app.py

import streamlit as st
import json
import ee
import os
import pandas as pd
import numpy as np
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
import matplotlib.pyplot as plt
import plotly.express as px

# 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 with dynamic scale handling
def calculate_custom_formula(image, geometry, selected_bands, custom_formula, reducer_choice, dataset_id, user_scale=None):
    try:
        # Fetch the nominal scales of the selected bands
        band_scales = []
        for band in selected_bands:
            band_scale = image.select(band).projection().nominalScale().getInfo()
            band_scales.append(band_scale)
        default_scale = min(band_scales) if band_scales else 30  # Default to 30m if no bands are found
        scale = user_scale if user_scale is not None else default_scale
        # Rescale all bands to the chosen scale
        rescaled_bands = {}
        for band in selected_bands:
            band_image = image.select(band)
            band_scale = band_image.projection().nominalScale().getInfo()
            if band_scale != scale:
                rescaled_band = band_image.resample('bilinear').reproject(
                    crs=band_image.projection().crs(),
                    scale=scale
                )
                rescaled_bands[band] = rescaled_band
            else:
                rescaled_bands[band] = band_image
        # Validate and extract band values
        reduced_values = {}
        reducer = get_reducer(reducer_choice)
        for band in selected_bands:
            value = rescaled_bands[band].reduceRegion(
                reducer=reducer,
                geometry=geometry,
                scale=scale
            ).get(band).getInfo()
            reduced_values[band] = float(value if value is not None else 0)
        # Evaluate the custom formula
        formula = custom_formula
        for band in selected_bands:
            formula = formula.replace(band, str(reduced_values[band]))
        result = eval(formula, {"__builtins__": {}}, reduced_values)
        # Validate the result
        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))

# Cloud percentage calculation
def calculate_cloud_percentage(image, cloud_band='QA60'):
    qa60 = image.select(cloud_band)
    opaque_clouds = qa60.bitwiseAnd(1 << 10)
    cirrus_clouds = qa60.bitwiseAnd(1 << 11)
    cloud_mask = opaque_clouds.Or(cirrus_clouds)
    total_pixels = qa60.reduceRegion(
        reducer=ee.Reducer.count(),
        geometry=image.geometry(),
        scale=60,
        maxPixels=1e13
    ).get(cloud_band)
    cloudy_pixels = cloud_mask.reduceRegion(
        reducer=ee.Reducer.sum(),
        geometry=image.geometry(),
        scale=60,
        maxPixels=1e13
    ).get(cloud_band)
    if total_pixels == 0:
        return 0
    return ee.Number(cloudy_pixels).divide(ee.Number(total_pixels)).multiply(100)

# Preprocessing function
def preprocess_collection(collection, pixel_cloud_threshold):
    def mask_cloudy_pixels(image):
        qa60 = image.select('QA60')
        opaque_clouds = qa60.bitwiseAnd(1 << 10)
        cirrus_clouds = qa60.bitwiseAnd(1 << 11)
        cloud_mask = opaque_clouds.Or(cirrus_clouds)
        clear_pixels = cloud_mask.Not()
        return image.updateMask(clear_pixels)
    if pixel_cloud_threshold > 0:
        return collection.map(mask_cloudy_pixels)
    return collection

# Process 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, original_lat_col, original_lon_col, kernel_size=None, include_boundary=None, user_scale=None, pixel_cloud_threshold=0):
    if shape_type.lower() == "point":
        latitude = row.get('latitude')
        longitude = row.get('longitude')
        if pd.isna(latitude) or pd.isna(longitude):
            return None
        location_name = row.get('name', f"Location_{row.name}")
        if kernel_size == "3x3 Kernel":
            buffer_size = 45
            roi = ee.Geometry.Point([longitude, latitude]).buffer(buffer_size).bounds()
        elif kernel_size == "5x5 Kernel":
            buffer_size = 75
            roi = ee.Geometry.Point([longitude, latitude]).buffer(buffer_size).bounds()
        else:
            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
    # Filter collection by date and area first
    collection = ee.ImageCollection(dataset_id) \
        .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
        .filterBounds(roi)
    st.write(f"After initial filtering: {collection.size().getInfo()} images")
    # Apply pixel cloud masking if threshold > 0
    if pixel_cloud_threshold > 0:
        collection = preprocess_collection(collection, pixel_cloud_threshold)
        st.write(f"After cloud masking: {collection.size().getInfo()} images")
    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, start_date_str, end_date_str)
    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_weeks = 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 = 'Date'
            date = ee.String(timestamp).getInfo()
        elif aggregation_period.lower() == 'weekly':
            timestamp = image.get('week_start')
            period_label = 'Week'
            date = ee.String(timestamp).getInfo()
            if (pd.to_datetime(date) < pd.to_datetime(start_date_str) or 
                pd.to_datetime(date) > pd.to_datetime(end_date_str) or 
                date in processed_weeks):
                continue
            processed_weeks.add(date)
        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, dataset_id, user_scale=user_scale)
        try:
            index_value = index_image.reduceRegion(
                reducer=get_reducer(reducer_choice),
                geometry=roi,
                scale=user_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[original_lat_col] = latitude
                    result[original_lon_col] = longitude
                aggregated_results.append(result)
        except Exception as e:
            st.error(f"Error retrieving value for {location_name}: {e}")
    return aggregated_results

