app.py

import streamlit as st
import json
import ee
import os
import pandas as pd
import geopandas as gpd
from datetime import datetime
import leafmap.foliumap as leafmap
import re
from shapely.geometry import base
from xml.etree import ElementTree as XET
from concurrent.futures import ThreadPoolExecutor, as_completed
import time

# Set up the page layout
st.set_page_config(layout="wide")

# Custom button styling
m = st.markdown(
    """
    <style>
    div.stButton > button:first-child {
        background-color: #006400;
        color:#ffffff;
    }
    </style>""",
    unsafe_allow_html=True,
)

# Logo and Title
st.write(
    f"""
    <div style="display: flex; justify-content: space-between; align-items: center;">
        <img src="https://huggingface.co/spaces/YashMK89/SATRANG/resolve/main/ISRO_Logo.png" style="width: 20%; margin-right: auto;">
        <img src="https://huggingface.co/spaces/YashMK89/SATRANG/resolve/main/SAC_Logo.png" style="width: 20%; margin-left: auto;">
    </div>
    """,
    unsafe_allow_html=True,
)
st.markdown(
    f"""
    <div style="display: flex; flex-direction: column; align-items: center;">
        <img src="https://huggingface.co/spaces/YashMK89/SATRANG/resolve/main/SATRANG.png" style="width: 30%;">
        <h3 style="text-align: center; margin: 0;">( Spatial and Temporal Aggregation for Remote-sensing Analysis of GEE Data )</h3>
    </div>
    <hr>
    """,
    unsafe_allow_html=True,
)

# Authenticate and initialize Earth Engine
earthengine_credentials = os.environ.get("EE_Authentication")
os.makedirs(os.path.expanduser("~/.config/earthengine/"), exist_ok=True)
with open(os.path.expanduser("~/.config/earthengine/credentials"), "w") as f:
    f.write(earthengine_credentials)
ee.Initialize(project='ee-yashsacisro24')

# Helper function to get reducer
def get_reducer(reducer_name):
    reducers = {
        'mean': ee.Reducer.mean(),
        'sum': ee.Reducer.sum(),
        'median': ee.Reducer.median(),
        'min': ee.Reducer.min(),
        'max': ee.Reducer.max(),
        'count': ee.Reducer.count(),
    }
    return reducers.get(reducer_name.lower(), ee.Reducer.mean())

# Function to convert geometry to Earth Engine format
def convert_to_ee_geometry(geometry):
    if isinstance(geometry, base.BaseGeometry):
        if geometry.is_valid:
            geojson = geometry.__geo_interface__
            return ee.Geometry(geojson)
        else:
            raise ValueError("Invalid geometry: The polygon geometry is not valid.")
    elif isinstance(geometry, dict) or isinstance(geometry, str):
        try:
            if isinstance(geometry, str):
                geometry = json.loads(geometry)
            if 'type' in geometry and 'coordinates' in geometry:
                return ee.Geometry(geometry)
            else:
                raise ValueError("GeoJSON format is invalid.")
        except Exception as e:
            raise ValueError(f"Error parsing GeoJSON: {e}")
    elif isinstance(geometry, str) and geometry.lower().endswith(".kml"):
        try:
            tree = XET.parse(geometry)
            kml_root = tree.getroot()
            kml_namespace = {'kml': 'http://www.opengis.net/kml/2.2'}
            coordinates = kml_root.findall(".//kml:coordinates", kml_namespace)
            if coordinates:
                coords_text = coordinates[0].text.strip()
                coords = coords_text.split()
                coords = [tuple(map(float, coord.split(','))) for coord in coords]
                geojson = {"type": "Polygon", "coordinates": [coords]}
                return ee.Geometry(geojson)
            else:
                raise ValueError("KML does not contain valid coordinates.")
        except Exception as e:
            raise ValueError(f"Error parsing KML: {e}")
    else:
        raise ValueError("Unsupported geometry input type. Supported types are Shapely, GeoJSON, and KML.")

