terrakio-core 0.3.7__tar.gz → 0.3.9__tar.gz

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: terrakio-core
-Version: 0.3.7
+Version: 0.3.9
 Summary: Core components for Terrakio API clients
 Author-email: Yupeng Chao <yupeng@haizea.com.au>
 Project-URL: Homepage, https://github.com/HaizeaAnalytics/terrakio-python-api
@@ -22,6 +22,7 @@ Requires-Dist: xarray>=2023.1.0
 Requires-Dist: shapely>=2.0.0
 Requires-Dist: geopandas>=0.13.0
 Requires-Dist: google-cloud-storage>=2.0.0
+Requires-Dist: scipy>=1.7.0
 Requires-Dist: nest_asyncio
 Provides-Extra: ml
 Requires-Dist: torch>=2.7.1; extra == "ml"

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "terrakio-core"
-version = "0.3.7"
+version = "0.3.9"
 authors = [
     {name = "Yupeng Chao", email = "yupeng@haizea.com.au"},
 ]
@@ -29,6 +29,7 @@ dependencies = [
     "shapely>=2.0.0",
     "geopandas>=0.13.0",
     "google-cloud-storage>=2.0.0",
+    "scipy>=1.7.0",
     "nest_asyncio",
 ]
 

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core/__init__.py

@@ -5,12 +5,12 @@ Terrakio Core
 Core components for Terrakio API clients.
 """
 
-__version__ = "0.3.7"
+__version__ = "0.3.9"
 
 from .async_client import AsyncClient
-from .sync_client import SyncClient
+from .sync_client import SyncClient as Client
 
 __all__ = [
     "AsyncClient", 
-    "SyncClient"
+    "Client"
 ]

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core/async_client.py

@@ -90,7 +90,6 @@ class AsyncClient(BaseClient):
         """Parse response based on content type."""
         content_type = response.headers.get('content-type', '').lower()
         content = await response.read()
-
         if 'json' in content_type:
             return json.loads(content.decode('utf-8'))
         elif 'csv' in content_type:
@@ -117,7 +116,6 @@ class AsyncClient(BaseClient):
                 except aiohttp.ClientError as e:
                     raise APIError(f"Request failed: {e}")
         else:
-            # this means that we used the with statement, and we already have a session
             try:
                 async with self._session.request(method, url, **kwargs) as response:
                     response.raise_for_status()
@@ -131,9 +129,9 @@ class AsyncClient(BaseClient):
         feature: Union[Dict[str, Any], ShapelyGeometry],
         in_crs: str = "epsg:4326",
         out_crs: str = "epsg:4326",
-        output: str = "csv",
         resolution: int = -1,
         geom_fix: bool = False,
+        validated: bool = True,
         **kwargs
     ):
         """
@@ -144,9 +142,9 @@ class AsyncClient(BaseClient):
             feature (Union[Dict[str, Any], ShapelyGeometry]): The geographic feature
             in_crs (str): Input coordinate reference system
             out_crs (str): Output coordinate reference system
-            output (str): Output format ('csv' or 'netcdf')
             resolution (int): Resolution parameter
             geom_fix (bool): Whether to fix the geometry (default False)
+            validated (bool): Whether to use validated data (default True)
             **kwargs: Additional parameters to pass to the WCS request
             
         Returns:
@@ -165,10 +163,11 @@ class AsyncClient(BaseClient):
             "feature": feature,
             "in_crs": in_crs,
             "out_crs": out_crs,
-            "output": output,
+            "output": "netcdf",
             "resolution": resolution,
             "expr": expr,
             "buffer": geom_fix,
+            "validated": validated,
             **kwargs
         }
         return await self._terrakio_request("POST", "geoquery", json=payload)

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core/client.py

@@ -22,10 +22,12 @@ class BaseClient():
         self.key = api_key
 
         config = read_config_file( DEFAULT_CONFIG_FILE, logger = self.logger)
+        
         if self.url is None:
             self.url = config.get('url')
-            
-        self.key = config.get('key')
+        
+        if self.key is None:
+            self.key = config.get('key')
 
         self.token = config.get('token')
 

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core/convenience_functions/convenience_functions.py

@@ -9,6 +9,8 @@ from ..exceptions import APIError, ConfigurationError
 from ..helper.bounded_taskgroup import BoundedTaskGroup
 from ..helper.tiles import tiles
 import uuid
+import xarray as xr
+
 
 async def zonal_stats(
         client,
@@ -35,7 +37,8 @@ async def zonal_stats(
         resolution (int): Resolution parameter
         geom_fix (bool): Whether to fix the geometry (default False)
     Returns:
-        geopandas.GeoDataFrame: GeoDataFrame with added columns for results, or None if inplace=True
+        geopandas.GeoDataFrame: GeoDataFrame with variable dataarrays in separate columns.
+                               Each row represents one geometry with full time-dimensional dataarrays.
 
