app.py

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
import tropycal.tracks as tracks
import pickle
import requests
import os
import argparse
from datetime import datetime
import statsmodels.api as sm
import shutil
import tempfile
import csv
from collections import defaultdict
import filecmp
from sklearn.manifold import TSNE
from sklearn.cluster import DBSCAN
from scipy.interpolate import interp1d

# Command-line argument parsing
parser = argparse.ArgumentParser(description='Typhoon Analysis Dashboard')
parser.add_argument('--data_path', type=str, default=os.getcwd(), help='Path to the data directory')
args = parser.parse_args()
DATA_PATH = args.data_path

ONI_DATA_PATH = os.path.join(DATA_PATH, 'oni_data.csv')
TYPHOON_DATA_PATH = os.path.join(DATA_PATH, 'processed_typhoon_data.csv')
LOCAL_iBtrace_PATH = os.path.join(DATA_PATH, 'ibtracs.WP.list.v04r01.csv')
iBtrace_uri = 'https://www.ncei.noaa.gov/data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r01/access/csv/ibtracs.WP.list.v04r01.csv'
CACHE_FILE = 'ibtracs_cache.pkl'
CACHE_EXPIRY_DAYS = 1

# Color maps for Plotly (RGB)
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)'
}

# Classification standards with distinct colors for Matplotlib
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'}
}

# Season months mapping
season_months = {
    'all': list(range(1, 13)),
    'summer': [6, 7, 8],
    'winter': [12, 1, 2]
}

# Regions for duration calculations
regions = {
    "Taiwan Land": {"lat_min": 21.8, "lat_max": 25.3, "lon_min": 119.5, "lon_max": 122.1},
    "Taiwan Sea": {"lat_min": 19, "lat_max": 28, "lon_min": 117, "lon_max": 125},
    "Japan": {"lat_min": 20, "lat_max": 45, "lon_min": 120, "lon_max": 150},
    "China": {"lat_min": 18, "lat_max": 53, "lon_min": 73, "lon_max": 135},
    "Hong Kong": {"lat_min": 21.5, "lat_max": 23, "lon_min": 113, "lon_max": 115},
    "Philippines": {"lat_min": 5, "lat_max": 21, "lon_min": 115, "lon_max": 130}
}

# Data loading and preprocessing functions
def download_oni_file(url, filename):
    response = requests.get(url)
    response.raise_for_status()
    with open(filename, 'wb') as f:
        f.write(response.content)
    return True

def convert_oni_ascii_to_csv(input_file, output_file):
    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}
    with open(input_file, 'r') as f:
        lines = f.readlines()[1:]
        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
    with open(output_file, 'w', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(['Year', 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])
        for year in sorted(data.keys()):
            writer.writerow([year] + data[year])

def update_oni_data():
    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
    if download_oni_file(url, temp_file):
        if not os.path.exists(input_file) or not filecmp.cmp(temp_file, input_file):
            os.replace(temp_file, input_file)
            convert_oni_ascii_to_csv(input_file, output_file)
        else:
            os.remove(temp_file)

def load_ibtracs_data():
    if os.path.exists(CACHE_FILE) and (datetime.now() - datetime.fromtimestamp(os.path.getmtime(CACHE_FILE))).days < CACHE_EXPIRY_DAYS:
        with open(CACHE_FILE, 'rb') as f:
            return pickle.load(f)
    if os.path.exists(LOCAL_iBtrace_PATH):
        ibtracs = tracks.TrackDataset(basin='west_pacific', source='ibtracs', ibtracs_url=LOCAL_iBtrace_PATH)
    else:
        response = requests.get(iBtrace_uri)
        response.raise_for_status()
        with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.csv') as temp_file:
            temp_file.write(response.text)
            shutil.move(temp_file.name, LOCAL_iBtrace_PATH)
        ibtracs = tracks.TrackDataset(basin='west_pacific', source='ibtracs', ibtracs_url=LOCAL_iBtrace_PATH)
    with open(CACHE_FILE, 'wb') as f:
        pickle.dump(ibtracs, f)
    return ibtracs

def convert_typhoondata(input_file, output_file):
    with open(input_file, 'r') as infile:
        next(infile); next(infile)
        reader = csv.reader(infile)
        sid_data = defaultdict(list)
        for row in reader:
            if row:
                sid = row[0]
                sid_data[sid].append((row, row[6]))
    with open(output_file, 'w', newline='') as outfile:
        fieldnames = ['SID', 'ISO_TIME', 'LAT', 'LON', 'SEASON', 'NAME', 'WMO_WIND', 'WMO_PRES', 'USA_WIND', 'USA_PRES', 'START_DATE', 'END_DATE']
        writer = csv.DictWriter(outfile, fieldnames=fieldnames)
        writer.writeheader()
        for sid, data in sid_data.items():
            start_date = min(data, key=lambda x: x[1])[1]
            end_date = max(data, key=lambda x: x[1])[1]
            for row, iso_time in data:
                writer.writerow({
                    'SID': row[0], 'ISO_TIME': iso_time, 'LAT': row[8], 'LON': row[9], 'SEASON': row[1], 'NAME': row[5],
                    'WMO_WIND': row[10].strip() or ' ', 'WMO_PRES': row[11].strip() or ' ',
                    'USA_WIND': row[23].strip() or ' ', 'USA_PRES': row[24].strip() or ' ',
                    'START_DATE': start_date, 'END_DATE': end_date
                })

