1.2 if month in [7, 8, 9, 10] else 0.8
        latitude_factor = max(0.5, (30 - abs(lat)) / 30) if abs(lat) < 30 else 0.1
        
        # Simple intensity prediction
        base_intensity = 40
        intensity = base_intensity + sst_anomaly * 10 + seasonal_factor * 20 + latitude_factor * 30
        intensity = max(0, min(180, intensity))  # Clamp to reasonable range
        
        confidence = 0.75 + np.random.normal(0, 0.1)
        confidence = max(0.5, min(0.95, confidence))
        
        return intensity, f"CNN Prediction: {intensity:.1f} kt (Confidence: {confidence:.1%})"
    except Exception as e:
        # Fallback to physics-based prediction
        return simulate_physics_based_prediction(lat, lon, month, oni_value)

def simulate_physics_based_prediction(lat, lon, month, oni_value):
    """Physics-based intensity prediction as fallback"""
    try:
        # Simple climatological prediction based on known relationships
        base_intensity = 45
        
        # ENSO effects
        if oni_value > 0.5:  # El Niño
            intensity_modifier = -15  # Generally suppresses activity in WP
        elif oni_value < -0.5:  # La Niña
            intensity_modifier = +20  # Generally enhances activity
        else:
            intensity_modifier = 0
        
        # Seasonal effects
        if month in [8, 9, 10]:  # Peak season
            seasonal_modifier = 25
        elif month in [6, 7, 11]:  # Active season
            seasonal_modifier = 15
        else:  # Quiet season
            seasonal_modifier = -10
        
        # Latitude effects (closer to equator = less favorable)
        if abs(lat) < 10:
            lat_modifier = -20  # Too close to equator
        elif 10 <= abs(lat) <= 25:
            lat_modifier = 10   # Optimal range
        else:
            lat_modifier = -5   # Too far from equator
        
        # Longitude effects for Western Pacific
        if 120 <= lon <= 160:
            lon_modifier = 10   # Favorable WP region
        else:
            lon_modifier = -5
        
        predicted_intensity = base_intensity + intensity_modifier + seasonal_modifier + lat_modifier + lon_modifier
        predicted_intensity = max(25, min(180, predicted_intensity))
        
        confidence = 0.65  # Lower confidence for physics-based model
        
        return predicted_intensity, f"Physics-based Prediction: {predicted_intensity:.1f} kt (Confidence: {confidence:.1%})"
    except Exception as e:
        return 50, f"Error in prediction: {str(e)}"

# -----------------------------
# Regression Functions (Original)
# -----------------------------

def perform_wind_regression(start_year, start_month, end_year, end_month):
    """Perform wind regression analysis"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].dropna(subset=['USA_WIND','ONI'])
    data['severe_typhoon'] = (data['USA_WIND']>=64).astype(int)
    X = sm.add_constant(data['ONI'])
    y = data['severe_typhoon']
    try:
        model = sm.Logit(y, X).fit(disp=0)
        beta_1 = model.params['ONI']
        exp_beta_1 = np.exp(beta_1)
        p_value = model.pvalues['ONI']
        return f"Wind Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"
    except Exception as e:
        return f"Wind Regression Error: {e}"

def perform_pressure_regression(start_year, start_month, end_year, end_month):
    """Perform pressure regression analysis"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].dropna(subset=['USA_PRES','ONI'])
    data['intense_typhoon'] = (data['USA_PRES']<=950).astype(int)
    X = sm.add_constant(data['ONI'])
    y = data['intense_typhoon']
    try:
        model = sm.Logit(y, X).fit(disp=0)
        beta_1 = model.params['ONI']
        exp_beta_1 = np.exp(beta_1)
        p_value = model.pvalues['ONI']
        return f"Pressure Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"
    except Exception as e:
        return f"Pressure Regression Error: {e}"

def perform_longitude_regression(start_year, start_month, end_year, end_month):
    """Perform longitude regression analysis"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].dropna(subset=['LON','ONI'])
    data['western_typhoon'] = (data['LON']<=140).astype(int)
    X = sm.add_constant(data['ONI'])
    y = data['western_typhoon']
    try:
        model = sm.OLS(y, sm.add_constant(X)).fit()
        beta_1 = model.params['ONI']
        exp_beta_1 = np.exp(beta_1)
        p_value = model.pvalues['ONI']
        return f"Longitude Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"
    except Exception as e:
        return f"Longitude Regression Error: {e}"

# -----------------------------
# Visualization Functions (Enhanced)
# -----------------------------

def get_full_tracks(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
    """Get full typhoon tracks"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
    filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
    if enso_phase != 'all':
        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
    unique_storms = filtered_data['SID'].unique()
    count = len(unique_storms)
    fig = go.Figure()
    for sid in unique_storms:
        storm_data = typhoon_data[typhoon_data['SID']==sid]
        if storm_data.empty:
            continue
        name = storm_data['NAME'].iloc[0] if pd.notnull(storm_data['NAME'].iloc[0]) else "Unnamed"
        basin = storm_data['SID'].iloc[0][:2]
        storm_oni = filtered_data[filtered_data['SID']==sid]['ONI'].iloc[0]
        color = 'red' if storm_oni>=0.5 else ('blue' if storm_oni<=-0.5 else 'green')
        fig.add_trace(go.Scattergeo(
            lon=storm_data['LON'], lat=storm_data['LAT'], mode='lines',
            name=f"{name} ({basin})",
            line=dict(width=1.5, color=color), hoverinfo="name"
        ))
    if typhoon_search:
        search_mask = typhoon_data['NAME'].str.contains(typhoon_search, case=False, na=False)
        if search_mask.any():
            for sid in typhoon_data[search_mask]['SID'].unique():
                storm_data = typhoon_data[typhoon_data['SID']==sid]
                fig.add_trace(go.Scattergeo(
                    lon=storm_data['LON'], lat=storm_data['LAT'], mode='lines+markers',
                    name=f"MATCHED: {storm_data['NAME'].iloc[0]}",
                    line=dict(width=3, color='yellow'),
                    marker=dict(size=5), hoverinfo="name"
                ))
    fig.update_layout(
        title=f"Typhoon Tracks ({start_year}-{start_month} to {end_year}-{end_month})",
        geo=dict(
            projection_type='natural earth',
            showland=True,
            showcoastlines=True,
            landcolor='rgb(243,243,243)',
            countrycolor='rgb(204,204,204)',
            coastlinecolor='rgb(204,204,204)',
            center=dict(lon=140, lat=20),
            projection_scale=3
        ),
        legend_title="Typhoons by ENSO Phase",
        showlegend=True,
        height=700
    )
    fig.add_annotation(
        x=0.02, y=0.98, xref="paper", yref="paper",
        text="Red: El Niño, Blue: La Nina, Green: Neutral",
        showarrow=False, align="left",
        bgcolor="rgba(255,255,255,0.8)"
    )
    return fig, f"Total typhoons displayed: {count}"

