Update add_indices

app.py

@@ -23,6 +23,7 @@ import xml.etree.ElementTree as ET
 def one_time_setup():
     """Initializes the Earth Engine API."""
     try:
+        # Attempt to initialize with default credentials
         ee.Initialize()
     except Exception as e:
         try:
@@ -36,11 +37,12 @@ def one_time_setup():
                 credentials = ee.ServiceAccountCredentials('ujjwal@ee-ujjwaliitd.iam.gserviceaccount.com', credentials_path)
                 ee.Initialize(credentials, project='ee-ujjwaliitd')
             else:
+                # If no credentials are found, re-raise the original exception
                 raise e
         except Exception as inner_e:
+            # If the fallback also fails, print the error
             print(f"Earth Engine initialization failed: {inner_e}")
-            # In a real app, you might want to show an error to the user here
-            # For this Gradio app, we'll let it proceed and fail gracefully later if EE is needed.
+
 
 def _process_spatial_data(data_bytes):
     """Core function to process bytes of a KML or GeoJSON file."""
@@ -78,7 +80,7 @@ def get_gdf_from_url(url):
     """Downloads and reads a KML/GeoJSON from a URL."""
     if not url or not url.strip():
         return None
-
+    
     # Handle Google Drive URLs
     if "drive.google.com" in url:
         if "/file/d/" in url:
@@ -173,39 +175,44 @@ def get_wayback_data():
     """Fetches and parses Wayback imagery data from ArcGIS."""
     try:
         url = "https://wayback.maptiles.arcgis.com/arcgis/rest/services/World_Imagery/MapServer/WMTS/1.0.0/WMTSCapabilities.xml"
-        response = requests.get(url)
-        response.raise_for_status()  # Ensure request was successful
-
-        # Parse XML
+        response = requests.get(url, timeout=30)
+        response.raise_for_status()
         root = ET.fromstring(response.content)
-
+        
+        # Define the namespaces found in the XML document
         ns = {
-            "wmts": "https://www.opengis.net/wmts/1.0",
-            "ows": "https://www.opengis.net/ows/1.1",
-            "xlink": "https://www.w3.org/1999/xlink",
+            "wmts": "http://www.opengis.net/wmts/1.0",
+            "ows": "http://www.opengis.net/ows/1.1",
         }
-
+        
         # Use a robust XPath to find all 'Layer' elements anywhere in the document.
-        # This is less brittle than specifying the full path.
-        layers = root.findall(".//wmts:Contents/wmts:Layer", ns)
-
+        layers = root.findall(".//wmts:Layer", ns)
+        
         layer_data = []
         for layer in layers:
-            title = layer.find("ows:Title", ns)
-            identifier = layer.find("ows:Identifier", ns)
-            resource = layer.find("wmts:ResourceURL", ns)  # Tile URL template
-
-            title_text = title.text if title is not None else "N/A"
-            identifier_text = identifier.text if identifier is not None else "N/A"
-            url_template = resource.get("template") if resource is not None else "N/A"
-
-            layer_data.append({"Title": title_text, "ResourceURL_Template": url_template})
+            title_element = layer.find("ows:Title", ns)
+            resource_element = layer.find("wmts:ResourceURL", ns)
+            
+            # Ensure elements and their attributes exist before trying to access them
+            if title_element is not None and resource_element is not None and title_element.text is not None:
+                template = resource_element.get("template")
+                if template:
+                    layer_data.append({
+                        "Title": title_element.text,
+                        "ResourceURL_Template": template
+                    })
+        
+        if not layer_data:
+            print("Warning: No valid layers with titles and resource URLs found in Wayback XML response.")
+            return pd.DataFrame()
 
         wayback_df = pd.DataFrame(layer_data)
-        wayback_df["date"] = pd.to_datetime(wayback_df["Title"].str.extract(r"(\d{4}-\d{2}-\d{2})").squeeze(), errors="coerce")
+        # Extract date and handle potential parsing errors by coercing them to NaT
+        wayback_df["date"] = pd.to_datetime(wayback_df["Title"].str.extract(r"(\d{4}-\d{2}-\d{2})")[0], errors="coerce")
+        # Drop rows where date could not be parsed
+        wayback_df.dropna(subset=['date'], inplace=True)
         wayback_df.set_index("date", inplace=True)
-        return wayback_df
-
+        return wayback_df.sort_index()
     except requests.exceptions.RequestException as e:
         print(f"Could not fetch Wayback data from URL: {e}")
         return pd.DataFrame()
@@ -216,7 +223,7 @@ def get_wayback_data():
         print(f"An unexpected error occurred in get_wayback_data: {e}")
         return pd.DataFrame() # Return empty dataframe on failure
 
-def add_indices(image, nir_band, red_band, blue_band, green_band, evi_vars):
+def add_indices(image, nir_band, red_band, blue_band, green_band, swir1_band, swir2_band, evi_vars):
     """Calculates and adds multiple vegetation indices to an Earth Engine image."""
     # It's safer to work with the image bands directly
     nir = image.select(nir_band).divide(10000)
@@ -242,16 +249,25 @@ def add_indices(image, nir_band, red_band, blue_band, green_band, evi_vars):
         }).rename('EVI2')
 