def load_data(oni_path, typhoon_path):
    oni_data = pd.read_csv(oni_path)
    typhoon_data = pd.read_csv(typhoon_path, low_memory=False)
    typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
    typhoon_data = typhoon_data.dropna(subset=['ISO_TIME'])
    return oni_data, typhoon_data

def process_oni_data(oni_data):
    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):
    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')
    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()
    typhoon_max['Month'] = typhoon_max['ISO_TIME'].dt.strftime('%m')
    typhoon_max['Year'] = typhoon_max['ISO_TIME'].dt.year
    typhoon_max['Category'] = typhoon_max['USA_WIND'].apply(categorize_typhoon)
    return typhoon_max

def merge_data(oni_long, typhoon_max):
    return pd.merge(typhoon_max, oni_long, on=['Year', 'Month'])

def categorize_typhoon(wind_speed):
    wind_speed_kt = wind_speed
    if wind_speed_kt >= 137:
        return 'C5 Super Typhoon'
    elif wind_speed_kt >= 113:
        return 'C4 Very Strong Typhoon'
    elif wind_speed_kt >= 96:
        return 'C3 Strong Typhoon'
    elif wind_speed_kt >= 83:
        return 'C2 Typhoon'
    elif wind_speed_kt >= 64:
        return 'C1 Typhoon'
    elif wind_speed_kt >= 34:
        return 'Tropical Storm'
    else:
        return 'Tropical Depression'

def classify_enso_phases(oni_value):
    if isinstance(oni_value, pd.Series):
        oni_value = oni_value.iloc[0]
    if oni_value >= 0.5:
        return 'El Nino'
    elif oni_value <= -0.5:
        return 'La Nina'
    else:
        return 'Neutral'

# Load data globally
update_oni_data()
ibtracs = load_ibtracs_data()
convert_typhoondata(LOCAL_iBtrace_PATH, TYPHOON_DATA_PATH)
oni_data, typhoon_data = load_data(ONI_DATA_PATH, TYPHOON_DATA_PATH)
oni_long = process_oni_data(oni_data)
typhoon_max = process_typhoon_data(typhoon_data)
merged_data = merge_data(oni_long, typhoon_max)

# Main analysis functions (using Plotly)
def generate_typhoon_tracks(filtered_data, typhoon_search):
    fig = go.Figure()
    for sid in filtered_data['SID'].unique():
        storm_data = filtered_data[filtered_data['SID'] == sid]
        color = {'El Nino': 'red', 'La Nina': 'blue', 'Neutral': 'green'}[storm_data['ENSO_Phase'].iloc[0]]
        fig.add_trace(go.Scattergeo(
            lon=storm_data['LON'], lat=storm_data['LAT'], mode='lines',
            name=storm_data['NAME'].iloc[0], line=dict(width=2, color=color)
        ))
    if typhoon_search:
        mask = filtered_data['NAME'].str.contains(typhoon_search, case=False, na=False)
        if mask.any():
            storm_data = filtered_data[mask]
            fig.add_trace(go.Scattergeo(
                lon=storm_data['LON'], lat=storm_data['LAT'], mode='lines',
                name=f'Matched: {typhoon_search}', line=dict(width=5, color='yellow')
            ))
    fig.update_layout(
        title='Typhoon Tracks',
        geo=dict(projection_type='natural earth', showland=True),
        height=700
    )
    return fig

def generate_wind_oni_scatter(filtered_data, typhoon_search):
    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=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) + ')'
            ))
    return fig

def generate_pressure_oni_scatter(filtered_data, typhoon_search):
    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=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) + ')'
            ))
    return fig

def generate_regression_analysis(filtered_data):
    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']
        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}"
    else:
        slopes_text = "Insufficient data for regression"
    return fig, slopes_text

def generate_main_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
    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)
    ]
    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()]
    
    tracks_fig = generate_typhoon_tracks(filtered_data, typhoon_search)
    wind_scatter = generate_wind_oni_scatter(filtered_data, typhoon_search)
    pressure_scatter = generate_pressure_oni_scatter(filtered_data, typhoon_search)
    regression_fig, slopes_text = generate_regression_analysis(filtered_data)
    
