update app.py

app.py

@@ -30,8 +30,8 @@ m = st.markdown(
 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;">
+        <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,
@@ -44,7 +44,7 @@ st.markdown(
     """,
     unsafe_allow_html=True,
 )
-st.write("<h2><div style='text-align: center;'>User  Inputs</div></h2>", unsafe_allow_html=True)
+st.write("<h2><div style='text-align: center;'>User Inputs</div></h2>", unsafe_allow_html=True)
 
 # Authenticate and initialize Earth Engine
 earthengine_credentials = os.environ.get("EE_Authentication")
@@ -55,66 +55,105 @@ with open(os.path.expanduser("~/.config/earthengine/credentials"), "w") as f:
     f.write(earthengine_credentials)
 
 ee.Initialize(project='ee-yashsacisro24')
+# Imagery base selection
+imagery_base = st.selectbox("Select Imagery Base", ["Sentinel", "Landsat"], index=0)
 
-# Load the Sentinel dataset options from JSON file
-with open("sentinel_datasets.json") as f:
+# Load the appropriate dataset based on imagery base
+if imagery_base == "Sentinel":
+    dataset_file = "sentinel_datasets.json"
+else:
+    dataset_file = "landsat_datasets.json"
+
+with open(dataset_file) as f:
     data = json.load(f)
 
 # Display the title for the Streamlit app
-st.title("Sentinel Dataset")
+st.title(f"{imagery_base} Dataset")
 
 # Select dataset category (main selection)
-main_selection = st.selectbox("Select Sentinel Dataset Category", list(data.keys()))
+main_selection = st.selectbox(f"Select {imagery_base} Dataset Category", list(data.keys()))
+
+# Initialize sub_selection and dataset_id as None
+sub_selection = None
+dataset_id = None
 
 # If a category is selected, display the sub-options (specific datasets)
 if main_selection:
     sub_options = data[main_selection]["sub_options"]
-    sub_selection = st.selectbox("Select Specific Dataset ID", list(sub_options.keys()))
+    sub_selection = st.selectbox(f"Select Specific {imagery_base} Dataset ID", list(sub_options.keys()))
 
     # Display the selected dataset ID based on user input
     if sub_selection:
-        st.write(f"You selected: {main_selection} -> {sub_selection}")
-        st.write(f"Dataset ID: {sub_options[sub_selection]}")
-
-        # Fetch the correct dataset ID from the sub-selection
-        dataset_id = sub_options[sub_selection]
+        st.write(f"You selected: {main_selection} -> {sub_options[sub_selection]}")
+        st.write(f"Dataset ID: {sub_selection}")
+        dataset_id = sub_selection  # Use the key directly as the dataset ID
 
 # Earth Engine Index Calculator Section
 st.header("Earth Engine Index Calculator")
 
-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 (case-insensitive)
-if index_choice.lower() == 'ndvi':
-    st.write("Formula for NDVI: NDVI = (B8 - B4) / (B8 + B4)")
-elif index_choice.lower() == 'ndwi':
-    st.write("Formula for NDWI: NDWI = (B3 - B8) / (B3 + B8)")
-elif index_choice.lower() == 'average no₂':
-    st.write("Formula for Average NO₂: Average NO₂ = Mean(NO2 band)")
-elif index_choice.lower() == 'custom formula':
-    custom_formula = st.text_input("Enter Custom Formula (e.g., B5,B4 for two bands or B3 for one band)")
-    # Check if custom formula is empty and show warning
-    if not custom_formula:
-        st.warning("Please enter a custom formula before proceeding.")
-    else:
-        # Check if the input contains a comma (indicating two bands)
-        if ',' in custom_formula:
-            # Split the input into two bands and strip whitespace
-            band1, band2 = [b.strip() for b in custom_formula.split(',', 1)]
-            st.write(f"Custom Formula: ({band1} - {band2}) / ({band1} + {band2})")
-        else:
-            # Single band case
-            band = custom_formula.strip()
-            st.write(f"Custom Formula: {band}")
+# Load band information based on selected dataset
+if main_selection and sub_selection:  # Now safe because sub_selection is initialized
+    dataset_bands = data[main_selection]["bands"].get(sub_selection, [])
+    st.write(f"Available Bands for {sub_options[sub_selection]}: {', '.join(dataset_bands)}")
+
+    # Allow user to select 1 or 2 bands
+    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)}"
+    )
+
+    # Ensure minimum 1 and maximum 2 bands are selected
+    if len(selected_bands) < 1:
+        st.warning("Please select at least one band.")
+        st.stop()
+    elif len(selected_bands) > 2:
+        st.warning("You can select a maximum of 2 bands.")
+        st.stop()
+
+    # Show custom formula input if bands are selected
+    if selected_bands:
+        # Provide a default formula based on the number of 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:  # len(selected_bands) == 2
+            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",
+            value=default_formula,
+            help=f"Use only these bands: {', '.join(selected_bands)}. Examples: {example}"
+        )
+
+        # Validate the formula
+        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()
+
+        # Display the validated formula
+        st.write(f"Custom Formula: {custom_formula}")
+        
+# The rest of your code (reducer, geometry conversion, date input, aggregation, etc.) remains unchanged...
 