# Function to calculate custom formula
def calculate_custom_formula(image, geometry, selected_bands, custom_formula, reducer_choice, scale=30):
    try:
        band_values = {}
        band_names = image.bandNames().getInfo()
        for band in selected_bands:
            if band not in band_names:
                raise ValueError(f"Band '{band}' not found in the dataset.")
            band_values[band] = image.select(band)
        reducer = get_reducer(reducer_choice)
        reduced_values = {}
        for band in selected_bands:
            value = band_values[band].reduceRegion(
                reducer=reducer,
                geometry=geometry,
                scale=scale
            ).get(band).getInfo()
            reduced_values[band] = float(value if value is not None else 0)
        formula = custom_formula
        for band in selected_bands:
            formula = formula.replace(band, str(reduced_values[band]))
        result = eval(formula, {"__builtins__": {}}, reduced_values)
        if not isinstance(result, (int, float)):
            raise ValueError("Formula did not result in a numeric value.")
        return ee.Image.constant(result).rename('custom_result')
    except ZeroDivisionError:
        st.error("Error: Division by zero in the formula.")
        return ee.Image(0).rename('custom_result').set('error', 'Division by zero')
    except SyntaxError:
        st.error(f"Error: Invalid syntax in formula '{custom_formula}'.")
        return ee.Image(0).rename('custom_result').set('error', 'Invalid syntax')
    except ValueError as e:
        st.error(f"Error: {str(e)}")
        return ee.Image(0).rename('custom_result').set('error', str(e))
    except Exception as e:
        st.error(f"Unexpected error: {e}")
        return ee.Image(0).rename('custom_result').set('error', str(e))

# Aggregation functions (unchanged)

def aggregate_data_custom(collection):
    collection = collection.map(lambda image: image.set('day', ee.Date(image.get('system:time_start')).format('YYYY-MM-dd')))
    grouped_by_day = collection.aggregate_array('day').distinct()
    def calculate_daily_mean(day):
        daily_collection = collection.filter(ee.Filter.eq('day', day))
        daily_mean = daily_collection.mean()
        return daily_mean.set('day', day)
    daily_images = ee.List(grouped_by_day.map(calculate_daily_mean))
    return ee.ImageCollection(daily_images)

def aggregate_data_weekly(collection):
    def set_week_start(image):
        date = ee.Date(image.get('system:time_start'))
        days_since_week_start = date.getRelative('day', 'week')
        offset = ee.Number(days_since_week_start).multiply(-1)
        week_start = date.advance(offset, 'day')
        return image.set('week_start', week_start.format('YYYY-MM-dd'))
    collection = collection.map(set_week_start)
    grouped_by_week = collection.aggregate_array('week_start').distinct()
    def calculate_weekly_mean(week_start):
        weekly_collection = collection.filter(ee.Filter.eq('week_start', week_start))
        weekly_mean = weekly_collection.mean()
        return weekly_mean.set('week_start', week_start)
    weekly_images = ee.List(grouped_by_week.map(calculate_weekly_mean))
    return ee.ImageCollection(weekly_images)

def aggregate_data_monthly(collection, start_date, end_date):
    collection = collection.filterDate(start_date, end_date)
    collection = collection.map(lambda image: image.set('month', ee.Date(image.get('system:time_start')).format('YYYY-MM')))
    grouped_by_month = collection.aggregate_array('month').distinct()
    def calculate_monthly_mean(month):
        monthly_collection = collection.filter(ee.Filter.eq('month', month))
        monthly_mean = monthly_collection.mean()
        return monthly_mean.set('month', month)
    monthly_images = ee.List(grouped_by_month.map(calculate_monthly_mean))
    return ee.ImageCollection(monthly_images)

def aggregate_data_yearly(collection):
    collection = collection.map(lambda image: image.set('year', ee.Date(image.get('system:time_start')).format('YYYY')))
    grouped_by_year = collection.aggregate_array('year').distinct()
    def calculate_yearly_mean(year):
        yearly_collection = collection.filter(ee.Filter.eq('year', year))
        yearly_mean = yearly_collection.mean()
        return yearly_mean.set('year', year)
    yearly_images = ee.List(grouped_by_year.map(calculate_yearly_mean))
    return ee.ImageCollection(yearly_images)