    return tracks_fig, wind_scatter, pressure_scatter, regression_fig, slopes_text

# Video animation function with fixed sidebar
def categorize_typhoon_by_standard(wind_speed, standard):
    if standard == 'taiwan':
        wind_speed_ms = wind_speed * 0.514444
        if wind_speed_ms >= 51.0:
            return 'Strong Typhoon', taiwan_standard['Strong Typhoon']['hex']
        elif wind_speed_ms >= 33.7:
            return 'Medium Typhoon', taiwan_standard['Medium Typhoon']['hex']
        elif wind_speed_ms >= 17.2:
            return 'Mild Typhoon', taiwan_standard['Mild Typhoon']['hex']
        return 'Tropical Depression', taiwan_standard['Tropical Depression']['hex']
    else:
        if wind_speed >= 137:
            return 'C5 Super Typhoon', atlantic_standard['C5 Super Typhoon']['hex']
        elif wind_speed >= 113:
            return 'C4 Very Strong Typhoon', atlantic_standard['C4 Very Strong Typhoon']['hex']
        elif wind_speed >= 96:
            return 'C3 Strong Typhoon', atlantic_standard['C3 Strong Typhoon']['hex']
        elif wind_speed >= 83:
            return 'C2 Typhoon', atlantic_standard['C2 Typhoon']['hex']
        elif wind_speed >= 64:
            return 'C1 Typhoon', atlantic_standard['C1 Typhoon']['hex']
        elif wind_speed >= 34:
            return 'Tropical Storm', atlantic_standard['Tropical Storm']['hex']
        return 'Tropical Depression', atlantic_standard['Tropical Depression']['hex']

def generate_track_video(year, typhoon, standard):
    if not typhoon:
        return None

    typhoon_id = typhoon.split('(')[-1].strip(')')
    storm = ibtracs.get_storm(typhoon_id)

    # Map focus
    min_lat, max_lat = min(storm.lat), max(storm.lat)
    min_lon, max_lon = min(storm.lon), max(storm.lon)
    lat_padding = max((max_lat - min_lat) * 0.3, 5)
    lon_padding = max((max_lon - min_lon) * 0.3, 5)

    # Set up the figure (900x700 pixels at 100 DPI)
    fig = plt.figure(figsize=(9, 7), dpi=100)
    ax = plt.axes([0.05, 0.05, 0.65, 0.90], projection=ccrs.PlateCarree())  # Adjusted to leave space for sidebar
    ax.set_extent([min_lon - lon_padding, max_lon + lon_padding, min_lat - lat_padding, max_lat + lat_padding], crs=ccrs.PlateCarree())

    # Add world map features
    ax.add_feature(cfeature.LAND, facecolor='lightgray')
    ax.add_feature(cfeature.OCEAN, facecolor='lightblue')
    ax.add_feature(cfeature.COASTLINE, edgecolor='black')
    ax.add_feature(cfeature.BORDERS, linestyle=':', edgecolor='gray')
    ax.gridlines(draw_labels=True, linestyle='--', color='gray', alpha=0.5)

    ax.set_title(f"{year} {storm.name} Typhoon Path")

    # Initialize the line and point
    line, = ax.plot([], [], 'b-', linewidth=2, transform=ccrs.PlateCarree())
    point, = ax.plot([], [], 'o', markersize=8, transform=ccrs.PlateCarree())
    date_text = ax.text(0.02, 0.02, '', transform=ax.transAxes, fontsize=10, bbox=dict(facecolor='white', alpha=0.8))

    # Add sidebar on the right with adjusted positions
    details_title = fig.text(0.7, 0.95, "Typhoon Details", fontsize=12, fontweight='bold', verticalalignment='top')
    details_text = fig.text(0.7, 0.85, '', fontsize=12, verticalalignment='top',
                            bbox=dict(facecolor='white', alpha=0.8, boxstyle='round,pad=0.5'))

    # Add color legend
    standard_dict = atlantic_standard if standard == 'atlantic' else taiwan_standard
    legend_elements = [plt.Line2D([0], [0], marker='o', color='w', label=f"{cat}", 
                                  markerfacecolor=details['hex'], markersize=10)
                       for cat, details in standard_dict.items()]
    fig.legend(handles=legend_elements, title="Color Legend", loc='center right', 
               bbox_to_anchor=(0.95, 0.5), fontsize=10)

    def init():
        line.set_data([], [])
        point.set_data([], [])
        date_text.set_text('')
        details_text.set_text('')
        return line, point, date_text, details_text

    def update(frame):
        line.set_data(storm.lon[:frame+1], storm.lat[:frame+1])
        category, color = categorize_typhoon_by_standard(storm.vmax[frame], standard)
        point.set_data([storm.lon[frame]], [storm.lat[frame]])
        point.set_color(color)
        date_text.set_text(storm.time[frame].strftime('%Y-%m-%d %H:%M'))
        details = f"Name: {storm.name}\n" \
                  f"Date: {storm.time[frame].strftime('%Y-%m-%d %H:%M')}\n" \
                  f"Wind Speed: {storm.vmax[frame]:.1f} kt\n" \
                  f"Category: {category}"
        details_text.set_text(details)
        return line, point, date_text, details_text

    ani = animation.FuncAnimation(fig, update, init_func=init, frames=len(storm.time),
                                  interval=200, blit=True, repeat=True)