def get_wind_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
    """Get wind analysis with enhanced categorization"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
    filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
    if enso_phase != 'all':
        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
    
    fig = px.scatter(filtered_data, x='ONI', y='USA_WIND', color='Category',
                     hover_data=['NAME','Year','Category'],
                     title='Wind Speed vs ONI',
                     labels={'ONI':'ONI Value','USA_WIND':'Max Wind Speed (knots)'},
                     color_discrete_map=enhanced_color_map)
    
    if typhoon_search:
        mask = filtered_data['NAME'].str.contains(typhoon_search, case=False, na=False)
        if mask.any():
            fig.add_trace(go.Scatter(
                x=filtered_data.loc[mask,'ONI'], y=filtered_data.loc[mask,'USA_WIND'],
                mode='markers', marker=dict(size=10, color='red', symbol='star'),
                name=f'Matched: {typhoon_search}',
                text=filtered_data.loc[mask,'NAME']+' ('+filtered_data.loc[mask,'Year'].astype(str)+')'
            ))
    
    regression = perform_wind_regression(start_year, start_month, end_year, end_month)
    return fig, regression

def get_pressure_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
    """Get pressure analysis with enhanced categorization"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
    filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
    if enso_phase != 'all':
        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
    
    fig = px.scatter(filtered_data, x='ONI', y='USA_PRES', color='Category',
                     hover_data=['NAME','Year','Category'],
                     title='Pressure vs ONI',
                     labels={'ONI':'ONI Value','USA_PRES':'Min Pressure (hPa)'},
                     color_discrete_map=enhanced_color_map)
    
    if typhoon_search:
        mask = filtered_data['NAME'].str.contains(typhoon_search, case=False, na=False)
        if mask.any():
            fig.add_trace(go.Scatter(
                x=filtered_data.loc[mask,'ONI'], y=filtered_data.loc[mask,'USA_PRES'],
                mode='markers', marker=dict(size=10, color='red', symbol='star'),
                name=f'Matched: {typhoon_search}',
                text=filtered_data.loc[mask,'NAME']+' ('+filtered_data.loc[mask,'Year'].astype(str)+')'
            ))
    
    regression = perform_pressure_regression(start_year, start_month, end_year, end_month)
    return fig, regression

def get_longitude_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
    """Get longitude analysis"""
    start_date = datetime(start_year, start_month, 1)
    end_date = datetime(end_year, end_month, 28)
    filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
    filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
    if enso_phase != 'all':
        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
    
    fig = px.scatter(filtered_data, x='LON', y='ONI', hover_data=['NAME'],
                     title='Typhoon Generation Longitude vs ONI (All Years)')
    
    if len(filtered_data) > 1:
        X = np.array(filtered_data['LON']).reshape(-1,1)
        y = filtered_data['ONI']
        try:
            model = sm.OLS(y, sm.add_constant(X)).fit()
            y_pred = model.predict(sm.add_constant(X))
            fig.add_trace(go.Scatter(x=filtered_data['LON'], y=y_pred, mode='lines', name='Regression Line'))
            slope = model.params[1]
            slopes_text = f"All Years Slope: {slope:.4f}"
        except Exception as e:
            slopes_text = f"Regression Error: {e}"
    else:
        slopes_text = "Insufficient data for regression"
    
    regression = perform_longitude_regression(start_year, start_month, end_year, end_month)
    return fig, slopes_text, regression

def categorize_typhoon_by_standard(wind_speed, standard='atlantic'):
    """Categorize typhoon by standard with enhanced TD support - FIXED for matplotlib"""
    if pd.isna(wind_speed):
        return 'Tropical Depression', '#808080'
    
    if standard=='taiwan':
        wind_speed_ms = wind_speed * 0.514444
        if wind_speed_ms >= 51.0:
            return 'Strong Typhoon', '#FF0000'  # Red
        elif wind_speed_ms >= 33.7:
            return 'Medium Typhoon', '#FFA500'  # Orange
        elif wind_speed_ms >= 17.2:
            return 'Mild Typhoon', '#FFFF00'   # Yellow
        return 'Tropical Depression', '#808080'  # Gray
    else:
        if wind_speed >= 137:
            return 'C5 Super Typhoon', '#FF0000'      # Red
        elif wind_speed >= 113:
            return 'C4 Very Strong Typhoon', '#FFA500' # Orange
        elif wind_speed >= 96:
            return 'C3 Strong Typhoon', '#FFFF00'     # Yellow
        elif wind_speed >= 83:
            return 'C2 Typhoon', '#00FF00'            # Green
        elif wind_speed >= 64:
            return 'C1 Typhoon', '#00FFFF'            # Cyan
        elif wind_speed >= 34:
            return 'Tropical Storm', '#0000FF'        # Blue
        return 'Tropical Depression', '#808080'       # Gray