     # RandomForest (This part requires a pre-trained model asset in GEE)
-    # For demonstration, we'll return a constant image if asset is not available
     try:
-        table = ee.FeatureCollection('projects/in793-aq-nb-24330048/assets/cleanedVDI')
+        # FIX: Select and rename bands from the training data to match what the classifier expects.
+        table = ee.FeatureCollection('projects/in793-aq-nb-24330048/assets/cleanedVDI').select(
+            ["B2", "B4", "B8", "cVDI"],
+            ["Blue", "Red", "NIR", 'cVDI']
+        )
+        
+        bands = ['Blue', 'Red', 'NIR']
+        label = 'cVDI'
+        
         classifier = ee.Classifier.smileRandomForest(50).train(
             features=table,
-            classProperty='cVDI',
-            inputProperties=['Blue', 'Red', 'NIR']
+            classProperty=label,
+            inputProperties=bands,
         )
-        rf = image.select(['Blue', 'Red', 'NIR']).classify(classifier).multiply(0.2).add(0.1).rename('RandomForest')
-    except Exception:
+        # Classify the image. The image already has bands named 'Blue', 'Red', 'NIR' from the previous select.
+        rf = image.classify(classifier).multiply(ee.Number(0.2)).add(ee.Number(0.1)).rename('RandomForest')
+    except Exception as e:
+        print(f"Random Forest calculation failed: {e}") # More specific error message
         rf = ee.Image.constant(0).rename('RandomForest')
 
 
@@ -273,7 +289,7 @@ def add_indices(image, nir_band, red_band, blue_band, green_band, evi_vars):
 
 # --- Gradio App Logic ---
 
-# Initialize GEE and fetch wayback data once
+# Initialize GEE and fetch wayback data once at the start
 one_time_setup()
 WAYBACK_DF = get_wayback_data()
 
@@ -319,13 +335,12 @@ def process_and_display(file_obj, url_str, buffer_m, progress=gr.Progress()):
 
     progress(0.5, desc="Generating map and stats...")
 
-    # Create map - initialize without a specific location
+    # Create map
     m = folium.Map()
-
+    
     if not WAYBACK_DF.empty:
-        # Select the last row, which is the most recent date after sorting
-        latest_item = WAYBACK_DF.iloc[0]
-        print(latest_item)
+        # The DataFrame is already sorted by date, so the last item is the latest.
+        latest_item = WAYBACK_DF.iloc[-1]
         wayback_url = (
             latest_item["ResourceURL_Template"]
             .replace("{TileMatrixSet}", "GoogleMapsCompatible")
@@ -338,13 +353,13 @@ def process_and_display(file_obj, url_str, buffer_m, progress=gr.Progress()):
             attr=f"Esri, i-cubed, USDA, USGS, AEX, GeoEye, Getmapping, Aerogrid, IGN, IGP, UPR-EGP, and the GIS User Community | Imagery Date: {latest_item.name.strftime('%Y-%m-%d')}",
             name="Latest Esri Satellite"
         ).add_to(m)
-
+        
     # Add geometries to the map
     m = add_geometry_to_map(m, geometry_gdf, buffer_geometry_gdf, opacity=0.3)
-
+    
     # Add a layer control panel
     m.add_child(folium.LayerControl())
-
+    
     # Fit the map view to the bounds of the geometry
     bounds = geometry_gdf.to_crs(epsg=4326).total_bounds
     map_bounds = [[bounds[1], bounds[0]], [bounds[3], bounds[2]]] # Format: [[south, west], [north, east]]
@@ -365,11 +380,15 @@ def process_and_display(file_obj, url_str, buffer_m, progress=gr.Progress()):
     progress(1, desc="Done!")
     return m._repr_html_(), None, stats_df, geometry_json, buffer_geometry_json
 
+
 def calculate_indices(
     geometry_json, buffer_geometry_json, veg_indices, evi_vars, date_range,
     min_year, max_year, progress=gr.Progress()
 ):
     """Calculates vegetation indices based on user inputs."""
+    # **FIX**: Ensure GEE is initialized before making any calls.
+    one_time_setup()
+    
     if not all([geometry_json, buffer_geometry_json, veg_indices]):
         return "Please process a file and select at least one index first.", None, None, None
 