    # Save as video
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
    writer = animation.FFMpegWriter(fps=5, bitrate=1800)
    ani.save(temp_file.name, writer=writer)
    plt.close(fig)

    return temp_file.name

# Logistic regression functions
def perform_wind_regression(start_year, start_month, end_year, end_month):
    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']
    model = sm.Logit(y, X).fit()
    beta_1, exp_beta_1, p_value = model.params['ONI'], np.exp(model.params['ONI']), model.pvalues['ONI']
    return f"Wind Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"

def perform_pressure_regression(start_year, start_month, end_year, end_month):
    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']
    model = sm.Logit(y, X).fit()
    beta_1, exp_beta_1, p_value = model.params['ONI'], np.exp(model.params['ONI']), model.pvalues['ONI']
    return f"Pressure Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"

def perform_longitude_regression(start_year, start_month, end_year, end_month):
    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']
    model = sm.Logit(y, X).fit()
    beta_1, exp_beta_1, p_value = model.params['ONI'], np.exp(model.params['ONI']), model.pvalues['ONI']
    return f"Longitude Regression: β1={beta_1:.4f}, Odds Ratio={exp_beta_1:.4f}, P-value={p_value:.4f}"

# t-SNE clustering functions
def filter_west_pacific_coordinates(lons, lats):
    mask = (lons >= 100) & (lons <= 180) & (lats >= 0) & (lats <= 40)
    return lons[mask], lats[mask]

def filter_storm_by_season(storm, season):
    start_month = storm.time[0].month
    if season == 'all':
        return True
    elif season == 'summer':
        return 4 <= start_month <= 8
    elif season == 'winter':
        return 9 <= start_month <= 12
    return False

def point_region(lat, lon):
    twl = regions["Taiwan Land"]
    if twl["lat_min"] <= lat <= twl["lat_max"] and twl["lon_min"] <= lon <= twl["lon_max"]:
        return "Taiwan Land"
    tws = regions["Taiwan Sea"]
    if tws["lat_min"] <= lat <= tws["lat_max"] and tws["lon_min"] <= lon <= tws["lon_max"]:
        if not (twl["lat_min"] <= lat <= twl["lat_max"] and twl["lon_min"] <= lon <= twl["lon_max"]):
            return "Taiwan Sea"
    for rg in ["Japan", "China", "Hong Kong", "Philippines"]:
        box = regions[rg]
        if box["lat_min"] <= lat <= box["lat_max"] and box["lon_min"] <= lon <= box["lon_max"]:
            return rg
    return None

def calculate_region_durations(lons, lats, times):
    region_times = defaultdict(float)
    point_regions_list = [point_region(lats[i], lons[i]) for i in range(len(lons))]
    for i in range(len(lons) - 1):
        dt = (times[i + 1] - times[i]).total_seconds() / 3600.0
        r1 = point_regions_list[i]
        r2 = point_regions_list[i + 1]
        if r1 and r2:
            if r1 == r2:
                region_times[r1] += dt
            else:
                region_times[r1] += dt / 2
                region_times[r2] += dt / 2
        elif r1 and not r2:
            region_times[r1] += dt / 2
        elif r2 and not r1:
            region_times[r2] += dt / 2
    return dict(region_times)

def endpoint_region_label(cluster_label, cluster_labels, filtered_storms):
    indices = np.where(cluster_labels == cluster_label)[0]
    if len(indices) == 0:
        return ""
    end_count = defaultdict(int)
    for idx in indices:
        lons, lats, vmax_, mslp_, times = filtered_storms[idx]
        reg = point_region(lats[-1], lons[-1])
        if reg:
            end_count[reg] += 1
    if end_count:
        max_reg = max(end_count, key=end_count.get)
        ratio = end_count[max_reg] / len(indices)
        if ratio > 0.5:
            return max_reg
    return ""