 # Function to get the corresponding reducer based on user input
 def get_reducer(reducer_name):
-    """
-    Map user-friendly reducer names to Earth Engine reducer objects.
-    """
     reducers = {
         'mean': ee.Reducer.mean(),
         'sum': ee.Reducer.sum(),
@@ -123,91 +162,52 @@ def get_reducer(reducer_name):
         'max': ee.Reducer.max(),
         'count': ee.Reducer.count(),
     }
-    
-    # Default to 'mean' if the reducer_name is not recognized
     return reducers.get(reducer_name.lower(), ee.Reducer.mean())
 
 # Streamlit selectbox for reducer choice
 reducer_choice = st.selectbox(
-    "Select Reducer",
+    "Select Reducer (e.g, mean , sum , median , min , max , count)",
     ['mean', 'sum', 'median', 'min', 'max', 'count'],
     index=0  # Default to 'mean'
 )
 
+# Function to convert geometry to Earth Engine format
 def convert_to_ee_geometry(geometry):
-    # Handle Shapely geometry
     if isinstance(geometry, base.BaseGeometry):
         if geometry.is_valid:
             geojson = geometry.__geo_interface__
-            print("Shapely GeoJSON:", geojson)  # Debugging: Inspect the GeoJSON structure
             return ee.Geometry(geojson)
         else:
             raise ValueError("Invalid geometry: The polygon geometry is not valid.")
-    
-    # Handle GeoJSON input (string or dictionary)
     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:
-                print("GeoJSON Geometry:", geometry)  # Debugging: Inspect the GeoJSON structure
                 return ee.Geometry(geometry)
             else:
                 raise ValueError("GeoJSON format is invalid.")
         except Exception as e:
             raise ValueError(f"Error parsing GeoJSON: {e}")
-
-    # Handle KML input (string or file path)
     elif isinstance(geometry, str) and geometry.lower().endswith(".kml"):
         try:
-            # Parse the KML file
             tree = ET.parse(geometry)
             kml_root = tree.getroot()
-
-            # Extract coordinates from KML geometry (assuming it's a Polygon or MultiPolygon)
-            # KML coordinates are usually within the <coordinates> tag
             kml_namespace = {'kml': 'http://www.opengis.net/kml/2.2'}
             coordinates = kml_root.findall(".//kml:coordinates", kml_namespace)
-            
             if coordinates:
-                # Extract and format coordinates
                 coords_text = coordinates[0].text.strip()
                 coords = coords_text.split()
-                # Convert KML coordinates (comma-separated) into a list of tuples
                 coords = [tuple(map(float, coord.split(','))) for coord in coords]
-                geojson = {
-                    "type": "Polygon",  # Make sure the GeoJSON type is Polygon
-                    "coordinates": [coords]  # Wrap the coordinates in a list (required by GeoJSON format)
-                }
-
-                # Debugging: Inspect the KML-to-GeoJSON structure
-                print("KML GeoJSON:", geojson)
-                
+                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 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
-
-
 # Date Input for Start and End Dates
 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'))
@@ -217,18 +217,38 @@ start_date_str = start_date.strftime('%Y-%m-%d')
 end_date_str = end_date.strftime('%Y-%m-%d')
 
