terrakio-core 0.4.96__tar.gz → 0.4.98__tar.gz

{terrakio_core-0.4.96 → terrakio_core-0.4.98}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: terrakio-core
-Version: 0.4.96
+Version: 0.4.98
 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-0.4.98}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "terrakio-core"
-version = "0.4.96"
+version = "0.4.98"
 description = "Core package for the terrakio-python-api"
 readme = "README.md"
 requires-python = ">=3.11"

{terrakio_core-0.4.96 → terrakio_core-0.4.98}/terrakio_core/__init__.py

@@ -5,7 +5,7 @@ Terrakio Core
 Core components for Terrakio API clients.
 """
 
-__version__ = "0.4.96"
+__version__ = "0.4.98"
 
 from .async_client import AsyncClient
 from .sync_client import SyncClient as Client

{terrakio_core-0.4.96 → terrakio_core-0.4.98}/terrakio_core/convenience_functions/zonal_stats.py

@@ -9,18 +9,18 @@ from typing import Optional
 # Third-party library imports
 import aiohttp
 import geopandas as gpd
-import nest_asyncio
 import pandas as pd
 import pyproj
 import xarray as xr
 from geopandas import GeoDataFrame
 from shapely.geometry import box, mapping, shape
 from shapely.ops import transform
+import threading
+from concurrent.futures import ThreadPoolExecutor
 
 # Local imports
 from .geoquries import request_geoquery_list
 
-nest_asyncio.apply()
 class cloud_object(gpd.GeoDataFrame):
     """
     This class is a class used for cloud
@@ -36,12 +36,51 @@ class cloud_object(gpd.GeoDataFrame):
         self.client = client
         self.job_name = job_name
 
+    def __repr__(self):
+        return (
+            f"<CloudZonalStats job_id='{self.job_id}', job_name='{self.job_name}'>\n"
+            f"Call .head(n) to fetch a preview GeoDataFrame when the job completes."
+        )
+
+    def _repr_html_(self):
+        # Jupyter HTML-friendly representation to avoid auto-rendering an empty DataFrame
+        return (
+            f"<div style='font-family:system-ui,Segoe UI,Helvetica,Arial,sans-serif'>"
+            f"<strong>Cloud Zonal Stats</strong><br/>"
+            f"job_id: <code>{self.job_id}</code><br/>"
+            f"job_name: <code>{self.job_name}</code><br/>"
+            f"<em>Use <code>.head(n)</code> to retrieve a preview once the job is completed.</em>"
+            f"</div>"
+        )
+
     def head(self, n = 5):
         """
         Returns the first n files stored in the cloud bucket.
         """
-        return asyncio.run(self._head_async(n))
+        # Detect if we're inside an existing event loop (e.g., Jupyter)
+        in_running_loop = False
+        try:
+            asyncio.get_running_loop()
+            in_running_loop = True
+        except RuntimeError:
+            in_running_loop = False
 
+        if in_running_loop:
+            # Run the async function in a separate thread with its own loop
+            def run_async_in_thread():
+                new_loop = asyncio.new_event_loop()
+                try:
+                    return new_loop.run_until_complete(self._head_async(n))
+                finally:
+                    new_loop.close()
+            
+            with ThreadPoolExecutor(max_workers=1) as executor:
+                future = executor.submit(run_async_in_thread)
+                return future.result()
+        else:
+            # No running loop - safe to use asyncio.run
+            return asyncio.run(self._head_async(n))
+        
     async def _head_async(self, n = 5):
         """
         Returns the first n files stored in the cloud bucket.
@@ -120,12 +159,54 @@ class cloud_object(gpd.GeoDataFrame):
                             })
                             
                             self.client.logger.info(f"Created GeoDataFrame with {len(gdf)} rows")
+
+                            # Derive id values from json metadata (prefer 'file', fallback to 'group')
+                            id_values = []
+                            for i in range(min_length):
+                                entry = json_data[i] if i < len(json_data) else {}
+                                id_candidate = entry.get('file') or entry.get('group') or ''
+                                if isinstance(id_candidate, str) and id_candidate.startswith('file_'):
+                                    id_val = id_candidate[len('file_'):]
+                                elif isinstance(id_candidate, str) and id_candidate.startswith('group_'):
+                                    id_val = id_candidate[len('group_'):]
+                                else:
+                                    id_val = str(id_candidate) if id_candidate else str(i)
+                                id_values.append(id_val)
+
+                            # Geometry to id mapping using WKB to avoid precision issues
+                            geom_to_id = {geometries[i].wkb: id_values[i] for i in range(min_length)}
+
                             try:
                                 expanded_gdf = expand_on_variables_and_time(gdf)
+
+                                # Attach id as first index level, geometry second, time third if present
+                                if hasattr(expanded_gdf.index, 'names') and 'geometry' in expanded_gdf.index.names:
+                                    if isinstance(expanded_gdf.index, pd.MultiIndex):
+                                        geometry_index = expanded_gdf.index.get_level_values('geometry')
+                                    else:
+                                        geometry_index = expanded_gdf.index
+                                    id_col = [geom_to_id.get(geom.wkb) for geom in geometry_index]
+                                    expanded_gdf['id'] = id_col
+                                    expanded_gdf = expanded_gdf.reset_index()
+                                    if 'time' in expanded_gdf.columns:
+                                        expanded_gdf = expanded_gdf.set_index(['id', 'geometry', 'time'])
+                                    else:
+                                        expanded_gdf = expanded_gdf.set_index(['id', 'geometry'])
+                                else:
+                                    # geometry exists as a column
+                                    id_col = [geom_to_id.get(geom.wkb) for geom in expanded_gdf['geometry']]
+                                    expanded_gdf['id'] = id_col
+                                    if 'time' in expanded_gdf.columns:
+                                        expanded_gdf = expanded_gdf.set_index(['id', 'geometry', 'time'])
+                                    else:
+                                        expanded_gdf = expanded_gdf.set_index(['id', 'geometry'])
+
                                 return expanded_gdf
                             except NameError:
                                 self.client.logger.warning("expand_on_variables_and_time function not found, returning raw GeoDataFrame")
-                                return gdf
+                                # Set id on raw gdf and index appropriately
+                                gdf['id'] = id_values
+                                return gdf.set_index(['id', 'geometry'])
                                 
                         else:
                             self.client.logger.warning(f"Failed to download geometry data: HTTP {response.status}")
@@ -513,6 +594,7 @@ 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)
+
         return cloud_files_object
     
     quries = []
@@ -539,5 +621,33 @@ 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-0.4.98}/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