def dynamic_dbscan(tsne_results, min_clusters=10, max_clusters=20, eps_values=np.linspace(1.0, 10.0, 91)):
    best_labels = None
    best_n_clusters = 0
    best_n_noise = len(tsne_results)
    best_eps = None
    for eps in eps_values:
        dbscan = DBSCAN(eps=eps, min_samples=3)
        labels = dbscan.fit_predict(tsne_results)
        unique_labels = set(labels)
        if -1 in unique_labels:
            unique_labels.remove(-1)
        n_clusters = len(unique_labels)
        n_noise = np.sum(labels == -1)
        if min_clusters <= n_clusters <= max_clusters and n_noise < best_n_noise:
            best_labels = labels
            best_n_clusters = n_clusters
            best_n_noise = n_noise
            best_eps = eps
    if best_labels is None:
        for eps in eps_values[::-1]:
            dbscan = DBSCAN(eps=eps, min_samples=3)
            labels = dbscan.fit_predict(tsne_results)
            unique_labels = set(labels)
            if -1 in unique_labels:
                unique_labels.remove(-1)
            n_clusters = len(unique_labels)
            if n_clusters == max_clusters:
                best_labels = labels
                best_n_clusters = n_clusters
                best_n_noise = np.sum(labels == -1)
                best_eps = eps
                break
    return best_labels, best_n_clusters, best_n_noise, best_eps

def update_route_clusters(start_year, start_month, end_year, end_month, enso_value, season):
    start_date = datetime(int(start_year), int(start_month), 1)
    end_date = datetime(int(end_year), int(end_month), 28)
    
    all_storms_data = []
    for year in range(int(start_year), int(end_year) + 1):
        season_data = ibtracs.get_season(year)
        for storm_id in season_data.summary()['id']:
            storm = ibtracs.get_storm(storm_id)
            if storm.time[0] >= start_date and storm.time[-1] <= end_date and filter_storm_by_season(storm, season):
                lons, lats = filter_west_pacific_coordinates(np.array(storm.lon), np.array(storm.lat))
                if len(lons) > 1:
                    start_time = storm.time[0]
                    start_year_storm = start_time.year
                    start_month_storm = start_time.month
                    oni_row = oni_long[(oni_long['Year'] == start_year_storm) & (oni_long['Month'] == f'{start_month_storm:02d}')]
                    if not oni_row.empty:
                        oni_value_storm = oni_row['ONI'].iloc[0]
                        enso_phase_storm = classify_enso_phases(oni_value_storm)
                        if enso_value == 'all' or enso_phase_storm == enso_value.capitalize():
                            all_storms_data.append((lons, lats, np.array(storm.vmax), np.array(storm.mslp), np.array(storm.time), storm.name, enso_phase_storm))

    if not all_storms_data:
        return go.Figure(), go.Figure(), make_subplots(rows=2, cols=1), "No storms found in the selected period."

    # Prepare route vectors for t-SNE
    max_length = max(len(st[0]) for st in all_storms_data)
    route_vectors = []
    filtered_storms = []
    storms_vmax_list = []
    storms_mslp_list = []
    for idx, (lons, lats, vmax, mslp, times, name, enso_phase) in enumerate(all_storms_data):
        t = np.linspace(0, 1, len(lons))
        t_new = np.linspace(0, 1, max_length)
        try:
            lon_i = interp1d(t, lons, kind='linear', fill_value='extrapolate')(t_new)
            lat_i = interp1d(t, lats, kind='linear', fill_value='extrapolate')(t_new)
            vmax_i = interp1d(t, vmax, kind='linear', fill_value='extrapolate')(t_new)
            if not np.all(np.isnan(mslp)):
                mslp_i = interp1d(t, mslp, kind='linear', fill_value='extrapolate')(t_new)
            else:
                mslp_i = np.full(max_length, np.nan)
        except Exception as e:
            continue
        route_vector = np.column_stack((lon_i, lat_i)).flatten()
        if np.isnan(route_vector).any():
            continue
        route_vectors.append(route_vector)
        filtered_storms.append((lons, lats, vmax_i, mslp_i, times))
        storms_vmax_list.append(vmax_i)
        storms_mslp_list.append(mslp_i)

    route_vectors = np.array(route_vectors)
    if len(route_vectors) == 0:
        return go.Figure(), go.Figure(), make_subplots(rows=2, cols=1), "No valid storms after interpolation."

    # Perform t-SNE
    tsne = TSNE(n_components=2, random_state=42, verbose=1)
    tsne_results = tsne.fit_transform(route_vectors)