 # Aggregation period selection
-aggregation_period = st.selectbox("Select Aggregation Period", ["Daily", "Weekly", "Monthly", "Yearly"], index=0)
+aggregation_period = st.selectbox(
+    "Select Aggregation Period (e.g, Custom(Start Date to End Date) , Weekly , Monthly , Yearly)",
+    ["Custom (Start Date to End Date)", "Weekly", "Monthly", "Yearly"],
+    index=0
+)
 
-# Ask user whether they want to process 'Point' or 'Polygon' data (case-insensitive)
+# 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 (case-insensitive)
+# Additional options based on shape type
+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."
+    )
+
+# 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"])
 
 if file_upload is not None:
     # Read the user-uploaded file
     if shape_type.lower() == "point":
-        # Handle different file types for Point data
         if file_upload.name.endswith('.csv'):
             locations_df = pd.read_csv(file_upload)
         elif file_upload.name.endswith('.geojson'):
@@ -239,53 +259,34 @@ if file_upload is not None:
             st.error("Unsupported file format. Please upload CSV, GeoJSON, or KML.")
             locations_df = pd.DataFrame()
 
-         # Check if the file contains polygons when the user selected "Point"
         if 'geometry' in locations_df.columns:
-            # Check if the geometry type is Polygon or MultiPolygon
             if locations_df.geometry.geom_type.isin(['Polygon', 'MultiPolygon']).any():
                 st.warning("The uploaded file contains polygon data. Please select 'Polygon' for processing.")
-                st.stop()  # Stop further processing if polygons are detected
+                st.stop()
 
-        # Processing the point data
         with st.spinner('Processing Map...'):
             if locations_df is not None and not locations_df.empty:
-                # For GeoJSON data, the coordinates are in the geometry column
                 if 'geometry' in locations_df.columns:
-                    # Extract latitude and longitude from the geometry column
                     locations_df['latitude'] = locations_df['geometry'].y
                     locations_df['longitude'] = locations_df['geometry'].x
 
-                # Ensure the necessary columns exist in the dataframe
                 if 'latitude' not in locations_df.columns or 'longitude' not in locations_df.columns:
                     st.error("Uploaded file is missing required 'latitude' or 'longitude' columns.")
                 else:
-                    # 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
-                        
+                            continue
                         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
 
     elif shape_type.lower() == "polygon":
-        # Handle different file types for Polygon data:
         if file_upload.name.endswith('.csv'):
             locations_df = pd.read_csv(file_upload)
         elif file_upload.name.endswith('.geojson'):
@@ -296,229 +297,172 @@ if file_upload is not None:
             st.error("Unsupported file format. Please upload CSV, GeoJSON, or KML.")
             locations_df = pd.DataFrame()
 
-        # Check if the file contains points when the user selected "Polygon"
         if 'geometry' in locations_df.columns:
-            # Check if the geometry type is Point or MultiPoint
             if locations_df.geometry.geom_type.isin(['Point', 'MultiPoint']).any():
                 st.warning("The uploaded file contains point data. Please select 'Point' for processing.")
-                st.stop()  # Stop further processing if point data is detected
+                st.stop()
 
-        # Processing the polygon data
         with st.spinner('Processing Map...'):
             if locations_df is not None and not locations_df.empty:
-                # Ensure the 'geometry' column exists in the dataframe
                 if 'geometry' not in locations_df.columns:
                     st.error("Uploaded file is missing required 'geometry' column.")
                 else:
-                    # Display a preview of the polygons data
                     st.write("Preview of the uploaded polygons data:")
                     st.dataframe(locations_df.head())
-
-                    # Create a LeafMap object to display the polygons
-                    # Calculate the centroid of the polygons for the map center
                     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)
-
-                    # Add polygons to the map using a loop
                     for _, row in locations_df.iterrows():
                         polygon = row['geometry']
-                        if polygon.is_valid:  # Check if polygon is valid
-                            # Create a GeoDataFrame for this polygon
+                        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'))
-
-                    # Display map
                     st.write("Map of Uploaded Polygons:")
                     m.to_streamlit()
-
-                    # Store the map in session_state
                     st.session_state.map_data = m
 