     Raises:
         ValueError: If concurrency is too high
@@ -51,7 +54,7 @@ async def zonal_stats(
     completed_count = 0
     lock = asyncio.Lock()
     
-    async def process_geometry(geom, index):
+    async def process_geometry(geom):
         """Process a single geometry"""
         nonlocal completed_count
         
@@ -59,19 +62,20 @@ async def zonal_stats(
             feature = {
                 "type": "Feature",
                 "geometry": mapping(geom),
-                "properties": {"index": index}
+                "properties": {}
             }
-            result = await client.geoquery(expr=expr, feature=feature, output="csv",
+            # Request xarray dataset
+            result = await client.geoquery(expr=expr, feature=feature,
                                         in_crs=in_crs, out_crs=out_crs, resolution=resolution, geom_fix=geom_fix)
-            
             if isinstance(result, dict) and result.get("error"):
-                error_msg = f"Request {index} failed: {result.get('error_message', 'Unknown error')}"
+                error_msg = f"Request failed: {result.get('error_message', 'Unknown error')}"
                 if result.get('status_code'):
-                    error_msg = f"Request {index} failed with status {result['status_code']}: {result.get('error_message', 'Unknown error')}"
+                    error_msg = f"Request failed with status {result['status_code']}: {result.get('error_message', 'Unknown error')}"
                 raise APIError(error_msg)
             
-            if isinstance(result, pd.DataFrame):
-                result['_geometry_index'] = index
+            # Ensure we got an xarray Dataset
+            if not isinstance(result, xr.Dataset):
+                raise ValueError(f"Expected xarray Dataset, got {type(result)}")
             
             async with lock:
                 completed_count += 1
@@ -88,11 +92,11 @@ async def zonal_stats(
     try:
         async with BoundedTaskGroup(max_concurrency=conc) as tg:
             tasks = [
-                tg.create_task(process_geometry(gdf.geometry.iloc[idx], idx))
+                tg.create_task(process_geometry(gdf.geometry.iloc[idx]))
                 for idx in range(len(gdf))
             ]
         all_results = [task.result() for task in tasks]
-        
+
     except* Exception as eg:
         for e in eg.exceptions:
             if hasattr(e, 'response'):
@@ -100,73 +104,51 @@ async def zonal_stats(
         raise
     
     client.logger.info("All requests completed! Processing results...")
+
     
     if not all_results:
         raise ValueError("No valid results were returned for any geometry")
-        
-    combined_df = pd.concat(all_results, ignore_index=True)
     
-    has_time = 'time' in combined_df.columns
+
+    result_rows = []
+    geometries = []
     
-    if has_time:
-        if '_geometry_index' not in combined_df.columns:
-            raise ValueError("Missing geometry index in results")
-        
-        combined_df.set_index(['_geometry_index', 'time'], inplace=True)
+    # Results should be in the same order as input geometries
+    for i, dataset in enumerate(all_results):
+        # Get the original geometry by index
+        original_geom = gdf.geometry.iloc[i]
+        # Create single row for this geometry
+        new_row = {}
+                 
+        # Copy original GeoDataFrame attributes
+        for col in gdf.columns:
+            if col != 'geometry':
+                new_row[col] = gdf.iloc[i][col]
+        # Store the full dataarray for each variable (with time dimension intact)
+        data_vars = list(dataset.data_vars.keys())
+        for var_name in data_vars:
+            var_data = dataset[var_name]
+            new_row[f'{var_name}_dataarray'] = var_data
+        result_rows.append(new_row)
+        geometries.append(original_geom)
+    # Create the result GeoDataFrame with default integer index
+    result_gdf = GeoDataFrame(result_rows, geometry=geometries)
+    if inplace:
+        # Clear original gdf and replace with result_gdf content
+        gdf.drop(gdf.index, inplace=True)
+        gdf.drop(gdf.columns, axis=1, inplace=True)
         