    # Dynamic DBSCAN clustering
    best_labels, best_n_clusters, best_n_noise, best_eps = dynamic_dbscan(tsne_results)

    # Calculate region durations and mean routes
    unique_labels = sorted(set(best_labels) - {-1})
    label_to_idx = {label: i for i, label in enumerate(unique_labels)}
    cluster_region_durations = [defaultdict(float) for _ in range(len(unique_labels))]
    cluster_mean_routes = []
    cluster_mean_vmax = []
    cluster_mean_mslp = []

    for i, (lons, lats, vmax, mslp, times) in enumerate(filtered_storms):
        c = best_labels[i]
        if c == -1:
            continue
        durations = calculate_region_durations(lons, lats, times)
        idx = label_to_idx[c]
        for r, val in durations.items():
            cluster_region_durations[idx][r] += val

    for c in unique_labels:
        indices = np.where(best_labels == c)[0]
        if len(indices) == 0:
            cluster_mean_routes.append(([], []))
            cluster_mean_vmax.append([])
            cluster_mean_mslp.append([])
            continue
        cluster_lons = []
        cluster_lats = []
        cluster_v = []
        cluster_p = []
        for idx in indices:
            lons, lats, vmax_, mslp_, times = filtered_storms[idx]
            t = np.linspace(0, 1, len(lons))
            t_new = np.linspace(0, 1, max_length)
            lon_i = interp1d(t, lons, kind='linear', fill_value='extrapolate')(t_new)
            lat_i = interp1d(t, lats, kind='linear', fill_value='extrapolate')(t_new)
            cluster_lons.append(lon_i)
            cluster_lats.append(lat_i)
            cluster_v.append(storms_vmax_list[idx])
            if not np.all(np.isnan(storms_mslp_list[idx])):
                cluster_p.append(storms_mslp_list[idx])
        if cluster_lons and cluster_lats:
            mean_lon = np.mean(cluster_lons, axis=0)
            mean_lat = np.mean(cluster_lats, axis=0)
            mean_v = np.mean(cluster_v, axis=0)
            if cluster_p:
                mean_p = np.nanmean(cluster_p, axis=0)
            else:
                mean_p = np.full(max_length, np.nan)
            cluster_mean_routes.append((mean_lon, mean_lat))
            cluster_mean_vmax.append(mean_v)
            cluster_mean_mslp.append(mean_p)
        else:
            cluster_mean_routes.append(([], []))
            cluster_mean_vmax.append([])
            cluster_mean_mslp.append([])

    # t-SNE Scatter Plot
    fig_tsne = go.Figure()
    cluster_colors = px.colors.qualitative.Safe
    if len(cluster_colors) < len(unique_labels):
        cluster_colors = px.colors.qualitative.Dark24
    for i, c in enumerate(unique_labels):
        indices = np.where(best_labels == c)[0]
        end_reg = endpoint_region_label(c, best_labels, filtered_storms)
        name = f"Cluster {i+1}" + (f" (towards {end_reg})" if end_reg else "")
        fig_tsne.add_trace(go.Scatter(
            x=tsne_results[indices, 0],
            y=tsne_results[indices, 1],
            mode='markers',
            marker=dict(size=5, color=cluster_colors[i % len(cluster_colors)]),
            name=name
        ))
    noise_indices = np.where(best_labels == -1)[0]
    if len(noise_indices) > 0:
        fig_tsne.add_trace(go.Scatter(
            x=tsne_results[noise_indices, 0],
            y=tsne_results[noise_indices, 1],
            mode='markers',
            marker=dict(size=5, color='grey'),
            name='Noise'
        ))
    fig_tsne.update_layout(
        title="TSNE of Typhoon Routes",
        xaxis_title="TSNE Dim 1",
        yaxis_title="TSNE Dim 2",
        legend_title="Clusters"
    )

    # Typhoon Routes Plot with Mean Routes
    fig_routes = go.Figure()
    for i, (lons, lats, _, _, _) in enumerate(filtered_storms):
        c = best_labels[i]
        if c == -1:
            continue
        color_idx = label_to_idx[c]
        fig_routes.add_trace(
            go.Scattergeo(
                lon=lons,
                lat=lats,
                mode='lines',
                opacity=0.3,
                line=dict(width=1, color=cluster_colors[color_idx % len(cluster_colors)]),
                showlegend=False
            )
        )
    for i, c in enumerate(unique_labels):
        mean_lon, mean_lat = cluster_mean_routes[i]
        if len(mean_lon) == 0:
            continue
        end_reg = endpoint_region_label(c, best_labels, filtered_storms)
        name = f"Cluster {i+1}" + (f" (towards {end_reg})" if end_reg else "")
        fig_routes.add_trace(
            go.Scattergeo(
                lon=mean_lon,
                lat=mean_lat,
                mode='lines',
                line=dict(width=4, color=cluster_colors[i % len(cluster_colors)]),
                name=name
            )
        )
        fig_routes.add_trace(
            go.Scattergeo(
                lon=[mean_lon[0]],
                lat=[mean_lat[0]],
                mode='markers',
                marker=dict(size=10, color='green', symbol='triangle-up'),
                name=f"Cluster {i+1} Start"
            )
        )
        fig_routes.add_trace(
            go.Scattergeo(
                lon=[mean_lon[-1]],
                lat=[mean_lat[-1]],
                mode='markers',
                marker=dict(size=10, color='red', symbol='x'),
                name=f"Cluster {i+1} End"
            )
        )
    enso_phase_text = {'all': 'All Years', 'El Nino': 'El Niño', 'La Nina': 'La Niña', 'Neutral': 'Neutral Years'}
    fig_routes.update_layout(
        title=f"West Pacific Typhoon Routes ({start_year}-{end_year}, {season.capitalize()}, {enso_phase_text.get(enso_value, 'All Years')})",
        geo=dict(scope='asia', projection_type='mercator', showland=True, landcolor='lightgray')
    )