-# Initialize session state for storing results if not already done
+# Initialize session state for storing results
 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
+    st.session_state.map_data = None
+if 'show_example' not in st.session_state:
+    st.session_state.show_example = True
 
 # 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('dataset_id') != dataset_id or
-        st.session_state.last_params.get('index_choice') != index_choice or
+        st.session_state.last_params.get('selected_bands') != selected_bands or
+        st.session_state.last_params.get('custom_formula') != custom_formula 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 or
         st.session_state.last_params.get('shape_type') != shape_type or
-        st.session_state.last_params.get('file_upload') != file_upload
+        st.session_state.last_params.get('file_upload') != file_upload or
+        st.session_state.last_params.get('kernel_size') != kernel_size or
+        st.session_state.last_params.get('include_boundary') != include_boundary
     )
 
 # If parameters have changed, reset the results
 if parameters_changed():
-    st.session_state.results = []  # Clear the previous results
+    st.session_state.results = []
     st.session_state.last_params = {
         'main_selection': main_selection,
         'dataset_id': dataset_id,
-        'index_choice': index_choice,
+        'selected_bands': selected_bands,
+        'custom_formula': custom_formula,
         'start_date_str': start_date_str,
         'end_date_str': end_date_str,
         'shape_type': shape_type,
-        'file_upload': file_upload
+        'file_upload': file_upload,
+        'kernel_size': kernel_size,
+        'include_boundary': include_boundary
     }
 
-# Function to calculate NDVI with the selected reducer
-def calculate_ndvi(image, geometry, reducer_choice):
-    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
-    return ndvi
-
-# Function to calculate NDWI
-def calculate_ndwi(image, geometry, reducer_choice):
-    ndwi = image.normalizedDifference(['B3', 'B8']).rename('NDWI')
-    return ndwi
-
-def calculate_custom_formula(image, geometry, custom_formula, reducer_choice, scale=30):
+# Function to calculate custom formula
+def calculate_custom_formula(image, geometry, selected_bands, custom_formula, reducer_choice, scale=30):
     try:
-        if "," in custom_formula:
-            band1, band2 = [b.strip() for b in custom_formula.split(",")]
-            band_names = image.bandNames().getInfo()
-            if band1 not in band_names or band2 not in band_names:
-                raise ValueError(f"One or both bands ({band1}, {band2}) do not exist in the image.")
-            result = image.normalizedDifference([band1, band2]).rename('custom_formula')
-        else:
-            band = custom_formula.strip()
-            band_names = image.bandNames().getInfo()
+        band_values = {}
+        band_names = image.bandNames().getInfo()
+        
+        for band in selected_bands:
             if band not in band_names:
-                raise ValueError(f"The band '{band}' does not exist in the image.")
-            result = image.select(band).rename('custom_formula')
-        return result
-    except Exception as e:
-        return ee.Image(0).rename('custom_formula').set('error', str(e))
+                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.")
         
-# Modify aggregation functions to return the correct time period and aggregated results
-def aggregate_data_daily(collection):
-    # Extract day from the image date (using the exact date)
-    collection = collection.map(lambda image: image.set('day', ee.Date(image.get('system:time_start')).format('YYYY-MM-dd')))
+        return ee.Image.constant(result).rename('custom_result')
     
-    # Group images by day (distinct days)
-    grouped_by_day = collection.aggregate_array('day').distinct()
+    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))
 