def aggregate_data_daily(collection):
    def set_day_start(image):
        date = ee.Date(image.get('system:time_start'))
        day_start = date.format('YYYY-MM-dd')
        return image.set('day_start', day_start)
    collection = collection.map(set_day_start)
    grouped_by_day = collection.aggregate_array('day_start').distinct()
    def calculate_daily_mean(day_start):
        daily_collection = collection.filter(ee.Filter.eq('day_start', day_start))
        daily_mean = daily_collection.mean()
        return daily_mean.set('day_start', day_start)
    daily_images = ee.List(grouped_by_day.map(calculate_daily_mean))
    return ee.ImageCollection(daily_images)

# Worker function for processing a single geometry
def process_single_geometry(row, start_date_str, end_date_str, dataset_id, selected_bands, reducer_choice, shape_type, aggregation_period, custom_formula, kernel_size=None, include_boundary=None, default_scale=None):
    image_count = 0  # Initialize image counter
    if shape_type.lower() == "point":
        latitude = row.get('latitude')
        longitude = row.get('longitude')
        if pd.isna(latitude) or pd.isna(longitude):
            return None, 0  # Return 0 images for invalid points
        location_name = row.get('name', f"Location_{row.name}")
        if kernel_size == "3x3 Kernel":
            buffer_size = 45  # 90m x 90m
            roi = ee.Geometry.Point([longitude, latitude]).buffer(buffer_size).bounds()
        elif kernel_size == "5x5 Kernel":
            buffer_size = 75  # 150m x 150m
            roi = ee.Geometry.Point([longitude, latitude]).buffer(buffer_size).bounds()
        else:  # Point
            roi = ee.Geometry.Point([longitude, latitude])
    elif shape_type.lower() == "polygon":
        polygon_geometry = row.get('geometry')
        location_name = row.get('name', f"Polygon_{row.name}")
        try:
            roi = convert_to_ee_geometry(polygon_geometry)
            if not include_boundary:
                roi = roi.buffer(-30).bounds()
        except ValueError:
            return None, 0  # Return 0 images for invalid polygons

    collection = ee.ImageCollection(dataset_id) \
        .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
        .filterBounds(roi) \
        .select(selected_bands)

    # Get the count of images before aggregation
    initial_count = collection.size().getInfo()
    image_count += initial_count

    if aggregation_period.lower() == 'custom (start date to end date)':
        collection = aggregate_data_custom(collection)
    elif aggregation_period.lower() == 'daily':
        collection = aggregate_data_daily(collection)
    elif aggregation_period.lower() == 'weekly':
        collection = aggregate_data_weekly(collection)
    elif aggregation_period.lower() == 'monthly':
        collection = aggregate_data_monthly(collection, start_date_str, end_date_str)
    elif aggregation_period.lower() == 'yearly':
        collection = aggregate_data_yearly(collection)

    image_list = collection.toList(collection.size())
    processed_days = set()
    aggregated_results = []

    for i in range(image_list.size().getInfo()):
        image = ee.Image(image_list.get(i))
        if aggregation_period.lower() == 'custom (start date to end date)':
            timestamp = image.get('day')
            period_label = 'Date'
            date = ee.Date(timestamp).format('YYYY-MM-dd').getInfo()
        elif aggregation_period.lower() == 'daily':
            timestamp = image.get('day_start')
            period_label = 'Day'
            date = ee.String(timestamp).getInfo()
        elif aggregation_period.lower() == 'weekly':
            timestamp = image.get('week_start')
            period_label = 'Week'
            date = ee.String(timestamp).getInfo()
        elif aggregation_period.lower() == 'monthly':
            timestamp = image.get('month')
            period_label = 'Month'
            date = ee.Date(timestamp).format('YYYY-MM').getInfo()
        elif aggregation_period.lower() == 'yearly':
            timestamp = image.get('year')
            period_label = 'Year'
            date = ee.Date(timestamp).format('YYYY').getInfo()