# -----------------------------
# ENHANCED: Animation Functions
# -----------------------------

def get_available_years(typhoon_data):
    """Get all available years including 2025 - with error handling"""
    try:
        if typhoon_data is None or typhoon_data.empty:
            return [str(year) for year in range(2000, 2026)]
            
        if 'ISO_TIME' in typhoon_data.columns:
            years = typhoon_data['ISO_TIME'].dt.year.dropna().unique()
        elif 'SEASON' in typhoon_data.columns:
            years = typhoon_data['SEASON'].dropna().unique()
        else:
            years = range(2000, 2026)  # Default range including 2025
        
        # Convert to strings and sort
        year_strings = sorted([str(int(year)) for year in years if not pd.isna(year)])
        
        # Ensure we have at least some years
        if not year_strings:
            return [str(year) for year in range(2000, 2026)]
            
        return year_strings
        
    except Exception as e:
        print(f"Error in get_available_years: {e}")
        return [str(year) for year in range(2000, 2026)]

def update_typhoon_options_enhanced(year, basin):
    """Enhanced typhoon options with TD support and 2025 data"""
    try:
        year = int(year)
        
        # Filter by year - handle both ISO_TIME and SEASON columns
        if 'ISO_TIME' in typhoon_data.columns:
            year_mask = typhoon_data['ISO_TIME'].dt.year == year
        elif 'SEASON' in typhoon_data.columns:
            year_mask = typhoon_data['SEASON'] == year
        else:
            # Fallback - try to extract year from SID or other fields
            year_mask = typhoon_data.index >= 0  # Include all data as fallback
        
        year_data = typhoon_data[year_mask].copy()
        
        # Filter by basin if specified
        if basin != "All Basins":
            basin_code = basin.split(' - ')[0] if ' - ' in basin else basin[:2]
            if 'SID' in year_data.columns:
                year_data = year_data[year_data['SID'].str.startswith(basin_code, na=False)]
            elif 'BASIN' in year_data.columns:
                year_data = year_data[year_data['BASIN'] == basin_code]
        
        if year_data.empty:
            return gr.update(choices=["No storms found"], value=None)
        
        # Get unique storms - include ALL intensities (including TD)
        storms = year_data.groupby('SID').agg({
            'NAME': 'first',
            'USA_WIND': 'max'
        }).reset_index()
        
        # Enhanced categorization including TD
        storms['category'] = storms['USA_WIND'].apply(categorize_typhoon_enhanced)
        
        # Create options with category information
        options = []
        for _, storm in storms.iterrows():
            name = storm['NAME'] if pd.notna(storm['NAME']) and storm['NAME'] != '' else 'UNNAMED'
            sid = storm['SID']
            category = storm['category']
            max_wind = storm['USA_WIND'] if pd.notna(storm['USA_WIND']) else 0
            
            option = f"{name} ({sid}) - {category} ({max_wind:.0f}kt)"
            options.append(option)
        
        if not options:
            return gr.update(choices=["No storms found"], value=None)
        
        return gr.update(choices=sorted(options), value=options[0])
        
    except Exception as e:
        print(f"Error in update_typhoon_options_enhanced: {e}")
        return gr.update(choices=["Error loading storms"], value=None)

def generate_enhanced_track_video(year, typhoon_selection, standard):
    """Enhanced track video generation with TD support and 2025 compatibility - FIXED color handling"""
    if not typhoon_selection or typhoon_selection == "No storms found":
        return None
    
    try:
        # Extract SID from selection
        sid = typhoon_selection.split('(')[1].split(')')[0]
        
        # Get storm data
        storm_df = typhoon_data[typhoon_data['SID'] == sid].copy()
        if storm_df.empty:
            print(f"No data found for storm {sid}")
            return None
        
        # Sort by time
        if 'ISO_TIME' in storm_df.columns:
            storm_df = storm_df.sort_values('ISO_TIME')
        
        # Extract data for animation
        lats = storm_df['LAT'].astype(float).values
        lons = storm_df['LON'].astype(float).values
        
        if 'USA_WIND' in storm_df.columns:
            winds = pd.to_numeric(storm_df['USA_WIND'], errors='coerce').fillna(0).values
        else:
            winds = np.full(len(lats), 30)  # Default TD strength
        
        # Enhanced metadata
        storm_name = storm_df['NAME'].iloc[0] if pd.notna(storm_df['NAME'].iloc[0]) else "UNNAMED"
        season = storm_df['SEASON'].iloc[0] if 'SEASON' in storm_df.columns else year
        
        print(f"Generating video for {storm_name} ({sid}) with {len(lats)} track points")
        
        # Create figure with enhanced map
        fig, ax = plt.subplots(figsize=(14, 8), subplot_kw={'projection': ccrs.PlateCarree()})
        
        # Enhanced map features
        ax.stock_img()
        ax.add_feature(cfeature.COASTLINE, linewidth=0.8)
        ax.add_feature(cfeature.BORDERS, linewidth=0.5)
        ax.add_feature(cfeature.OCEAN, color='lightblue', alpha=0.5)
        ax.add_feature(cfeature.LAND, color='lightgray', alpha=0.5)
        
        # Set extent based on track
        padding = 5
        ax.set_extent([
            min(lons) - padding, max(lons) + padding,
            min(lats) - padding, max(lats) + padding
        ])
        