+# Function to calculate index for a period
+def calculate_index_for_period(image, roi, selected_bands, custom_formula, reducer_choice):
+    return calculate_custom_formula(image, roi, selected_bands, custom_formula, reducer_choice)
+
+# Aggregation functions
+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):
-        # Filter the collection by the specific day
         daily_collection = collection.filter(ee.Filter.eq('day', day))
-        daily_mean = daily_collection.mean()  # Calculate mean for the day
+        daily_mean = daily_collection.mean()
         return daily_mean.set('day', day)
-
-    # Calculate the daily mean for each day
     daily_images = ee.List(grouped_by_day.map(calculate_daily_mean))
-    
     return ee.ImageCollection(daily_images)
 
 def aggregate_data_weekly(collection):
-    # Extract the start date of the week from the image date
-    collection = collection.map(lambda image: image.set(
-        'week_start', ee.Date(image.get('system:time_start'))
-            .advance(-ee.Date(image.get('system:time_start')).getRelative('day', 'week'), 'day')
-    ))
-    # Group images by week start date
+    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):
-        # Filter the collection by the specific week start date
         weekly_collection = collection.filter(ee.Filter.eq('week_start', week_start))
-        weekly_mean = weekly_collection.mean()  # Calculate mean for the week
+        weekly_mean = weekly_collection.mean()
         return weekly_mean.set('week_start', week_start)
-    
-    # Calculate the weekly mean for each week
     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):
-    # Filter the collection for the specific date range
     collection = collection.filterDate(start_date, end_date)
-    
-    # Extract month and year from the image date
     collection = collection.map(lambda image: image.set('month', ee.Date(image.get('system:time_start')).format('YYYY-MM')))
-    
-    # Group images by month
     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)
-
-    # Calculate the monthly mean for each month
     monthly_images = ee.List(grouped_by_month.map(calculate_monthly_mean))
-    
     return ee.ImageCollection(monthly_images)
-    
+
 def aggregate_data_yearly(collection):
-    # Extract year from the image date
     collection = collection.map(lambda image: image.set('year', ee.Date(image.get('system:time_start')).format('YYYY')))
-    
-    # Group images by year
     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)
-
-    # Calculate the yearly mean for each year
     yearly_images = ee.List(grouped_by_year.map(calculate_yearly_mean))
-    
     return ee.ImageCollection(yearly_images)
 
-# Function to calculate index based on the selected choice
-def calculate_index_for_period(image, roi, index_choice, reducer_choice, custom_formula):
-    if index_choice.lower() == 'ndvi':
-        return calculate_ndvi(image, roi, reducer_choice)
-    elif index_choice.lower() == 'ndwi':
-        return calculate_ndwi(image, roi, reducer_choice)
-    elif index_choice.lower() == 'average no₂':
-        mean_no2 = image.select('NO2').mean().rename('Average NO₂')
-        return mean_no2
-    elif index_choice.lower() == 'custom formula':
-        # Pass the custom formula here, not the index_choice
-        return calculate_custom_formula(image, roi, custom_formula, reducer_choice)
-    else:
-        st.write("Please Select any one option...."+ index_choice.lower())
-
-def aggregate_data_weekly(collection):
-    def set_week_start(image):
-        # Get the image timestamp
-        date = ee.Date(image.get('system:time_start'))
-        # Calculate days since the start of the week (0 = Monday, 6 = Sunday)
-        days_since_week_start = date.getRelative('day', 'week')
-        # Convert to ee.Number and negate it to get the offset to the week start
-        offset = ee.Number(days_since_week_start).multiply(-1)
-        # Advance the date by the negative offset to get the week start
-        week_start = date.advance(offset, 'day')
-        return image.set('week_start', week_start.format('YYYY-MM-dd'))  # Ensure string format
-    
-    # Apply the week start calculation to each image
-    collection = collection.map(set_week_start)
-    
-    # Group images by week start date
-    grouped_by_week = collection.aggregate_array('week_start').distinct()
-    
-    def calculate_weekly_mean(week_start):
-        # Filter the collection by the specific week start date
-        weekly_collection = collection.filter(ee.Filter.eq('week_start', week_start))
-        weekly_mean = weekly_collection.mean()  # Calculate mean for the week
-        return weekly_mean.set('week_start', week_start)
-    
-    # Calculate the weekly mean for each week
-    weekly_images = ee.List(grouped_by_week.map(calculate_weekly_mean))
-    return ee.ImageCollection(weekly_images)
-
-def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id, index_choice, reducer_choice, shape_type, aggregation_period, custom_formula=""):
+# Process aggregation 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):
     aggregated_results = []
     