    # Cluster Statistics Plot
    fig_stats = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Average Wind Speed", "Average Pressure"))
    for i, c in enumerate(unique_labels):
        if len(cluster_mean_vmax[i]) > 0:
            end_reg = endpoint_region_label(c, best_labels, filtered_storms)
            name = f"Cluster {i+1}" + (f" ({end_reg})" if end_reg else "")
            fig_stats.add_trace(
                go.Scatter(y=cluster_mean_vmax[i], mode='lines', line=dict(width=2, color=cluster_colors[i % len(cluster_colors)]), name=name),
                row=1, col=1
            )
            if not np.all(np.isnan(cluster_mean_mslp[i])):
                fig_stats.add_trace(
                    go.Scatter(y=cluster_mean_mslp[i], mode='lines', line=dict(width=2, color=cluster_colors[i % len(cluster_colors)]), name=name),
                    row=2, col=1
                )
    fig_stats.update_layout(
        title="Cluster Average Wind & Pressure Profiles",
        xaxis_title="Route Normalized Index",
        yaxis_title="Wind Speed (knots)",
        xaxis2_title="Route Normalized Index",
        yaxis2_title="Pressure (hPa)",
        showlegend=True,
        legend_tracegroupgap=300
    )

    # Cluster Information
    cluster_info_lines = [f"Selected DBSCAN eps: {best_eps:.2f}", f"Number of noise points: {best_n_noise}"]
    for i, c in enumerate(unique_labels):
        indices = np.where(best_labels == c)[0]
        count = len(indices)
        if count == 0:
            continue
        avg_durations = {r: (cluster_region_durations[i][r] / count) for r in cluster_region_durations[i]}
        end_reg = endpoint_region_label(c, best_labels, filtered_storms)
        name = f"Cluster {i+1}" + (f" (towards {end_reg})" if end_reg else "")
        cluster_info_lines.append(f"\n{name}")
        if avg_durations:
            for reg, hrs in avg_durations.items():
                cluster_info_lines.append(f"{reg}: {hrs:.2f} hours")
        else:
            cluster_info_lines.append("No significant region durations.")
        if end_reg in ["Taiwan Land", "Taiwan Sea"] and len(cluster_mean_vmax[i]) > 0:
            final_wind = cluster_mean_vmax[i][-1]
            if final_wind >= 34:
                cluster_info_lines.append(
                    "CWA would issue a land warning ~18 hours before arrival." if end_reg == "Taiwan Land"
                    else "CWA would issue a sea warning ~24 hours before arrival."
                )
    if len(noise_indices) > 0:
        cluster_info_lines.append(f"\nNoise Cluster\nNumber of storms classified as noise: {len(noise_indices)}")

    cluster_info_text = "\n".join(cluster_info_lines)
    return fig_tsne, fig_routes, fig_stats, cluster_info_text

# Gradio Interface
with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
    gr.Markdown("# Typhoon Analysis Dashboard")
    
    with gr.Tab("Overview"):
        gr.Markdown("""
        ## Welcome to the Typhoon Analysis Dashboard
        
        This dashboard allows you to analyze typhoon data in relation to ENSO phases.
        
        ### Features:
        - **Track Visualization**: View typhoon tracks by time period and ENSO phase
        - **Wind Analysis**: Examine wind speed vs ONI relationships
        - **Pressure Analysis**: Analyze pressure vs ONI relationships
        - **Longitude Analysis**: Study typhoon generation longitude vs ONI
        - **Path Animation**: Watch animated typhoon paths with a sidebar
        - **TSNE Cluster**: Perform t-SNE clustering on typhoon routes with mean routes and region analysis
        
        Select a tab above to begin your analysis.
        """)
    
    with gr.Tab("Track Visualization"):
        with gr.Row():
            start_year = gr.Number(label="Start Year", value=2000, minimum=1900, maximum=2024, step=1)
            start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
            end_year = gr.Number(label="End Year", value=2024, minimum=1900, maximum=2024, step=1)
            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(label="Typhoon Tracks", elem_id="tracks_plot")
        typhoon_count = gr.Textbox(label="Number of Typhoons Displayed")
        
        def get_full_tracks(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
            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)
            ]
            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]
                name = storm_data['NAME'].iloc[0] if not pd.isna(storm_data['NAME'].iloc[0]) else "Unnamed"
                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} ({storm_data['SEASON'].iloc[0]})",
                    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]} ({storm_data['SEASON'].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 Niña, Green: Neutral",
                showarrow=False, align="left",
                bgcolor="rgba(255,255,255,0.8)"
            )
            return fig, f"Total typhoons displayed: {count}"
            