        # Add gridlines
        gl = ax.gridlines(draw_labels=True, alpha=0.3)
        gl.top_labels = gl.right_labels = False
        
        # Title with enhanced info
        ax.set_title(f"{season} {storm_name} ({sid}) Track Animation", fontsize=16, fontweight='bold')
        
        # Animation elements
        line, = ax.plot([], [], 'b-', linewidth=3, alpha=0.7, label='Track')
        point, = ax.plot([], [], 'o', markersize=12)
        
        # Enhanced info display
        info_box = ax.text(0.02, 0.98, '', transform=ax.transAxes, 
                          fontsize=11, verticalalignment='top',
                          bbox=dict(boxstyle="round,pad=0.5", facecolor='white', alpha=0.9))
        
        # Color legend with TD support - FIXED
        legend_elements = []
        for category in ['Tropical Depression', 'Tropical Storm', 'C1 Typhoon', 'C2 Typhoon', 
                        'C3 Strong Typhoon', 'C4 Very Strong Typhoon', 'C5 Super Typhoon']:
            if category in matplotlib_color_map:
                color = get_matplotlib_color(category)
                legend_elements.append(plt.Line2D([0], [0], marker='o', color='w',
                                                markerfacecolor=color, markersize=8, label=category))
        
        ax.legend(handles=legend_elements, loc='upper right', fontsize=9)
        
        def animate(frame):
            try:
                if frame >= len(lats):
                    return line, point, info_box
                
                # Update track line
                line.set_data(lons[:frame+1], lats[:frame+1])
                
                # Update current position
                current_wind = winds[frame]
                category = categorize_typhoon_enhanced(current_wind)
                color = get_matplotlib_color(category)  # FIXED: Use matplotlib-compatible color
                
                # Debug print for first few frames
                if frame < 3:
                    print(f"Frame {frame}: Wind={current_wind:.1f}kt, Category={category}, Color={color}")
                
                point.set_data([lons[frame]], [lats[frame]])
                point.set_color(color)
                point.set_markersize(8 + current_wind/10)  # Size based on intensity
                
                # Enhanced info display
                if 'ISO_TIME' in storm_df.columns and frame < len(storm_df):
                    current_time = storm_df.iloc[frame]['ISO_TIME']
                    time_str = current_time.strftime('%Y-%m-%d %H:%M UTC') if pd.notna(current_time) else 'Unknown'
                else:
                    time_str = f"Step {frame+1}"
                
                info_text = (
                    f"Storm: {storm_name}\n"
                    f"Time: {time_str}\n"
                    f"Position: {lats[frame]:.1f}°N, {lons[frame]:.1f}°E\n"
                    f"Max Wind: {current_wind:.0f} kt\n"
                    f"Category: {category}\n"
                    f"Frame: {frame+1}/{len(lats)}"
                )
                info_box.set_text(info_text)
                
                return line, point, info_box
                
            except Exception as e:
                print(f"Error in animate frame {frame}: {e}")
                return line, point, info_box
        
        # Create animation
        anim = animation.FuncAnimation(
            fig, animate, frames=len(lats),
            interval=300, blit=False, repeat=True
        )
        
        # Save animation
        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4', 
                                              dir=tempfile.gettempdir())
        
        # Enhanced writer settings
        writer = animation.FFMpegWriter(
            fps=4, bitrate=2000, codec='libx264',
            extra_args=['-pix_fmt', 'yuv420p']  # Better compatibility
        )
        
        print(f"Saving animation to {temp_file.name}")
        anim.save(temp_file.name, writer=writer, dpi=100)
        plt.close(fig)
        
        print(f"Video generated successfully: {temp_file.name}")
        return temp_file.name
        
    except Exception as e:
        print(f"Error generating video: {e}")
        import traceback
        traceback.print_exc()
        return None

# Simplified wrapper for backward compatibility - FIXED
def simplified_track_video(year, basin, typhoon, standard):
    """Simplified track video function with fixed color handling"""
    if not typhoon:
        return None
    return generate_enhanced_track_video(year, typhoon, standard)

# -----------------------------
# Load & Process Data
# -----------------------------

# Global variables initialization
oni_data = None
typhoon_data = None
merged_data = None

def initialize_data():
    """Initialize all data safely"""
    global oni_data, typhoon_data, merged_data
    try:
        logging.info("Starting data loading process...")
        update_oni_data()
        oni_data, typhoon_data = load_data_fixed(ONI_DATA_PATH, TYPHOON_DATA_PATH)
        
        if oni_data is not None and typhoon_data is not None:
            oni_long = process_oni_data(oni_data)
            typhoon_max = process_typhoon_data(typhoon_data)
            merged_data = merge_data(oni_long, typhoon_max)
            logging.info("Data loading complete.")
        else:
            logging.error("Failed to load required data")
            # Create minimal fallback data
            oni_data = pd.DataFrame({'Year': [2000], 'Jan': [0], 'Feb': [0], 'Mar': [0], 'Apr': [0], 
                                   'May': [0], 'Jun': [0], 'Jul': [0], 'Aug': [0], 'Sep': [0], 
                                   'Oct': [0], 'Nov': [0], 'Dec': [0]})
            typhoon_data = create_fallback_typhoon_data()
            oni_long = process_oni_data(oni_data)
            typhoon_max = process_typhoon_data(typhoon_data)
            merged_data = merge_data(oni_long, typhoon_max)
    except Exception as e:
        logging.error(f"Error during data initialization: {e}")
        # Create minimal fallback data
        oni_data = pd.DataFrame({'Year': [2000], 'Jan': [0], 'Feb': [0], 'Mar': [0], 'Apr': [0], 
                               'May': [0], 'Jun': [0], 'Jul': [0], 'Aug': [0], 'Sep': [0], 
                               'Oct': [0], 'Nov': [0], 'Dec': [0]})
        typhoon_data = create_fallback_typhoon_data()
        oni_long = process_oni_data(oni_data)
        typhoon_max = process_typhoon_data(typhoon_data)
        merged_data = merge_data(oni_long, typhoon_max)