        index_image = calculate_custom_formula(image, roi, selected_bands, custom_formula, reducer_choice, scale=default_scale)

        try:
            index_value = index_image.reduceRegion(
                reducer=get_reducer(reducer_choice),
                geometry=roi,
                scale=default_scale
            ).get('custom_result')
            calculated_value = index_value.getInfo()
            if isinstance(calculated_value, (int, float)):
                result = {
                    'Location Name': location_name,
                    period_label: date,
                    'Start Date': start_date_str,
                    'End Date': end_date_str,
                    'Calculated Value': calculated_value
                }
                if shape_type.lower() == 'point':
                    result['Latitude'] = latitude
                    result['Longitude'] = longitude
                aggregated_results.append(result)
        except Exception as e:
            st.error(f"Error retrieving value for {location_name}: {e}")

    return aggregated_results, image_count  # Return both results and image count

# Main processing function
def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id, selected_bands, reducer_choice, shape_type, aggregation_period, custom_formula="", kernel_size=None, include_boundary=None, default_scale=None):
    # Auto-detect scale if not provided
    if default_scale is None:
        collection = ee.ImageCollection(dataset_id)
        default_scale = collection.first().select(0).projection().nominalScale().getInfo()
        
    aggregated_results = []
    total_images = 0  # Track total images processed
    total_steps = len(locations_df)
    progress_bar = st.progress(0)
    progress_text = st.empty()
    start_time = time.time()

    with ThreadPoolExecutor(max_workers=10) as executor:
        futures = []
        for idx, row in locations_df.iterrows():
            future = executor.submit(
                process_single_geometry,
                row,
                start_date_str,
                end_date_str,
                dataset_id,
                selected_bands,
                reducer_choice,
                shape_type,
                aggregation_period,
                custom_formula,
                kernel_size,
                include_boundary,
                default_scale
            )
            futures.append(future)

        completed = 0
        for future in as_completed(futures):
            result, image_count = future.result()
            if result:
                aggregated_results.extend(result)
                total_images += image_count
            completed += 1
            progress_percentage = completed / total_steps
            progress_bar.progress(progress_percentage)
            progress_text.markdown(f"Processing: {int(progress_percentage * 100)}% (Total images: {total_images})")

    end_time = time.time()
    processing_time = end_time - start_time

    if aggregated_results:
        result_df = pd.DataFrame(aggregated_results)
        if aggregation_period.lower() == 'custom (start date to end date)':
            agg_dict = {
                'Start Date': 'first',
                'End Date': 'first',
                'Calculated Value': 'mean'
            }
            if shape_type.lower() == 'point':
                agg_dict['Latitude'] = 'first'
                agg_dict['Longitude'] = 'first'
            aggregated_output = result_df.groupby('Location Name').agg(agg_dict).reset_index()
            aggregated_output.rename(columns={'Calculated Value': 'Aggregated Value'}, inplace=True)
            return aggregated_output.to_dict(orient='records'), processing_time, total_images
        else:
            return result_df.to_dict(orient='records'), processing_time, total_images
    return [], processing_time, total_images

# Streamlit App Logic
st.markdown("<h5>Image Collection</h5>", unsafe_allow_html=True)
imagery_base = st.selectbox("Select Imagery Base", ["Sentinel", "Landsat", "MODIS", "VIIRS", "Custom Input"], index=0)

