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 time
import re

# 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
st.write(
    f"""
    <div style="display: flex; justify-content: space-between; align-items: center;">
        <img src="https://huggingface.co/spaces/YashMK89/GEE_Calculator/resolve/main/ISRO_Logo.png"  style="width: 20%; margin-right: auto;">
        <img src="https://huggingface.co/spaces/YashMK89/GEE_Calculator/resolve/main/SAC_Logo.png"  style="width: 20%; margin-left: auto;">
    </div>
    """,
    unsafe_allow_html=True,
)

# Authenticate and initialize Earth Engine
earthengine_credentials = os.environ.get("EE_Authentication")

# Initialize Earth Engine with secret credentials
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')

# Load Sentinel dataset options from JSON file
with open("sentinel_datasets.json") as f:
    data = json.load(f)

# Display the title and dataset selection
st.title("Sentinel Dataset")

# Select dataset category and subcategory
main_selection = st.selectbox("Select Sentinel Dataset Category", list(data.keys()))

if main_selection:
    sub_options = data[main_selection]["sub_options"]
    sub_selection = st.selectbox("Select Specific Dataset ID", list(sub_options.keys()))

# Earth Engine Index Calculator Section
st.header("Earth Engine Index Calculator")

# Choose Index or Custom Formula
index_choice = st.selectbox("Select an Index or Enter Custom Formula", ['NDVI', 'NDWI', 'Average NO₂', 'Custom Formula'])

# Initialize custom_formula variable
custom_formula = ""

# Display corresponding formula based on the index selected
if index_choice == 'NDVI':
    st.write("Formula for NDVI: NDVI = (B8 - B4) / (B8 + B4)")
elif index_choice == 'NDWI':
    st.write("Formula for NDWI: NDWI = (B3 - B8) / (B3 + B8)")
elif index_choice == 'Average NO₂':
    st.write("Formula for Average NO₂: Average NO₂ = Mean(NO2 band)")
elif index_choice == 'Custom Formula':
    custom_formula = st.text_input("Enter Custom Formula (e.g., 'B5 - B4 / B5 + B4')")
    st.write(f"Custom Formula: {custom_formula}")  # Display the custom formula after the user inputs it

# Function to read points from CSV
def read_csv(file_path):
    df = pd.read_csv(file_path)
    return df

# Function to read points from GeoJSON
def read_geojson(file_path):
    gdf = gpd.read_file(file_path)
    return gdf

# Function to read points from KML
def read_kml(file_path):
    gdf = gpd.read_file(file_path, driver='KML')
    return gdf

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

# Ask user to upload a file based on shape type
file_upload = st.file_uploader(f"Upload your {shape_type} data (CSV, GeoJSON, KML)", type=["csv", "geojson", "kml"])

# Date Input for Start and End Dates
start_date = st.date_input("Start Date", value=pd.to_datetime('2020-01-01'))
end_date = st.date_input("End Date", value=pd.to_datetime('2020-12-31'))

# Convert start_date and end_date to string format for Earth Engine
start_date_str = start_date.strftime('%Y-%m-%d')
end_date_str = end_date.strftime('%Y-%m-%d')

# Initialize session state for storing results if not already done
if 'results' not in st.session_state:
    st.session_state.results = []
if 'last_params' not in st.session_state:
    st.session_state.last_params = {}
if 'map_data' not in st.session_state:
    st.session_state.map_data = None  # Initialize map_data

# Function to check if parameters have changed
def parameters_changed():
    return (
        st.session_state.last_params.get('main_selection') != main_selection or
        st.session_state.last_params.get('sub_selection') != sub_selection or
        st.session_state.last_params.get('index_choice') != index_choice or
        st.session_state.last_params.get('start_date_str') != start_date_str or
        st.session_state.last_params.get('end_date_str') != end_date_str
    )

# If parameters have changed, reset the results
if parameters_changed():
    st.session_state.results = []  # Clear the previous results
    # Update the last parameters to the current ones
    st.session_state.last_params = {
        'main_selection': main_selection,
        'sub_selection': sub_selection,
        'index_choice': index_choice,
        'start_date_str': start_date_str,
        'end_date_str': end_date_str
    }

# Function to perform index calculations
def calculate_ndvi(image, geometry):
    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
    result = ndvi.reduceRegion(
        reducer=ee.Reducer.mean(),
        geometry=geometry,
        scale=30
    )
    return result.get('NDVI')

def calculate_ndwi(image, geometry):
    ndwi = image.normalizedDifference(['B3', 'B8']).rename('NDWI')
    result = ndwi.reduceRegion(
        reducer=ee.Reducer.mean(),
        geometry=geometry,
        scale=30
    )
    return result.get('NDWI')

def calculate_avg_no2_sentinel5p(image, geometry):
    no2 = image.select('NO2').reduceRegion(
        reducer=ee.Reducer.mean(),
        geometry=geometry,
        scale=1000
    ).get('NO2')
    return no2

def calculate_custom_formula(image, geometry, formula):
    result = image.expression(formula).rename('Custom Index').reduceRegion(
        reducer=ee.Reducer.mean(),
        geometry=geometry,
        scale=30
    )
    return result.get('Custom Index')

# Function to sanitize the description for export
def sanitize_description(description):
    # Replace spaces and other invalid characters with underscores
    sanitized = re.sub(r'[^a-zA-Z0-9._-]', '_', description)
    # Ensure the description is no longer than 100 characters
    sanitized = sanitized[:100]
    return sanitized