# Initialize data
initialize_data()

# -----------------------------
# ENHANCED: Gradio Interface
# -----------------------------

def create_interface():
    """Create the enhanced Gradio interface with robust error handling"""
    try:
        # Ensure data is available
        if oni_data is None or typhoon_data is None or merged_data is None:
            logging.warning("Data not properly loaded, creating minimal interface")
            return create_minimal_fallback_interface()
            
        # Get safe data statistics
        try:
            total_storms = len(typhoon_data['SID'].unique()) if 'SID' in typhoon_data.columns else 0
            total_records = len(typhoon_data)
            available_years = get_available_years(typhoon_data)
            year_range_display = f"{available_years[0]} - {available_years[-1]}" if available_years else "Unknown"
        except Exception as e:
            logging.error(f"Error getting data statistics: {e}")
            total_storms = 0
            total_records = 0
            year_range_display = "Unknown"
            available_years = [str(year) for year in range(2000, 2026)]

        with gr.Blocks(title="Enhanced Typhoon Analysis Platform", theme=gr.themes.Soft()) as demo:
            gr.Markdown("# Enhanced Typhoon Analysis Platform")
            gr.Markdown("Advanced ML clustering, CNN predictions, and comprehensive tropical cyclone analysis including Tropical Depressions")
            
            with gr.Tab("Overview"):
                overview_text = f"""
                ## Welcome to the Enhanced Typhoon Analysis Dashboard

                This dashboard provides comprehensive analysis of typhoon data in relation to ENSO phases with advanced machine learning capabilities.

                ### Enhanced Features:
                - Advanced ML Clustering: UMAP/t-SNE storm pattern analysis with route visualization
                - Optional CNN Predictions: Deep learning intensity forecasting
                - Complete TD Support: Now includes Tropical Depressions (< 34 kt)
                - 2025 Data Ready: Real-time compatibility with current year data
                - Enhanced Animations: High-quality storm track visualizations
                
                ### Data Status:
                - ONI Data: {len(oni_data)} years loaded
                - Typhoon Data: {total_records} records loaded
                - Merged Data: {len(merged_data)} typhoons with ONI values
                - Available Years: {year_range_display}
                
                ### Technical Capabilities:
                - UMAP Clustering: {"Available" if UMAP_AVAILABLE else "Limited to t-SNE/PCA"}
                - AI Predictions: {"Deep Learning" if CNN_AVAILABLE else "Physics-based"}
                - Enhanced Categorization: Tropical Depression to Super Typhoon
                - Platform Compatibility: Optimized for Hugging Face Spaces
                """
                gr.Markdown(overview_text)

            with gr.Tab("Advanced ML Clustering with Routes"):
                gr.Markdown("## Storm Pattern Analysis using UMAP/t-SNE with Route Visualization")
                gr.Markdown("**This tab shows both the dimensional clustering analysis AND the actual storm tracks colored by cluster**")
                
                with gr.Row():
                    reduction_method = gr.Dropdown(
                        choices=['UMAP', 't-SNE', 'PCA'], 
                        value='UMAP' if UMAP_AVAILABLE else 't-SNE',
                        label="Dimensionality Reduction Method"
                    )
                    show_routes = gr.Checkbox(
                        label="Show Storm Routes on Map",
                        value=True,
                        info="Display actual storm tracks colored by cluster"
                    )
                
                analyze_clusters_btn = gr.Button("Analyze Storm Clusters & Routes", variant="primary")
                
                with gr.Row():
                    cluster_plot = gr.Plot(label="Storm Clustering with Route Visualization")
                
                with gr.Row():
                    cluster_stats = gr.Textbox(label="Detailed Cluster Statistics", lines=15, max_lines=20)
                
                def run_advanced_clustering_analysis(method, show_routes):
                    try:
                        # Extract features for clustering
                        storm_features = extract_storm_features(typhoon_data)
                        fig, stats, _ = create_advanced_clustering_visualization(storm_features, typhoon_data, method.lower(), show_routes)
                        return fig, stats
                    except Exception as e:
                        import traceback
                        error_details = traceback.format_exc()
                        return None, f"Error: {str(e)}\n\nDetails:\n{error_details}"
                
                analyze_clusters_btn.click(
                    fn=run_advanced_clustering_analysis,
                    inputs=[reduction_method, show_routes],
                    outputs=[cluster_plot, cluster_stats]
                )
                
                cluster_info_text = """
                ### Advanced Clustering Features:
                - Multi-dimensional Analysis: Uses 15+ storm characteristics including intensity, track shape, genesis location
                - Route Visualization: Shows actual storm tracks colored by cluster membership
                - DBSCAN Clustering: Automatically finds natural groupings without predefined cluster count
                - Comprehensive Stats: Detailed cluster analysis including intensity, pressure, track length, curvature
                - Interactive: Hover over points to see storm details, zoom and pan the route map
                