# Initialize data as an empty dictionary
data = {}

if imagery_base == "Sentinel":
    dataset_file = "sentinel_datasets.json"
    try:
        with open(dataset_file) as f:
            data = json.load(f)
    except FileNotFoundError:
        st.error(f"Dataset file '{dataset_file}' not found.")
        data = {}
elif imagery_base == "Landsat":
    dataset_file = "landsat_datasets.json"
    try:
        with open(dataset_file) as f:
            data = json.load(f)
    except FileNotFoundError:
        st.error(f"Dataset file '{dataset_file}' not found.")
        data = {}
elif imagery_base == "MODIS":
    dataset_file = "modis_datasets.json"
    try:
        with open(dataset_file) as f:
            data = json.load(f)
    except FileNotFoundError:
        st.error(f"Dataset file '{dataset_file}' not found.")
        data = {}
elif imagery_base == "VIIRS":
    dataset_file = "viirs_datasets.json"
    try:
        with open(dataset_file) as f:
            data = json.load(f)
    except FileNotFoundError:
        st.error(f"Dataset file '{dataset_file}' not found.")
        data = {}
elif imagery_base == "Custom Input":
    custom_dataset_id = st.text_input(
        "Enter Custom Earth Engine Dataset ID (e.g., MODIS/006/MOD13Q1)", 
        value="",
        help="Enter the full path of the EE dataset (e.g., 'COPERNICUS/S2_SR')"
    )

    if custom_dataset_id:
        try:
            # Clean input if it includes ee.ImageCollection syntax
            if custom_dataset_id.startswith("ee.ImageCollection("):
                custom_dataset_id = custom_dataset_id.replace("ee.ImageCollection('", "").replace("')", "").strip()

            # Initialize dataset structure
            data = {
                f"Custom Dataset: {custom_dataset_id}": {
                    "sub_options": {custom_dataset_id: f"Custom Dataset ({custom_dataset_id})"},
                    "bands": {custom_dataset_id: []}
                }
            }

            # Fetch collection and metadata
            collection = ee.ImageCollection(custom_dataset_id)
            first_image = collection.first()
            band_names = first_image.bandNames().getInfo()

            # Get the native scale from GEE (DO NOT DEFAULT TO 30)
            try:
                default_scale = first_image.select(0).projection().nominalScale().getInfo()
                if not isinstance(default_scale, (int, float)) or default_scale <= 0:
                    raise ValueError("Invalid scale from GEE")
            except:
                # If scale detection fails, use GEE's default instead of forcing 30
                default_scale = None  # Let GEE handle it

            # Update data structure
            data[f"Custom Dataset: {custom_dataset_id}"]["bands"][custom_dataset_id] = band_names

            st.success(f"✅ Successfully loaded: {custom_dataset_id}")
            st.write(f"Available Bands: {', '.join(band_names)}")
            if default_scale:
                st.write(f"Native Scale: {default_scale} meters")
            else:
                st.write("Native Scale: Letting GEE use its default resolution")

        except Exception as e:
            st.error(f"Error loading dataset: {str(e)}")
            data = {}
    else:
        st.warning("Please enter a custom dataset ID to proceed.")
        data = {}

if not data:
    st.error("No valid dataset available. Please check your inputs.")
    st.stop()

st.markdown("<hr><h5><b>{}</b></h5>".format(imagery_base), unsafe_allow_html=True)

main_selection = st.selectbox(f"Select {imagery_base} Dataset Category", list(data.keys()))

sub_selection = None
dataset_id = None

if main_selection:
    sub_options = data[main_selection]["sub_options"]
    sub_selection = st.selectbox(f"Select Specific {imagery_base} Dataset ID", list(sub_options.keys()))
    if sub_selection:
        st.write(f"You selected: {main_selection} -> {sub_options[sub_selection]}")
        st.write(f"Dataset ID: {sub_selection}")
        dataset_id = sub_selection
        try:
            collection = ee.ImageCollection(dataset_id)
            first_image = collection.first()
            default_scale = first_image.select(0).projection().nominalScale().getInfo()
            st.write(f"Default Scale for Selected Dataset: {default_scale} meters")
        except Exception as e:
            st.error(f"Error fetching default scale: {str(e)}")

st.markdown("<hr><h5><b>Earth Engine Index Calculator</b></h5>", unsafe_allow_html=True)