        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=2000, minimum=1900, maximum=2024, step=1)
            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, minimum=1900, maximum=2024, step=1)
            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(label="Wind Speed vs ONI")
        wind_regression_results = gr.Textbox(label="Wind Regression Results")
        
        def get_wind_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
            results = generate_main_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search)
            regression = perform_wind_regression(start_year, start_month, end_year, end_month)
            return results[1], regression
            
        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=2000, minimum=1900, maximum=2024, step=1)
            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, minimum=1900, maximum=2024, step=1)
            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(label="Pressure vs ONI")
        pressure_regression_results = gr.Textbox(label="Pressure Regression Results")
        
        def get_pressure_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
            results = generate_main_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search)
            regression = perform_pressure_regression(start_year, start_month, end_year, end_month)
            return results[2], regression
            
        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=2000, minimum=1900, maximum=2024, step=1)
            lon_start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
            lon_end_year = gr.Number(label="End Year", value=2024, minimum=1900, maximum=2024, step=1)
            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(label="Longitude vs ONI")
        slopes_text = gr.Textbox(label="Regression Slopes")
        lon_regression_results = gr.Textbox(label="Longitude Regression Results")
        
        def get_longitude_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search):
            results = generate_main_analysis(start_year, start_month, end_year, end_month, enso_phase, typhoon_search)
            regression = perform_longitude_regression(start_year, start_month, end_year, end_month)
            return results[3], results[4], regression
            
        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("Typhoon Path Animation"):
        with gr.Row():
            year_dropdown = gr.Dropdown(label="Year", choices=[str(y) for y in range(1950, 2025)], value="2024")
            typhoon_dropdown = gr.Dropdown(label="Typhoon")
            standard_dropdown = gr.Dropdown(label="Classification Standard", choices=['atlantic', 'taiwan'], value='atlantic')
        
        animate_btn = gr.Button("Generate Animation")
        path_video = gr.Video(label="Typhoon Path Animation", elem_id="path_video")
        animation_info = gr.Markdown("""
        ### Animation Instructions
        1. Select a year and typhoon from the dropdowns
        2. Choose a classification standard (Atlantic or Taiwan)
        3. Click "Generate Animation"
        4. Use the video player's built-in controls to play, pause, or scrub through the animation
        5. The animation shows the typhoon track growing over a world map, with:
           - Date on the bottom left
           - Sidebar on the right showing typhoon details (name, date, wind speed, category) as it moves
           - Color legend with colored markers centered on the right
        """)
        
        def update_typhoon_options(year):
            season = ibtracs.get_season(int(year))
            storm_summary = season.summary()
            options = [f"{storm_summary['name'][i]} ({storm_summary['id'][i]})" for i in range(storm_summary['season_storms'])]
            return gr.update(choices=options, value=options[0] if options else None)
        
        year_dropdown.change(fn=update_typhoon_options, inputs=year_dropdown, outputs=typhoon_dropdown)
        animate_btn.click(
            fn=generate_track_video,
            inputs=[year_dropdown, typhoon_dropdown, standard_dropdown],
            outputs=path_video
        )
    
    with gr.Tab("TSNE Cluster"):
        with gr.Row():
            tsne_start_year = gr.Number(label="Start Year", value=2000, minimum=1900, maximum=2024, step=1)
            tsne_start_month = gr.Dropdown(label="Start Month", choices=list(range(1, 13)), value=1)
            tsne_end_year = gr.Number(label="End Year", value=2024, minimum=1900, maximum=2024, step=1)
            tsne_end_month = gr.Dropdown(label="End Month", choices=list(range(1, 13)), value=12)
            tsne_enso_phase = gr.Dropdown(label="ENSO Phase", choices=['all', 'El Nino', 'La Nina', 'Neutral'], value='all')
            tsne_season = gr.Dropdown(label="Season", choices=['all', 'summer', 'winter'], value='all')
        tsne_analyze_btn = gr.Button("Analyze")
        tsne_plot = gr.Plot(label="t-SNE Clusters")
        routes_plot = gr.Plot(label="Typhoon Routes with Mean Routes")
        stats_plot = gr.Plot(label="Cluster Statistics")
        cluster_info = gr.Textbox(label="Cluster Information", lines=10)
        
        tsne_analyze_btn.click(
            fn=update_route_clusters,
            inputs=[tsne_start_year, tsne_start_month, tsne_end_year, tsne_end_month, tsne_enso_phase, tsne_season],
            outputs=[tsne_plot, routes_plot, stats_plot, cluster_info]
        )

demo.launch(share=True)