                ### How to Interpret:
                - Left Plot: Each dot is a storm positioned by similarity (close = similar characteristics)
                - Right Plot: Actual geographic storm tracks, colored by which cluster they belong to
                - Cluster Colors: Each cluster gets a unique color to identify similar storm patterns
                - Noise Points: Gray points represent storms that don't fit clear patterns
                """
                gr.Markdown(cluster_info_text)

            with gr.Tab("Intensity Prediction"):
                gr.Markdown("## AI-Powered Storm Intensity Forecasting")
                
                if CNN_AVAILABLE:
                    gr.Markdown("Deep Learning models available - TensorFlow loaded successfully")
                    method_description = "Using Convolutional Neural Networks for advanced intensity prediction"
                else:
                    gr.Markdown("Physics-based models available - Using climatological relationships")
                    gr.Markdown("*Install TensorFlow for deep learning features: `pip install tensorflow-cpu`*")
                    method_description = "Using established meteorological relationships and climatology"
                
                gr.Markdown(f"**Current Method**: {method_description}")
                
                with gr.Row():
                    cnn_lat = gr.Number(label="Latitude", value=20.0, info="Storm center latitude (-90 to 90)")
                    cnn_lon = gr.Number(label="Longitude", value=140.0, info="Storm center longitude (-180 to 180)")
                    cnn_month = gr.Slider(1, 12, label="Month", value=9, info="Month of year (1=Jan, 12=Dec)")
                    cnn_oni = gr.Number(label="ONI Value", value=0.0, info="Current ENSO index (-3 to 3)")
                
                predict_btn = gr.Button("Predict Storm Intensity", variant="primary")
                
                with gr.Row():
                    intensity_output = gr.Number(label="Predicted Max Wind (kt)")
                    confidence_output = gr.Textbox(label="Model Output & Confidence")
                
                predict_btn.click(
                    fn=simulate_cnn_prediction,
                    inputs=[cnn_lat, cnn_lon, cnn_month, cnn_oni],
                    outputs=[intensity_output, confidence_output]
                )
                
                prediction_info_text = """
                ### Prediction Features:
                - Environmental Analysis: Considers ENSO, latitude, seasonality
                - Real-time Capable: Predictions in milliseconds
                - Confidence Scoring: Uncertainty quantification included
                - Robust Fallbacks: Works with or without deep learning libraries
                
                ### Interpretation Guide:
                - 25-33 kt: Tropical Depression (TD)
                - 34-63 kt: Tropical Storm (TS) 
                - 64+ kt: Typhoon categories (C1-C5)
                - 100+ kt: Major typhoon (C3+)
                """
                gr.Markdown(prediction_info_text)

            with gr.Tab("Track Visualization"):
                with gr.Row():
                    start_year = gr.Number(label="Start Year", value=2020)
                    start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
                    end_year = gr.Number(label="End Year", value=2025)
                    end_month = gr.Dropdown(label="End Month", choices=list(range(1, 13)), value=6)
                    enso_phase = gr.Dropdown(label="ENSO Phase", choices=['all', 'El Nino', 'La Nina', 'Neutral'], value='all')
                    typhoon_search = gr.Textbox(label="Typhoon Search")
                analyze_btn = gr.Button("Generate Tracks")
                tracks_plot = gr.Plot()
                typhoon_count = gr.Textbox(label="Number of Typhoons Displayed")
                analyze_btn.click(
                    fn=get_full_tracks,
                    inputs=[start_year, start_month, end_year, end_month, enso_phase, typhoon_search],
                    outputs=[tracks_plot, typhoon_count]
                )
            
            with gr.Tab("Wind Analysis"):
                with gr.Row():
                    wind_start_year = gr.Number(label="Start Year", value=2020)
                    wind_start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
                    wind_end_year = gr.Number(label="End Year", value=2024)
                    wind_end_month = gr.Dropdown(label="End Month", choices=list(range(1, 13)), value=6)
                    wind_enso_phase = gr.Dropdown(label="ENSO Phase", choices=['all', 'El Nino', 'La Nina', 'Neutral'], value='all')
                    wind_typhoon_search = gr.Textbox(label="Typhoon Search")
                wind_analyze_btn = gr.Button("Generate Wind Analysis")
                wind_scatter = gr.Plot()
                wind_regression_results = gr.Textbox(label="Wind Regression Results")
                wind_analyze_btn.click(
                    fn=get_wind_analysis,
                    inputs=[wind_start_year, wind_start_month, wind_end_year, wind_end_month, wind_enso_phase, wind_typhoon_search],
                    outputs=[wind_scatter, wind_regression_results]
                )
            
            with gr.Tab("Pressure Analysis"):
                with gr.Row():
                    pressure_start_year = gr.Number(label="Start Year", value=2020)
                    pressure_start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
                    pressure_end_year = gr.Number(label="End Year", value=2024)
                    pressure_end_month = gr.Dropdown(label="End Month", choices=list(range(1, 13)), value=6)
                    pressure_enso_phase = gr.Dropdown(label="ENSO Phase", choices=['all', 'El Nino', 'La Nina', 'Neutral'], value='all')
                    pressure_typhoon_search = gr.Textbox(label="Typhoon Search")
                pressure_analyze_btn = gr.Button("Generate Pressure Analysis")
                pressure_scatter = gr.Plot()
                pressure_regression_results = gr.Textbox(label="Pressure Regression Results")
                pressure_analyze_btn.click(
                    fn=get_pressure_analysis,
                    inputs=[pressure_start_year, pressure_start_month, pressure_end_year, pressure_end_month, pressure_enso_phase, pressure_typhoon_search],
                    outputs=[pressure_scatter, pressure_regression_results]
                )
            
            with gr.Tab("Longitude Analysis"):
                with gr.Row():
                    lon_start_year = gr.Number(label="Start Year", value=2020)
                    lon_start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
                    lon_end_year = gr.Number(label="End Year", value=2020)
                    lon_end_month = gr.Dropdown(label="End Month", choices=list(range(1, 13)), value=6)
                    lon_enso_phase = gr.Dropdown(label="ENSO Phase", choices=['all', 'El Nino', 'La Nina', 'Neutral'], value='all')
                    lon_typhoon_search = gr.Textbox(label="Typhoon Search (Optional)")
                lon_analyze_btn = gr.Button("Generate Longitude Analysis")
                regression_plot = gr.Plot()
                slopes_text = gr.Textbox(label="Regression Slopes")
                lon_regression_results = gr.Textbox(label="Longitude Regression Results")
                lon_analyze_btn.click(
                    fn=get_longitude_analysis,
                    inputs=[lon_start_year, lon_start_month, lon_end_year, lon_end_month, lon_enso_phase, lon_typhoon_search],
                    outputs=[regression_plot, slopes_text, lon_regression_results]
                )
            