# Process aggregation
def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id, selected_bands, reducer_choice, shape_type, aggregation_period, original_lat_col, original_lon_col, custom_formula="", kernel_size=None, include_boundary=None, tile_cloud_threshold=0, pixel_cloud_threshold=0, user_scale=None):
    aggregated_results = []
    total_steps = len(locations_df)
    progress_bar = st.progress(0)
    progress_text = st.empty()
    start_time = time.time()
    raw_collection = ee.ImageCollection(dataset_id) \
        .filterDate(ee.Date(start_date_str), ee.Date(end_date_str))
    
    # Log the original collection size
    st.write(f"Original Collection Size: {raw_collection.size().getInfo()}")

    # # Apply spatial filtering
    # if roi is not None:
    #     raw_collection = raw_collection.filterBounds(roi)
    #     st.write(f"Filtered Collection Size (After Spatial Filtering): {raw_collection.size().getInfo()}")

    # Apply cloud masking if threshold > 0
    if pixel_cloud_threshold > 0:
        raw_collection = preprocess_collection(raw_collection, pixel_cloud_threshold)
        st.write(f"Filtered Collection Size (After Cloud Masking): {raw_collection.size().getInfo()}")

    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,
                original_lat_col,
                original_lon_col,
                kernel_size,
                include_boundary,
                user_scale=user_scale
            )
            futures.append(future)
        completed = 0
        for future in as_completed(futures):
            result = future.result()
            if result:
                aggregated_results.extend(result)
            completed += 1
            progress_percentage = completed / total_steps
            progress_bar.progress(progress_percentage)
            progress_text.markdown(f"Processing: {int(progress_percentage * 100)}%")
    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[original_lat_col] = 'first'
                agg_dict[original_lon_col] = 'first'
            aggregated_output = result_df.groupby('Location Name').agg(agg_dict).reset_index()
            aggregated_output['Date Range'] = aggregated_output['Start Date'] + " to " + aggregated_output['End Date']
            return aggregated_output.to_dict(orient='records'), processing_time
        else:
            return result_df.to_dict(orient='records'), processing_time
    return [], processing_time