if main_selection and sub_selection:
    dataset_bands = data[main_selection]["bands"].get(sub_selection, [])
    st.write(f"Available Bands for {sub_options[sub_selection]}: {', '.join(dataset_bands)}")
    selected_bands = st.multiselect(
        "Select Bands for Calculation",
        options=dataset_bands,
        default=[dataset_bands[0]] if dataset_bands else [],
        help=f"Select bands from: {', '.join(dataset_bands)}"
    )

    if len(selected_bands) < 1:
        st.warning("Please select at least one band.")
        st.stop()

    if selected_bands:
        if len(selected_bands) == 1:
            default_formula = f"{selected_bands[0]}"
            example = f"'{selected_bands[0]} * 2' or '{selected_bands[0]} + 1'"
        else:
            default_formula = f"({selected_bands[0]} - {selected_bands[1]}) / ({selected_bands[0]} + {selected_bands[1]})"
            example = f"'{selected_bands[0]} * {selected_bands[1]} / 2' or '({selected_bands[0]} - {selected_bands[1]}) / ({selected_bands[0]} + {selected_bands[1]})'"
        custom_formula = st.text_input(
            "Enter Custom Formula (e.g (B8 - B4) / (B8 + B4) , B4*B3/2)",
            value=default_formula,
            help=f"Use only these bands: {', '.join(selected_bands)}. Examples: {example}"
        )

        def validate_formula(formula, selected_bands):
            allowed_chars = set(" +-*/()0123456789.")
            terms = re.findall(r'[a-zA-Z][a-zA-Z0-9_]*', formula)
            invalid_terms = [term for term in terms if term not in selected_bands]
            if invalid_terms:
                return False, f"Invalid terms in formula: {', '.join(invalid_terms)}. Use only {', '.join(selected_bands)}."
            if not all(char in allowed_chars or char in ''.join(selected_bands) for char in formula):
                return False, "Formula contains invalid characters. Use only bands, numbers, and operators (+, -, *, /, ())"
            return True, ""

        is_valid, error_message = validate_formula(custom_formula, selected_bands)
        if not is_valid:
            st.error(error_message)
            st.stop()
        elif not custom_formula:
            st.warning("Please enter a custom formula to proceed.")
            st.stop()

        st.write(f"Custom Formula: {custom_formula}")

reducer_choice = st.selectbox(
    "Select Reducer (e.g, mean , sum , median , min , max , count)",
    ['mean', 'sum', 'median', 'min', 'max', 'count'],
    index=0
)

start_date = st.date_input("Start Date", value=pd.to_datetime('2024-11-01'))
end_date = st.date_input("End Date", value=pd.to_datetime('2024-12-01'))
start_date_str = start_date.strftime('%Y-%m-%d')
end_date_str = end_date.strftime('%Y-%m-%d')

aggregation_period = st.selectbox(
    "Select Aggregation Period (e.g, Custom(Start Date to End Date) , Daily , Weekly , Monthly , Yearly)",
    ["Custom (Start Date to End Date)", "Daily", "Weekly", "Monthly", "Yearly"],
    index=0
)

shape_type = st.selectbox("Do you want to process 'Point' or 'Polygon' data?", ["Point", "Polygon"])

kernel_size = None
include_boundary = None

if shape_type.lower() == "point":
    kernel_size = st.selectbox(
        "Select Calculation Area(e.g, Point , 3x3 Kernel , 5x5 Kernel)",
        ["Point", "3x3 Kernel", "5x5 Kernel"],
        index=0,
        help="Choose 'Point' for exact point calculation, or a kernel size for area averaging."
    )
elif shape_type.lower() == "polygon":
    include_boundary = st.checkbox(
        "Include Boundary Pixels",
        value=True,
        help="Check to include pixels on the polygon boundary; uncheck to exclude them."
    )

file_upload = st.file_uploader(f"Upload your {shape_type} data (CSV, GeoJSON, KML)", type=["csv", "geojson", "kml"])
locations_df = pd.DataFrame()
original_lat_col = None
original_lon_col = None