-    if index_choice.lower() == 'custom_formula' and not custom_formula:
+    if not custom_formula:
         st.error("Custom formula cannot be empty. Please provide a formula.")
         return aggregated_results
     
@@ -536,15 +480,22 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                     continue
                 
                 location_name = row.get('name', f"Location_{idx}")
-                roi = ee.Geometry.Point([longitude, latitude])
+                
+                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])
                 
                 collection = ee.ImageCollection(dataset_id) \
                     .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
                     .filterBounds(roi)
                 
-                # Aggregate data based on the selected period
-                if aggregation_period.lower() == 'daily':
-                    collection = aggregate_data_daily(collection)
+                if aggregation_period.lower() == 'custom (start date to end date)':
+                    collection = aggregate_data_custom(collection)
                 elif aggregation_period.lower() == 'weekly':
                     collection = aggregate_data_weekly(collection)
                 elif aggregation_period.lower() == 'monthly':
@@ -552,21 +503,19 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                 elif aggregation_period.lower() == 'yearly':
                     collection = aggregate_data_yearly(collection)
                 
-                # Process each image in the collection
                 image_list = collection.toList(collection.size())
-                processed_weeks = set()  # Track processed weeks to avoid duplicates
+                processed_weeks = set()
                 for i in range(image_list.size().getInfo()):
                     image = ee.Image(image_list.get(i))
                     
-                    if aggregation_period.lower() == 'daily':
+                    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() == 'weekly':
                         timestamp = image.get('week_start')
                         period_label = 'Week'
-                        date = ee.String(timestamp).getInfo()  # Already formatted as YYYY-MM-dd
-                        # Skip if week is outside the date range or already processed
+                        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):
@@ -581,14 +530,14 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                         period_label = 'Year'
                         date = ee.Date(timestamp).format('YYYY').getInfo()
                     
-                    index_image = calculate_index_for_period(image, roi, index_choice, reducer_choice, custom_formula)
+                    index_image = calculate_index_for_period(image, roi, selected_bands, custom_formula, reducer_choice)
                     
                     try:
                         index_value = index_image.reduceRegion(
                             reducer=get_reducer(reducer_choice),
                             geometry=roi,
                             scale=30
-                        ).get(index_image.bandNames().get(0))
+                        ).get('custom_result')
                         
                         calculated_value = index_value.getInfo()
                         
@@ -619,6 +568,8 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                 
                 try:
                     roi = convert_to_ee_geometry(polygon_geometry)
+                    if not include_boundary:
+                        roi = roi.buffer(-30).bounds()
                 except ValueError as e:
                     st.warning(f"Skipping invalid polygon {polygon_name}: {e}")
                     continue
@@ -627,9 +578,8 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                     .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
                     .filterBounds(roi)
                 
-                # Aggregate data based on the selected period
-                if aggregation_period.lower() == 'daily':
-                    collection = aggregate_data_daily(collection)
+                if aggregation_period.lower() == 'custom (start date to end date)':
+                    collection = aggregate_data_custom(collection)
                 elif aggregation_period.lower() == 'weekly':
                     collection = aggregate_data_weekly(collection)
                 elif aggregation_period.lower() == 'monthly':
@@ -637,21 +587,19 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                 elif aggregation_period.lower() == 'yearly':
                     collection = aggregate_data_yearly(collection)
                 
-                # Process each image in the collection
                 image_list = collection.toList(collection.size())
-                processed_weeks = set()  # Track processed weeks to avoid duplicates
+                processed_weeks = set()
                 for i in range(image_list.size().getInfo()):
                     image = ee.Image(image_list.get(i))
                     
-                    if aggregation_period.lower() == 'daily':
+                    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() == 'weekly':
                         timestamp = image.get('week_start')
                         period_label = 'Week'
-                        date = ee.String(timestamp).getInfo()  # Already formatted as YYYY-MM-dd
-                        # Skip if week is outside the date range or already processed
+                        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):
@@ -666,14 +614,14 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                         period_label = 'Year'
                         date = ee.Date(timestamp).format('YYYY').getInfo()
                     