# 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)
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., AHN/AHN4)", value="")
    if custom_dataset_id:
        try:
            if custom_dataset_id.startswith("ee.ImageCollection("):
                custom_dataset_id = custom_dataset_id.replace("ee.ImageCollection('", "").replace("')", "")
            collection = ee.ImageCollection(custom_dataset_id)
            first_image = collection.first()
            default_scale = first_image.projection().nominalScale().getInfo()
            band_names = first_image.bandNames().getInfo()
            data = {
                f"Custom Dataset: {custom_dataset_id}": {
                    "sub_options": {custom_dataset_id: f"Custom Dataset ({custom_dataset_id})"},
                    "bands": {custom_dataset_id: band_names}
                }
            }
            st.write(f"Fetched bands for {custom_dataset_id}: {', '.join(band_names)}")
            st.write(f"Default Scale for Dataset: {default_scale} meters")
        except Exception as e:
            st.error(f"Error fetching dataset: {str(e)}. Please check the dataset ID and ensure it's valid in Google Earth Engine.")
            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
        # Fetch the default scale for the selected dataset
        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)}")
    # Fetch nominal scales for all bands in the selected dataset
    if dataset_id:
        try:
            # Fetch the first image from the collection to extract band information
            collection = ee.ImageCollection(dataset_id)
            first_image = collection.first()
            band_names = first_image.bandNames().getInfo()
            # Extract scales for all bands
            band_scales = []
            for band in band_names:
                band_scale = first_image.select(band).projection().nominalScale().getInfo()
                band_scales.append(band_scale)
            # Identify unique scales using np.unique
            unique_scales = np.unique(band_scales)
            # Display the unique scales to the user
            st.write(f"Nominal Scales for Bands: {band_scales}")
            st.write(f"Unique Scales in Dataset: {unique_scales}")
            # If there are multiple unique scales, allow the user to choose one
            if len(unique_scales) > 1:
                selected_scale = st.selectbox(
                    "Select a Scale for Calculation (meters)",
                    options=unique_scales,
                    index=0,
                    help="Choose a scale from the unique scales available in the dataset."
                )
                default_scale = selected_scale
            else:
                default_scale = unique_scales[0]
                st.write(f"Default Scale for Dataset: {default_scale} meters")
        except Exception as e:
            st.error(f"Error fetching band scales: {str(e)}")
            default_scale = 30  # Fallback to 30 meters if an error occurs
    selected_bands = st.multiselect(
        "Select 1 or 2 Bands for Calculation",
        options=dataset_bands,
        default=[dataset_bands[0]] if dataset_bands else [],
        help=f"Select 1 or 2 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')
if imagery_base == "Sentinel" and "Sentinel-2" in sub_options[sub_selection]:
    st.markdown("<h5>Cloud Filtering</h5>", unsafe_allow_html=True)
    pixel_cloud_threshold = st.slider(
        "Select Maximum Pixel-Based Cloud Coverage Threshold (%)",
        min_value=0,
        max_value=100,
        value=5,
        step=5,
        help="Individual pixels with cloud coverage exceeding this threshold will be masked."
    )
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."
    )
# st.markdown("<h5>Calculation Scale</h5>", unsafe_allow_html=True)
# default_scale = ee.ImageCollection(dataset_id).first().select(0).projection().nominalScale().getInfo()
# user_scale = st.number_input(
#     "Enter Calculation Scale (meters) [Leave blank to use dataset's default scale]",
#     min_value=1.0,
#     value=float(default_scale),
#     help=f"Default scale for this dataset is {default_scale} meters. Adjust if needed."
# )
st.markdown("<h5>Calculation Scale</h5>", unsafe_allow_html=True)
user_scale = st.number_input(
    "Enter Calculation Scale (meters) [Leave blank to use dataset's default scale]",
    min_value=1.0,
    value=float(default_scale),
    help=f"Default scale for this dataset is {default_scale} meters. Adjust if needed."
)
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:
        with st.spinner("Processing Data..."):
            try:
                results, processing_time = process_aggregation(
                    locations_df,
                    start_date_str,
                    end_date_str,
                    dataset_id,
                    selected_bands,
                    reducer_choice,
                    shape_type,
                    aggregation_period,
                    original_lat_col,
                    original_lon_col,
                    custom_formula=custom_formula,
                    kernel_size=kernel_size,
                    include_boundary=include_boundary,
                    pixel_cloud_threshold=pixel_cloud_threshold if "pixel_cloud_threshold" in locals() else 0,
                    user_scale=user_scale
                )
                if results:
                    result_df = pd.DataFrame(results)
                    st.write(f"Processed Results Table ({aggregation_period}) for Formula: {custom_formula}")
                    st.dataframe(result_df)
                    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'
                    )
                    st.success(f"Processing complete! Total processing time: {processing_time:.2f} seconds.")
                    st.markdown("<h5>Graph Visualization</h5>", unsafe_allow_html=True)
                    if aggregation_period.lower() == 'custom (start date to end date)':
                        x_column = 'Date Range'
                    elif 'Date' in result_df.columns:
                        x_column = 'Date'
                    elif 'Week' in result_df.columns:
                        x_column = 'Week'
                    elif 'Month' in result_df.columns:
                        x_column = 'Month'
                    elif 'Year' in result_df.columns:
                        x_column = 'Year'
                    else:
                        st.warning("No valid time column found for plotting.")
                        st.stop()
                    y_column = 'Calculated Value'
                    fig = px.line(
                        result_df,
                        x=x_column,
                        y=y_column,
                        color='Location Name',
                        title=f"{custom_formula} Over Time"
                    )
                    st.plotly_chart(fig)
                else:
                    st.warning("No results were generated. Check your inputs or formula.")
                    st.info(f"Total processing time: {processing_time:.2f} seconds.")
            except Exception as e:
                st.error(f"An error occurred during processing: {str(e)}")
    else:
        st.warning("Please upload a valid file to proceed.")