-        result_cols = combined_df.columns
+        # Copy all data from result_gdf to gdf
+        for col in result_gdf.columns:
+            gdf[col] = result_gdf[col].values
         
-        result_rows = []
-        geometries = []
+        # Ensure it remains a GeoDataFrame with correct geometry
+        gdf.geometry = result_gdf.geometry
         
-        for (geom_idx, time_val), row in combined_df.iterrows():
-            new_row = {}
-            
-            for col in gdf.columns:
-                if col != 'geometry':
-                    new_row[col] = gdf.loc[geom_idx, col]
-            
-            for col in result_cols:
-                new_row[col] = row[col]
-            
-            result_rows.append(new_row)
-            geometries.append(gdf.geometry.iloc[geom_idx])
-        
-        multi_index = pd.MultiIndex.from_tuples(
-            combined_df.index.tolist(),
-            names=['geometry_index', 'time']
-        )
-        
-        result_gdf = GeoDataFrame(
-            result_rows, 
-            geometry=geometries,
-            index=multi_index
-        )
-        
-        if inplace:
-            return result_gdf
-        else:
-            return result_gdf
+        return None
     else:
-        result_gdf = gdf.copy() if not inplace else gdf
-        
-        result_cols = [col for col in combined_df.columns if col not in ['_geometry_index']]
-        
-        geom_idx_to_row = {}
-        for idx, row in combined_df.iterrows():
-            geom_idx = int(row['_geometry_index'])
-            geom_idx_to_row[geom_idx] = row
-        
-        for col in result_cols:
-            if col not in result_gdf.columns:
-                result_gdf[col] = None
-            
-            for geom_idx, row in geom_idx_to_row.items():
-                result_gdf.loc[geom_idx, col] = row[col]
-        if inplace:
-            return None
-        else:
-            return result_gdf
+
+        return result_gdf
 
 async def create_dataset_file(
     client,

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core/sync_client.py

@@ -166,7 +166,6 @@ class SyncClient:
         feature: Union[Dict[str, Any], ShapelyGeometry],
         in_crs: str = "epsg:4326",
         out_crs: str = "epsg:4326",
-        output: str = "csv",
         resolution: int = -1,
         geom_fix: bool = False,
         **kwargs
@@ -179,7 +178,6 @@ class SyncClient:
             feature (Union[Dict[str, Any], ShapelyGeometry]): The geographic feature
             in_crs (str): Input coordinate reference system
             out_crs (str): Output coordinate reference system
-            output (str): Output format ('csv' or 'netcdf')
             resolution (int): Resolution parameter
             geom_fix (bool): Whether to fix the geometry (default False)
             **kwargs: Additional parameters to pass to the WCS request
@@ -195,7 +193,7 @@ class SyncClient:
             feature=feature,
             in_crs=in_crs,
             out_crs=out_crs,
-            output=output,
+            output="netcdf",
             resolution=resolution,
             geom_fix=geom_fix,
             **kwargs

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: terrakio-core
-Version: 0.3.7
+Version: 0.3.9
 Summary: Core components for Terrakio API clients
 Author-email: Yupeng Chao <yupeng@haizea.com.au>
 Project-URL: Homepage, https://github.com/HaizeaAnalytics/terrakio-python-api
@@ -22,6 +22,7 @@ Requires-Dist: xarray>=2023.1.0
 Requires-Dist: shapely>=2.0.0
 Requires-Dist: geopandas>=0.13.0
 Requires-Dist: google-cloud-storage>=2.0.0
+Requires-Dist: scipy>=1.7.0
 Requires-Dist: nest_asyncio
 Provides-Extra: ml
 Requires-Dist: torch>=2.7.1; extra == "ml"

{terrakio_core-0.3.7 → terrakio_core-0.3.9}/terrakio_core.egg-info/requires.txt

@@ -5,6 +5,7 @@ xarray>=2023.1.0
 shapely>=2.0.0
 geopandas>=0.13.0
 google-cloud-storage>=2.0.0
+scipy>=1.7.0
 nest_asyncio
 
 [ml]