if file_upload is not None:
    if shape_type.lower() == "point":
        if file_upload.name.endswith('.csv'):
            locations_df = pd.read_csv(file_upload)
            st.write("Preview of your uploaded data (first 5 rows):")
            st.dataframe(locations_df.head())
            all_columns = locations_df.columns.tolist()
            col1, col2 = st.columns(2)
            with col1:
                original_lat_col = st.selectbox(
                    "Select Latitude Column",
                    options=all_columns,
                    index=all_columns.index('latitude') if 'latitude' in all_columns else 0,
                    help="Select the column containing latitude values"
                )
            with col2:
                original_lon_col = st.selectbox(
                    "Select Longitude Column",
                    options=all_columns,
                    index=all_columns.index('longitude') if 'longitude' in all_columns else 0,
                    help="Select the column containing longitude values"
                )
            if not pd.api.types.is_numeric_dtype(locations_df[original_lat_col]) or not pd.api.types.is_numeric_dtype(locations_df[original_lon_col]):
                st.error("Error: Selected Latitude and Longitude columns must contain numeric values")
                st.stop()
            locations_df = locations_df.rename(columns={
                original_lat_col: 'latitude',
                original_lon_col: 'longitude'
            })
        elif file_upload.name.endswith('.geojson'):
            locations_df = gpd.read_file(file_upload)
            if 'geometry' in locations_df.columns:
                locations_df['latitude'] = locations_df['geometry'].y
                locations_df['longitude'] = locations_df['geometry'].x
                original_lat_col = 'latitude'
                original_lon_col = 'longitude'
            else:
                st.error("GeoJSON file doesn't contain geometry column")
                st.stop()
        elif file_upload.name.endswith('.kml'):
            kml_string = file_upload.read().decode('utf-8')
            try:
                root = XET.fromstring(kml_string)
                ns = {'kml': 'http://www.opengis.net/kml/2.2'}
                points = []
                for placemark in root.findall('.//kml:Placemark', ns):
                    name = placemark.findtext('kml:name', default=f"Point_{len(points)}", namespaces=ns)
                    coords_elem = placemark.find('.//kml:Point/kml:coordinates', ns)
                    if coords_elem is not None:
                        coords_text = coords_elem.text.strip()
                        coords = [c.strip() for c in coords_text.split(',')]
                        if len(coords) >= 2:
                            lon, lat = float(coords[0]), float(coords[1])
                            points.append({'name': name, 'geometry': f"POINT ({lon} {lat})"})
                if not points:
                    st.error("No valid Point data found in the KML file.")
                else:
                    locations_df = gpd.GeoDataFrame(points, geometry=gpd.GeoSeries.from_wkt([p['geometry'] for p in points]), crs="EPSG:4326")
                    locations_df['latitude'] = locations_df['geometry'].y
                    locations_df['longitude'] = locations_df['geometry'].x
                    original_lat_col = 'latitude'
                    original_lon_col = 'longitude'
            except Exception as e:
                st.error(f"Error parsing KML file: {str(e)}")
        if not locations_df.empty and 'latitude' in locations_df.columns and 'longitude' in locations_df.columns:
            m = leafmap.Map(center=[locations_df['latitude'].mean(), locations_df['longitude'].mean()], zoom=10)
            for _, row in locations_df.iterrows():
                latitude = row['latitude']
                longitude = row['longitude']
                if pd.isna(latitude) or pd.isna(longitude):
                    continue
                m.add_marker(location=[latitude, longitude], popup=row.get('name', 'No Name'))
            st.write("Map of Uploaded Points:")
            m.to_streamlit()
    elif shape_type.lower() == "polygon":
        if file_upload.name.endswith('.csv'):
            st.error("CSV upload not supported for polygons. Please upload a GeoJSON or KML file.")
        elif file_upload.name.endswith('.geojson'):
            locations_df = gpd.read_file(file_upload)
            if 'geometry' not in locations_df.columns:
                st.error("GeoJSON file doesn't contain geometry column")
                st.stop()
        elif file_upload.name.endswith('.kml'):
            kml_string = file_upload.read().decode('utf-8')
            try:
                root = XET.fromstring(kml_string)
                ns = {'kml': 'http://www.opengis.net/kml/2.2'}
                polygons = []
                for placemark in root.findall('.//kml:Placemark', ns):
                    name = placemark.findtext('kml:name', default=f"Polygon_{len(polygons)}", namespaces=ns)
                    coords_elem = placemark.find('.//kml:Polygon//kml:coordinates', ns)
                    if coords_elem is not None:
                        coords_text = ' '.join(coords_elem.text.split())
                        coord_pairs = [pair.split(',')[:2] for pair in coords_text.split() if pair]
                        if len(coord_pairs) >= 4:
                            coords_str = " ".join([f"{float(lon)} {float(lat)}" for lon, lat in coord_pairs])
                            polygons.append({'name': name, 'geometry': f"POLYGON (({coords_str}))"})
                if not polygons:
                    st.error("No valid Polygon data found in the KML file.")
                else:
                    locations_df = gpd.GeoDataFrame(polygons, geometry=gpd.GeoSeries.from_wkt([p['geometry'] for p in polygons]), crs="EPSG:4326")
            except Exception as e:
                st.error(f"Error parsing KML file: {str(e)}")
        if not locations_df.empty and 'geometry' in locations_df.columns:
            centroid_lat = locations_df.geometry.centroid.y.mean()
            centroid_lon = locations_df.geometry.centroid.x.mean()
            m = leafmap.Map(center=[centroid_lat, centroid_lon], zoom=10)
            for _, row in locations_df.iterrows():
                polygon = row['geometry']
                if polygon.is_valid:
                    gdf = gpd.GeoDataFrame([row], geometry=[polygon], crs=locations_df.crs)
                    m.add_gdf(gdf=gdf, layer_name=row.get('name', 'Unnamed Polygon'))
            st.write("Map of Uploaded Polygons:")
            m.to_streamlit()