-                    index_image = calculate_index_for_period(image, roi, index_choice, reducer_choice, custom_formula)
+                    index_image = calculate_index_for_period(image, roi, selected_bands, custom_formula, reducer_choice)
                     
                     try:
                         index_value = index_image.reduceRegion(
                             reducer=get_reducer(reducer_choice),
                             geometry=roi,
                             scale=30
-                        ).get(index_image.bandNames().get(0))
+                        ).get('custom_result')
                         
                         calculated_value = index_value.getInfo()
                         
@@ -696,81 +644,76 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
     
     if aggregated_results:
         result_df = pd.DataFrame(aggregated_results)
-        if aggregation_period.lower() == 'daily':
-            aggregated_output = result_df.groupby('Location Name').agg({
-                'Latitude': 'first' if shape_type.lower() == 'point' else None,
-                'Longitude': 'first' if shape_type.lower() == 'point' else None,
+        if aggregation_period.lower() == 'custom (start date to end date)':
+            agg_dict = {
                 'Start Date': 'first',
                 'End Date': 'first',
                 'Calculated Value': 'mean'
-            }).reset_index()
-            # Remove None columns (for polygons)
-            aggregated_output = aggregated_output[[col for col in aggregated_output.columns if col is not None]]
+            }
+            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')
         else:
             return result_df.to_dict(orient='records')
-    
     return []
 
-# When the user clicks the process button, start the calculation
-if st.button(f"Calculate ({index_choice})"):
+# Button to trigger calculation
+if st.button(f"Calculate {custom_formula}"):
     if file_upload is not None:
-        if shape_type.lower() == "point":
-            results = process_aggregation(
-                locations_df,
-                start_date_str,
-                end_date_str,
-                dataset_id,
-                index_choice,
-                reducer_choice,
-                shape_type,
-                aggregation_period,
-                custom_formula
-            )
-            if results:
-                result_df = pd.DataFrame(results)
-                st.write(f"Processed Results Table ({aggregation_period}):")
-                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.spinner('')
-                st.success('Processing complete!')
-            else:
-                st.warning("No results were generated.")
-        
-        elif shape_type.lower() == "polygon":
+        if shape_type.lower() in ["point", "polygon"]:
             results = process_aggregation(
                 locations_df,
                 start_date_str,
                 end_date_str,
                 dataset_id,
-                index_choice,
+                selected_bands,
                 reducer_choice,
                 shape_type,
                 aggregation_period,
-                custom_formula
+                custom_formula,
+                kernel_size=kernel_size,
+                include_boundary=include_boundary
             )
             if results:
                 result_df = pd.DataFrame(results)
-                st.write(f"Processed Results Table ({aggregation_period}):")
+                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"
+                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.spinner('')
+                # Show an example calculation
+                if st.session_state.show_example and results:
+                    example_result = results[0]
+                    example_image = ee.ImageCollection(dataset_id).filterDate(start_date_str, end_date_str).first()
+                    example_roi = (
+                        ee.Geometry.Point([example_result['Longitude'], example_result['Latitude']]) 
+                        if shape_type.lower() == 'point' 
+                        else convert_to_ee_geometry(locations_df['geometry'].iloc[0])
+                    )
+                    example_values = {}
+                    for band in selected_bands:
+                        value = example_image.select(band).reduceRegion(
+                            reducer=get_reducer(reducer_choice),
+                            geometry=example_roi,
+                            scale=30
+                        ).get(band).getInfo()
+                        example_values[band] = float(value if value is not None else 0)
+                    example_formula = custom_formula
+                    for band in selected_bands:
+                        example_formula = example_formula.replace(band, str(example_values[band]))
+                    # st.write(f"Example Calculation: {custom_formula} -> {example_formula} = {example_result.get('Calculated Value', example_result.get('Aggregated Value'))}")
+                    st.session_state.show_example = False
                 st.success('Processing complete!')
             else:
-                st.warning("No results were generated.")
-        
+                st.warning("No results were generated. Check your inputs or formula.")
         else:
-            st.warning("Please upload a file.")
+            st.warning("Please upload a file to process.")
+    else:
+        st.warning("Please upload a file to proceed.")