            with gr.Tab("Enhanced Track Animation"):
                gr.Markdown("## High-Quality Storm Track Visualization (All Categories Including TD)")
                
                with gr.Row():
                    year_dropdown = gr.Dropdown(
                        label="Year",
                        choices=available_years,
                        value=available_years[-1] if available_years else "2024"
                    )
                    basin_dropdown = gr.Dropdown(
                        label="Basin",
                        choices=["All Basins", "WP - Western Pacific", "EP - Eastern Pacific", "NA - North Atlantic"],
                        value="All Basins"
                    )
                
                with gr.Row():
                    typhoon_dropdown = gr.Dropdown(label="Storm Selection (All Categories Including TD)")
                    standard_dropdown = gr.Dropdown(
                        label="Classification Standard",
                        choices=['atlantic', 'taiwan'], 
                        value='atlantic'
                    )
                
                generate_video_btn = gr.Button("Generate Enhanced Animation", variant="primary")
                video_output = gr.Video(label="Storm Track Animation")
                
                # Update storm options when year or basin changes
                for input_comp in [year_dropdown, basin_dropdown]:
                    input_comp.change(
                        fn=update_typhoon_options_enhanced,
                        inputs=[year_dropdown, basin_dropdown],
                        outputs=[typhoon_dropdown]
                    )
                
                # Generate video
                generate_video_btn.click(
                    fn=generate_enhanced_track_video,
                    inputs=[year_dropdown, typhoon_dropdown, standard_dropdown],
                    outputs=[video_output]
                )
                
                animation_info_text = """
                ### Enhanced Animation Features:
                - Full TD Support: Now displays Tropical Depressions (< 34 kt) in gray
                - 2025 Compatibility: Complete support for current year data
                - Enhanced Maps: Better cartographic projections with terrain features
                - Smart Scaling: Storm symbols scale dynamically with intensity
                - Real-time Info: Live position, time, and meteorological data display
                - Professional Styling: Publication-quality animations with proper legends
                - Optimized Export: Fast rendering with web-compatible video formats
                """
                gr.Markdown(animation_info_text)

            with gr.Tab("Data Statistics & Insights"):
                gr.Markdown("## Comprehensive Dataset Analysis")
                
                # Create enhanced data summary
                try:
                    if len(typhoon_data) > 0:
                        # Storm category distribution
                        storm_cats = typhoon_data.groupby('SID')['USA_WIND'].max().apply(categorize_typhoon_enhanced)
                        cat_counts = storm_cats.value_counts()
                        
                        # Create distribution chart with enhanced colors
                        fig_dist = px.bar(
                            x=cat_counts.index,
                            y=cat_counts.values,
                            title="Storm Intensity Distribution (Including Tropical Depressions)",
                            labels={'x': 'Category', 'y': 'Number of Storms'},
                            color=cat_counts.index,
                            color_discrete_map=enhanced_color_map
                        )
                        
                        # Seasonal distribution
                        if 'ISO_TIME' in typhoon_data.columns:
                            seasonal_data = typhoon_data.copy()
                            seasonal_data['Month'] = seasonal_data['ISO_TIME'].dt.month
                            monthly_counts = seasonal_data.groupby(['Month', 'SID']).size().groupby('Month').size()
                            
                            fig_seasonal = px.bar(
                                x=monthly_counts.index,
                                y=monthly_counts.values,
                                title="Seasonal Storm Distribution",
                                labels={'x': 'Month', 'y': 'Number of Storms'},
                                color=monthly_counts.values,
                                color_continuous_scale='Viridis'
                            )
                        else:
                            fig_seasonal = None
                        
                        # Basin distribution
                        if 'SID' in typhoon_data.columns:
                            basin_data = typhoon_data['SID'].str[:2].value_counts()
                            fig_basin = px.pie(
                                values=basin_data.values,
                                names=basin_data.index,
                                title="Distribution by Basin"
                            )
                        else:
                            fig_basin = None
                        
                        with gr.Row():
                            gr.Plot(value=fig_dist)
                        
                        if fig_seasonal:
                            with gr.Row():
                                gr.Plot(value=fig_seasonal)
                        
                        if fig_basin:
                            with gr.Row():
                                gr.Plot(value=fig_basin)
                                
                except Exception as e:
                    gr.Markdown(f"Visualization error: {str(e)}")
                
                # Enhanced statistics - FIXED formatting
                total_storms = len(typhoon_data['SID'].unique()) if 'SID' in typhoon_data.columns else 0
                total_records = len(typhoon_data)
                
                if 'SEASON' in typhoon_data.columns:
                    try:
                        min_year = int(typhoon_data['SEASON'].min())
                        max_year = int(typhoon_data['SEASON'].max())
                        year_range = f"{min_year}-{max_year}"
                        years_covered = typhoon_data['SEASON'].nunique()
                    except (ValueError, TypeError):
                        year_range = "Unknown"
                        years_covered = 0
                else:
                    year_range = "Unknown"
                    years_covered = 0
                
                if 'SID' in typhoon_data.columns:
                    try:
                        basins_available = ', '.join(sorted(typhoon_data['SID'].str[:2].unique()))
                        avg_storms_per_year = total_storms / max(years_covered, 1)
                    except Exception:
                        basins_available = "Unknown"
                        avg_storms_per_year = 0
                else:
                    basins_available = "Unknown"
                    avg_storms_per_year = 0
                
