update app.py

app.py

@@ -207,11 +207,12 @@ def aggregate_data_daily(collection):
 
 # Worker function for processing a single geometry
 def process_single_geometry(row, start_date_str, end_date_str, dataset_id, selected_bands, reducer_choice, shape_type, aggregation_period, custom_formula, kernel_size=None, include_boundary=None, default_scale=None):
+    image_count = 0  # Initialize image counter
     if shape_type.lower() == "point":
         latitude = row.get('latitude')
         longitude = row.get('longitude')
         if pd.isna(latitude) or pd.isna(longitude):
-            return None  # Skip invalid points
+            return None, 0  # Return 0 images for invalid points
         location_name = row.get('name', f"Location_{row.name}")
         if kernel_size == "3x3 Kernel":
             buffer_size = 45  # 90m x 90m
@@ -229,13 +230,17 @@ def process_single_geometry(row, start_date_str, end_date_str, dataset_id, selec
             if not include_boundary:
                 roi = roi.buffer(-30).bounds()
         except ValueError:
-            return None  # Skip invalid polygons
+            return None, 0  # Return 0 images for invalid polygons
 
     collection = ee.ImageCollection(dataset_id) \
         .filterDate(ee.Date(start_date_str), ee.Date(end_date_str)) \
         .filterBounds(roi) \
         .select(selected_bands)
 
+    # Get the count of images before aggregation
+    initial_count = collection.size().getInfo()
+    image_count += initial_count
+
     if aggregation_period.lower() == 'custom (start date to end date)':
         collection = aggregate_data_custom(collection)
     elif aggregation_period.lower() == 'daily':
@@ -298,7 +303,7 @@ def process_single_geometry(row, start_date_str, end_date_str, dataset_id, selec
         except Exception as e:
             st.error(f"Error retrieving value for {location_name}: {e}")
 
-    return aggregated_results
+    return aggregated_results, image_count  # Return both results and image count
 
 # Main processing function
 def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id, selected_bands, reducer_choice, shape_type, aggregation_period, custom_formula="", kernel_size=None, include_boundary=None, default_scale=None):
@@ -308,6 +313,7 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
         default_scale = collection.first().select(0).projection().nominalScale().getInfo()
         
     aggregated_results = []
+    total_images = 0  # Track total images processed
     total_steps = len(locations_df)
     progress_bar = st.progress(0)
     progress_text = st.empty()
@@ -335,13 +341,14 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
 
         completed = 0
         for future in as_completed(futures):
-            result = future.result()
+            result, image_count = future.result()
             if result:
                 aggregated_results.extend(result)
+                total_images += image_count
             completed += 1
             progress_percentage = completed / total_steps
             progress_bar.progress(progress_percentage)
-            progress_text.markdown(f"Processing: {int(progress_percentage * 100)}%")
+            progress_text.markdown(f"Processing: {int(progress_percentage * 100)}% (Total images: {total_images})")
 
     end_time = time.time()
     processing_time = end_time - start_time
@@ -359,10 +366,10 @@ def process_aggregation(locations_df, start_date_str, end_date_str, dataset_id,
                 agg_dict['Longitude'] = 'first'
             aggregated_output = result_df.groupby('Location Name').agg(agg_dict).reset_index()
             aggregated_output.rename(columns={'Calculated Value': 'Aggregated Value'}, inplace=True)
-            return aggregated_output.to_dict(orient='records'), processing_time
+            return aggregated_output.to_dict(orient='records'), processing_time, total_images
         else:
-            return result_df.to_dict(orient='records'), processing_time
-    return [], processing_time
+            return result_df.to_dict(orient='records'), processing_time, total_images
+    return [], processing_time, total_images
 
 # Streamlit App Logic
 st.markdown("<h5>Image Collection</h5>", unsafe_allow_html=True)
@@ -691,8 +698,8 @@ if st.button(f"Calculate {custom_formula}"):
         # Use a spinner to indicate data processing
         with st.spinner("Processing Data..."):
             try:
-                # Call the aggregation function and capture results and processing time
-                results, processing_time = process_aggregation(
+                # Call the aggregation function and capture results, processing time, and image count
+                results, processing_time, total_images = process_aggregation(
                     locations_df,
                     start_date_str,
                     end_date_str,
@@ -710,6 +717,7 @@ if st.button(f"Calculate {custom_formula}"):
                 if results:
                     result_df = pd.DataFrame(results)
                     st.write(f"Default Scale for Selected Dataset: {default_scale} meters")
+                    st.write(f"Total Images Processed: {total_images}")
                     st.write(f"Processed Results Table ({aggregation_period}) for Formula: {custom_formula}")
                     st.dataframe(result_df)
                     # Generate a downloadable CSV file
@@ -722,7 +730,7 @@ if st.button(f"Calculate {custom_formula}"):
                         mime='text/csv'
                     )
                     # Display processing time
-                    st.success(f"Processing complete! Total processing time: {processing_time:.2f} seconds.")
+                    st.success(f"Processing complete! Total processing time: {processing_time:.2f} seconds for {total_images} images.")
                 else:
                     st.warning("No results were generated. Check your inputs or formula.")
                     st.info(f"Total processing time: {processing_time:.2f} seconds.")  # Show processing time even if no results