terrakio-core 0.4.96__tar.gz → 0.4.97__tar.gz

{terrakio_core-0.4.96 → terrakio_core-0.4.97}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: terrakio-core
-Version: 0.4.96
+Version: 0.4.97
 Summary: Core package for the terrakio-python-api
 Requires-Python: >=3.11
 Requires-Dist: aiofiles>=24.1.0

{terrakio_core-0.4.96 → terrakio_core-0.4.97}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "terrakio-core"
-version = "0.4.96"
+version = "0.4.97"
 description = "Core package for the terrakio-python-api"
 readme = "README.md"
 requires-python = ">=3.11"

{terrakio_core-0.4.96 → terrakio_core-0.4.97}/terrakio_core/__init__.py

@@ -5,7 +5,7 @@ Terrakio Core
 Core components for Terrakio API clients.
 """
 
-__version__ = "0.4.96"
+__version__ = "0.4.97"
 
 from .async_client import AsyncClient
 from .sync_client import SyncClient as Client

{terrakio_core-0.4.96 → terrakio_core-0.4.97}/terrakio_core/convenience_functions/zonal_stats.py

@@ -513,6 +513,35 @@ async def zonal_stats(
         job_name = await client.mass_stats.track_job([mass_stats_id])
         job_name = job_name[mass_stats_id]["name"]
         cloud_files_object = cloud_object(job_id = mass_stats_id, job_name = job_name, client = client)
+        
+        # Attach id column behavior to cloud object via a wrapper method
+        async def _head_with_id(n = 5):
+            result_gdf = await cloud_files_object._head_async(n)
+            if id_column is not None and id_column in gdf.columns:
+                geometry_to_id = {geom.wkb: id_val for geom, id_val in zip(gdf.geometry, gdf[id_column])}
+                if hasattr(result_gdf.index, 'names') and 'geometry' in result_gdf.index.names:
+                    if isinstance(result_gdf.index, pd.MultiIndex):
+                        geometry_index = result_gdf.index.get_level_values('geometry')
+                    else:
+                        geometry_index = result_gdf.index
+                    id_values = [geometry_to_id.get(geom.wkb) for geom in geometry_index]
+                    result_gdf[id_column] = id_values
+                    result_gdf = result_gdf.reset_index()
+                    if 'time' in result_gdf.columns:
+                        result_gdf = result_gdf.set_index([id_column, 'geometry', 'time'])
+                    else:
+                        result_gdf = result_gdf.set_index([id_column, 'geometry'])
+                else:
+                    id_values = [geometry_to_id.get(geom.wkb) for geom in result_gdf['geometry']]
+                    result_gdf[id_column] = id_values
+                    if 'time' in result_gdf.columns:
+                        result_gdf = result_gdf.set_index([id_column, 'geometry', 'time'])
+                    else:
+                        result_gdf = result_gdf.set_index([id_column, 'geometry'])
+            return result_gdf
+
+        # Monkey-patch a convenience method without modifying original class contract
+        cloud_files_object.head_with_id = lambda n=5: asyncio.run(_head_with_id(n))
         return cloud_files_object
     
     quries = []
@@ -539,5 +568,33 @@ async def zonal_stats(
             "is_cloud_backed": False,
         } 
         gdf_with_datasets = expand_on_variables_and_time(gdf_with_datasets)
+        
+        # If an id_column is provided, attach it to the result and include in the index
+        if id_column is not None and id_column in gdf.columns:
+            # Build a mapping from input geometries to id values (use WKB for robust equality)
+            geometry_to_id = {geom.wkb: id_val for geom, id_val in zip(gdf.geometry, gdf[id_column])}
+
+            # Determine geometry values in the result (index may be geometry or (geometry, time))
+            if hasattr(gdf_with_datasets.index, 'names') and 'geometry' in gdf_with_datasets.index.names:
+                if isinstance(gdf_with_datasets.index, pd.MultiIndex):
+                    geometry_index = gdf_with_datasets.index.get_level_values('geometry')
+                else:
+                    geometry_index = gdf_with_datasets.index
+                id_values = [geometry_to_id.get(geom.wkb) for geom in geometry_index]
+                gdf_with_datasets[id_column] = id_values
+                # Reset index to control index composition precisely, then set to desired levels
+                gdf_with_datasets = gdf_with_datasets.reset_index()
+                if 'time' in gdf_with_datasets.columns:
+                    gdf_with_datasets = gdf_with_datasets.set_index([id_column, 'geometry', 'time'])
+                else:
+                    gdf_with_datasets = gdf_with_datasets.set_index([id_column, 'geometry'])
+            else:
+                # geometry exists as a column
+                id_values = [geometry_to_id.get(geom.wkb) for geom in gdf_with_datasets['geometry']]
+                gdf_with_datasets[id_column] = id_values
+                if 'time' in gdf_with_datasets.columns:
+                    gdf_with_datasets = gdf_with_datasets.set_index([id_column, 'geometry', 'time'])
+                else:
+                    gdf_with_datasets = gdf_with_datasets.set_index([id_column, 'geometry'])
     return gdf_with_datasets
 

{terrakio_core-0.4.96 → terrakio_core-0.4.97}/terrakio_core/endpoints/dataset_management.py

@@ -69,7 +69,7 @@ class DatasetManagement:
             name: Name of the dataset (required)
             collection: Dataset collection (default: 'terrakio-datasets')
             products: List of products
-            dates_iso8601: List of dates
+            dates_iso8601: List of dates (will be automatically sorted chronologically)
             bucket: Storage bucket
             path: Storage path
             data_type: Data type
@@ -142,7 +142,7 @@ class DatasetManagement:
             append: Whether to append data or replace (default: True)
             collection: Dataset collection (default: 'terrakio-datasets')
             products: List of products
-            dates_iso8601: List of dates
+            dates_iso8601: List of dates (will be automatically sorted chronologically)
             bucket: Storage bucket
             path: Storage path
             data_type: Data type
@@ -162,6 +162,10 @@ class DatasetManagement:
         Raises:
             APIError: If the API request fails
         """
+        # Sort dates_iso8601 chronologically if provided
+        if dates_iso8601 is not None:
+            dates_iso8601 = sorted(dates_iso8601)
+
         params = {"collection": collection, "append": str(append).lower()}
         payload = {"name": name}
         param_mapping = {
@@ -215,7 +219,7 @@ class DatasetManagement:
             append: Whether to append data or replace (default: True)
             collection: Dataset collection (default: 'terrakio-datasets')
             products: List of products
-            dates_iso8601: List of dates
+            dates_iso8601: List of dates (will be automatically sorted chronologically)
             bucket: Storage bucket
             path: Storage path
             data_type: Data type
@@ -236,6 +240,10 @@ class DatasetManagement:
         Raises:
             APIError: If the API request fails
         """
+        # Sort dates_iso8601 chronologically if provided
+        if dates_iso8601 is not None:
+            dates_iso8601 = sorted(dates_iso8601)
+
         params = {"collection": collection, "append": str(append).lower()}
         payload = {"name": name}
         param_mapping = {
@@ -289,7 +297,7 @@ class DatasetManagement:
             name: Name of the dataset (required)
             collection: Dataset collection (default: 'terrakio-datasets')
             products: List of products
-            dates_iso8601: List of dates
+            dates_iso8601: List of dates (will be automatically sorted chronologically)
             bucket: Storage bucket
             path: Storage path
             data_type: Data type