                # TD specific statistics
                try:
                    if 'USA_WIND' in typhoon_data.columns:
                        td_storms = len(typhoon_data[typhoon_data['USA_WIND'] < 34]['SID'].unique())
                        ts_storms = len(typhoon_data[(typhoon_data['USA_WIND'] >= 34) & (typhoon_data['USA_WIND'] < 64)]['SID'].unique())
                        typhoon_storms = len(typhoon_data[typhoon_data['USA_WIND'] >= 64]['SID'].unique())
                        td_percentage = (td_storms / max(total_storms, 1)) * 100
                    else:
                        td_storms = ts_storms = typhoon_storms = 0
                        td_percentage = 0
                except Exception as e:
                    print(f"Error calculating TD statistics: {e}")
                    td_storms = ts_storms = typhoon_storms = 0
                    td_percentage = 0
                
                # Create statistics text safely
                stats_text = f"""
                ### Enhanced Dataset Summary:
                - Total Unique Storms: {total_storms:,}
                - Total Track Records: {total_records:,}  
                - Year Range: {year_range} ({years_covered} years)
                - Basins Available: {basins_available}
                - Average Storms/Year: {avg_storms_per_year:.1f}
                
                ### Storm Category Breakdown:
                - Tropical Depressions: {td_storms:,} storms ({td_percentage:.1f}%)
                - Tropical Storms: {ts_storms:,} storms
                - Typhoons (C1-C5): {typhoon_storms:,} storms
                
                ### New Platform Capabilities:
                - Complete TD Analysis - First platform to include comprehensive TD tracking
                - Advanced ML Clustering - DBSCAN pattern recognition with route visualization  
                - Real-time Predictions - Physics-based and optional CNN intensity forecasting
                - 2025 Data Ready - Full compatibility with current season data
                - Enhanced Animations - Professional-quality storm track videos
                - Multi-basin Analysis - Comprehensive Pacific and Atlantic coverage
                
                ### Research Applications:
                - Climate change impact studies
                - Seasonal forecasting research
                - Storm pattern classification
                - ENSO-typhoon relationship analysis
                - Intensity prediction model development
                """
                gr.Markdown(stats_text)

        return demo
    except Exception as e:
        logging.error(f"Error creating Gradio interface: {e}")
        import traceback
        traceback.print_exc()
        # Create a minimal fallback interface
        return create_minimal_fallback_interface()

def create_minimal_fallback_interface():
    """Create a minimal fallback interface when main interface fails"""
    with gr.Blocks() as demo:
        gr.Markdown("# Enhanced Typhoon Analysis Platform")
        gr.Markdown("**Notice**: Loading with minimal interface due to data issues.")
        
        with gr.Tab("Status"):
            gr.Markdown("""
            ## Platform Status
            
            The application is running but encountered issues loading the full interface.
            This could be due to:
            - Data loading problems
            - Missing dependencies
            - Configuration issues
            
            ### Available Features:
            - Basic interface is functional
            - Error logs are being generated
            - System is ready for debugging
            
            ### Next Steps:
            1. Check the console logs for detailed error information
            2. Verify all required data files are accessible
            3. Ensure all dependencies are properly installed
            4. Try restarting the application
            """)
        
        with gr.Tab("Debug"):
            gr.Markdown("## Debug Information")
            
            def get_debug_info():
                debug_text = f"""
                Python Environment:
                - Working Directory: {os.getcwd()}
                - Data Path: {DATA_PATH}
                - UMAP Available: {UMAP_AVAILABLE}
                - CNN Available: {CNN_AVAILABLE}
                
                Data Status:
                - ONI Data: {'Loaded' if oni_data is not None else 'Failed'}
                - Typhoon Data: {'Loaded' if typhoon_data is not None else 'Failed'}
                - Merged Data: {'Loaded' if merged_data is not None else 'Failed'}
                
                File Checks:
                - ONI Path Exists: {os.path.exists(ONI_DATA_PATH)}
                - Typhoon Path Exists: {os.path.exists(TYPHOON_DATA_PATH)}
                """
                return debug_text
            
            debug_btn = gr.Button("Get Debug Info")
            debug_output = gr.Textbox(label="Debug Information", lines=15)
            debug_btn.click(fn=get_debug_info, outputs=debug_output)
    
    return demo

# -----------------------------
# Color Test Functions (Optional)
# -----------------------------

def test_color_conversion():
    """Test color conversion functions"""
    print("Testing color conversion...")
    
    # Test all categories
    test_winds = [25, 40, 70, 85, 100, 120, 150]  # TD, TS, C1, C2, C3, C4, C5
    
    for wind in test_winds:
        category = categorize_typhoon_enhanced(wind)
        plotly_color = enhanced_color_map.get(category, 'rgb(128,128,128)')
        matplotlib_color = get_matplotlib_color(category)
        
        print(f"Wind: {wind:3d}kt -> {category:20s} -> Plotly: {plotly_color:15s} -> Matplotlib: {matplotlib_color}")
    
    print("Color conversion test complete!")

def test_rgb_conversion():
    """Test RGB string to hex conversion"""
    test_colors = [
        'rgb(128, 128, 128)',
        'rgb(255, 0, 0)',
        'rgb(0, 255, 0)',
        'rgb(0, 0, 255)'
    ]
    
    print("Testing RGB to hex conversion...")
    for rgb_str in test_colors:
        hex_color = rgb_string_to_hex(rgb_str)
        print(f"{rgb_str:20s} -> {hex_color}")
    
    print("RGB conversion test complete!")

# Create and launch the interface
demo = create_interface()

if __name__ == "__main__":
    demo.launch()