@@ -381,7 +400,7 @@ def calculate_indices(
         # Convert to EE geometry
         ee_geometry = ee.Geometry(json.loads(geometry_gdf.to_crs(4326).to_json())['features'][0]['geometry'])
         buffer_ee_geometry = ee.Geometry(json.loads(buffer_geometry_gdf.to_crs(4326).to_json())['features'][0]['geometry'])
-
+        
         # Date ranges
         start_day, start_month = date_range[0].day, date_range[0].month
         end_day, end_month = date_range[1].day, date_range[1].month
@@ -394,10 +413,10 @@ def calculate_indices(
         collection = (
             ee.ImageCollection("COPERNICUS/S2_SR_HARMONIZED")
             .select(
-                ["B2", "B3", "B4", "B8", "MSK_CLDPRB"],
-                ["Blue", "Green", "Red", "NIR", "MSK_CLDPRB"]
+                ["B2", "B3", "B4", "B8", "B11", "B12", "MSK_CLDPRB"],
+                ["Blue", "Green", "Red", "NIR", "SWIR1", "SWIR2",  "MSK_CLDPRB"]
             )
-            .map(lambda img: add_indices(img, 'NIR', 'Red', 'Blue', 'Green', evi_vars))
+            .map(lambda img: add_indices(img, 'NIR', 'Red', 'Blue', 'Green', "SWIR1", "SWIR2", evi_vars))
         )
 
         result_rows = []
@@ -411,11 +430,21 @@ def calculate_indices(
             row = {'daterange': f"{start_date}_to_{end_date}"}
             for veg_index in veg_indices:
                 mosaic = filtered_collection.qualityMosaic(veg_index)
-                mean_val = mosaic.reduceRegion(reducer=ee.Reducer.mean(), geometry=ee_geometry, scale=10, maxPixels=1e9).get(veg_index).getInfo()
-                buffer_mean_val = mosaic.reduceRegion(reducer=ee.Reducer.mean(), geometry=buffer_ee_geometry, scale=10, maxPixels=1e9).get(veg_index).getInfo()
-                row[veg_index] = mean_val
-                row[f"{veg_index}_buffer"] = buffer_mean_val
-                row[f"{veg_index}_ratio"] = (mean_val / buffer_mean_val) if buffer_mean_val else 0
+                
+                mean_dict = mosaic.reduceRegion(reducer=ee.Reducer.mean(), geometry=ee_geometry, scale=10, maxPixels=1e9).getInfo()
+                mean_val = mean_dict.get(veg_index) if mean_dict else None
+
+                buffer_mean_dict = mosaic.reduceRegion(reducer=ee.Reducer.mean(), geometry=buffer_ee_geometry, scale=10, maxPixels=1e9).getInfo()
+                buffer_mean_val = buffer_mean_dict.get(veg_index) if buffer_mean_dict else None
+
+                row[veg_index] = mean_val if mean_val is not None else np.nan
+                row[f"{veg_index}_buffer"] = buffer_mean_val if buffer_mean_val is not None else np.nan
+                
+                if mean_val is not None and buffer_mean_val is not None and buffer_mean_val != 0:
+                    row[f"{veg_index}_ratio"] = mean_val / buffer_mean_val
+                else:
+                    row[f"{veg_index}_ratio"] = np.nan
+                    
             result_rows.append(row)
 
         if not result_rows:
@@ -427,14 +456,17 @@ def calculate_indices(
         # Create plots
         plots = []
         for veg_index in veg_indices:
-            plot_df = result_df[[veg_index, f"{veg_index}_buffer", f"{veg_index}_ratio"]]
-            fig = px.line(plot_df, x=plot_df.index, y=plot_df.columns, markers=True, title=f"{veg_index} Time Series")
-            fig.update_layout(xaxis_title="Year", yaxis_title="Index Value")
-            plots.append(fig)
+            plot_df = result_df[[veg_index, f"{veg_index}_buffer", f"{veg_index}_ratio"]].dropna()
+            if not plot_df.empty:
+                fig = px.line(plot_df, x=plot_df.index, y=plot_df.columns, markers=True, title=f"{veg_index} Time Series")
+                fig.update_layout(xaxis_title="Year", yaxis_title="Index Value")
+                plots.append(fig)
 
         return None, result_df, plots, "Calculation complete."
 
     except Exception as e:
+        import traceback
+        traceback.print_exc()
         return f"An error occurred during calculation: {e}", None, None, None
 
 
@@ -498,7 +530,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Kamlan: KML Analyzer") as demo:
 
 
     # --- Event Handlers ---
-
+    
     def process_on_load(request: gr.Request):
         """Checks for a 'file_url' query parameter when the app loads and populates the URL input field."""
         file_url = request.query_params.get("file_url")
@@ -542,7 +574,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Kamlan: KML Analyzer") as demo:
             # Catch any other unexpected errors during the process
             return f"An error occurred in the calculation wrapper: {e}", None, None
 
-    # **FIX**: Cleaned up the outputs to have a direct one-to-one mapping.
     calculate_button.click(
         fn=calculate_wrapper,
         inputs=[
@@ -554,7 +585,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Kamlan: KML Analyzer") as demo:
         outputs=[results_info_box, timeseries_table, plot_output]
     )
 
-
     gr.HTML("""
         <div style="text-align: center; margin-top: 20px;">
             <p>Developed by <a href="https://sustainability-lab.github.io/">Sustainability Lab</a>, <a href="https://www.iitgn.ac.in/">IIT Gandhinagar</a></p>
@@ -563,4 +593,4 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Kamlan: KML Analyzer") as demo:
     """)
 
 if __name__ == "__main__":
-    demo.launch(debug=True)
+    demo.launch(debug=True)