if st.button(f"Calculate {custom_formula}"):
    if not locations_df.empty:
        # Use a spinner to indicate data processing
        with st.spinner("Processing Data..."):
            try:
                # Call the aggregation function and capture results, processing time, and image count
                results, processing_time, total_images = process_aggregation(
                    locations_df,
                    start_date_str,
                    end_date_str,
                    dataset_id,
                    selected_bands,
                    reducer_choice,
                    shape_type,
                    aggregation_period,
                    custom_formula,
                    kernel_size,
                    include_boundary,
                    default_scale
                )
                # Check if results were generated
                if results:
                    result_df = pd.DataFrame(results)
                    st.write(f"Default Scale for Selected Dataset: {default_scale} meters")
                    st.write(f"Total Images Processed: {total_images}")
                    st.write(f"Processed Results Table ({aggregation_period}) for Formula: {custom_formula}")
                    st.dataframe(result_df)
                    # Generate a downloadable CSV file
                    filename = f"{main_selection}_{dataset_id}_{start_date.strftime('%Y/%m/%d')}_{end_date.strftime('%Y/%m/%d')}_{aggregation_period.lower()}.csv"

                    st.download_button(
                        label="Download results as CSV",
                        data=result_df.to_csv(index=False).encode('utf-8'),
                        file_name=filename,
                        mime='text/csv'
                    )
                    # Display processing time
                    st.success(f"Processing complete! Total processing time: {processing_time:.2f} seconds for {total_images} images.")
                else:
                    st.warning("No results were generated. Check your inputs or formula.")
                    st.info(f"Total processing time: {processing_time:.2f} seconds.")  # Show processing time even if no results
            except Exception as e:
                st.error(f"An error occurred during processing: {str(e)}")
    else:
        st.warning("Please upload a file to proceed.")

# Footer with developer credit
st.markdown(
    """
    <hr>
    <div style="text-align: center;">
        <p>Developed by <a href="https://huggingface.co/YashMK89" target="_blank">YashMK89</a> | 
        <a href="https://huggingface.co/AgricultureLab2024" target="_blank">AgricultureLab</a></p>
    </div>
    """,
    unsafe_allow_html=True
)