# Process each point
if file_upload:
    locations_df = None  # Initialize locations_df to None
    polygons_df = None   # Initialize polygons_df to None

    file_extension = os.path.splitext(file_upload.name)[1].lower()

    # Read file based on shape type
    if shape_type == 'Point':
        if file_extension == '.csv':
            locations_df = read_csv(file_upload)
        elif file_extension == '.geojson':
            locations_df = read_geojson(file_upload)
        elif file_extension == '.kml':
            locations_df = read_kml(file_upload)
        else:
            st.error("Unsupported file type. Please upload a CSV, GeoJSON, or KML file for points.")
    elif shape_type == 'Polygon':
        if file_extension == '.geojson':
            polygons_df = read_geojson(file_upload)
        elif file_extension == '.kml':
            polygons_df = read_kml(file_upload)
        else:
            st.error("Unsupported file type. Please upload a GeoJSON or KML file for polygons.")

    if locations_df is not None:
        # Display a preview of the points data
        st.write("Preview of the uploaded points data:")
        st.dataframe(locations_df.head())

        # Create a LeafMap object to display the points
        m = leafmap.Map(center=[locations_df['latitude'].mean(), locations_df['longitude'].mean()], zoom=10)

        # Add points to the map using a loop
        for _, row in locations_df.iterrows():
            latitude = row['latitude']
            longitude = row['longitude']
            
            # Check if latitude or longitude are NaN and skip if they are
            if pd.isna(latitude) or pd.isna(longitude):
                continue  # Skip this row and move to the next one
            
            m.add_marker(location=[latitude, longitude], popup=row.get('name', 'No Name'))

        # Display map
        st.write("Map of Uploaded Points:")
        m.to_streamlit()

        # Store the map in session_state
        st.session_state.map_data = m

    # Process each point for index calculation
    for idx, row in locations_df.iterrows():
        latitude = row['latitude']
        longitude = row['longitude']
        location_name = row.get('name', f"Location_{idx}")

        # Skip processing if latitude or longitude is NaN
        if pd.isna(latitude) or pd.isna(longitude):
            continue  # Skip this row and move to the next one

        # Define the region of interest (ROI)
        roi = ee.Geometry.Point([longitude, latitude])

        # Load Sentinel-2 image collection
        collection = ee.ImageCollection(sub_options[sub_selection]) \
            .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
            .filterBounds(roi)

        # Check if the collection has images for the selected date range
        image_count = collection.size().getInfo()
        if image_count == 0:
            st.warning(f"No images found for {location_name}.")
        else:
            st.write(f"Found {image_count} images for {location_name}.")
            image = collection.first()

            # Perform the calculation based on user selection
            result = None
            if index_choice == 'NDVI':
                result = calculate_ndvi(image, roi)
            elif index_choice == 'NDWI':
                result = calculate_ndwi(image, roi)
            elif index_choice == 'Average NO₂':
                if 'NO2' in image.bandNames().getInfo():
                    result = calculate_avg_no2_sentinel5p(image, roi)
                else:
                    st.warning(f"No NO2 band found for {location_name}. Please use Sentinel-5P for NO₂ data.")
            elif index_choice == 'Custom Formula' and custom_formula:
                result = calculate_custom_formula(image, roi, custom_formula)

            if result is not None:
                # Only store the numeric value (not the dictionary structure)
                calculated_value = result.getInfo()  # Get the numeric value

                # Store the result in session state
                st.session_state.results.append({
                    'Location Name': location_name,
                    'Latitude': latitude,
                    'Longitude': longitude,
                    'Calculated Value': calculated_value
                })

            # Sanitize the location name for use in the export task
            sanitized_location_name = sanitize_description(location_name)

            # Now allow user to download the image
            st.write(f"Click below to download the image for {sanitized_location_name}:")

            # Export image as GeoTIFF
            export_image = image.clip(roi)  # Clip the image to the region of interest (ROI)
            export_task = ee.batch.Export.image.toDrive(
                image=export_image,
                description=sanitized_location_name,
                folder='Sentinel_Images',
                fileNamePrefix=f'{sanitized_location_name}_image',
                region=roi,
                scale=30,
                fileFormat='GeoTIFF',
                crs='EPSG:4326'
            )
            export_task.start()

            # Show export status
            st.info(f"Exporting image for {sanitized_location_name}. This might take some time...")

            # Poll for the task status (to check if export is finished)
            while export_task.active():
                time.sleep(5)
                st.write("Export in progress...")

            st.write(f"Export complete! The image is ready for download.")
            
            # Generate a link to the exported image in Google Drive
            # Replace 'your_google_drive_folder_link' with the actual folder ID in your Drive
            st.write(f"Click below to download the GeoTIFF image for {sanitized_location_name}:")
            st.download_button(
                label=f"Download {sanitized_location_name} Image",
                data=export_image.getDownloadURL(),
                file_name=f'{sanitized_location_name}_image.tif'
            )

# After processing, show the results
if st.session_state.results:
    # Convert the results to a DataFrame for better visualization
    result_df = pd.DataFrame(st.session_state.results)

    # Show the results in a table format
    st.write("Processed Results Table:")
    st.dataframe(result_df[['Location Name', 'Latitude', 'Longitude', 'Calculated Value']])

    # Allow downloading of the results as CSV
    st.download_button(
        label="Download results as CSV",
        data=result_df.to_csv(index=False).encode('utf-8'),
        file_name="calculated_results.csv",
        mime='text/csv'
    )