terrakio-core 0.4.7__py3-none-any.whl → 0.4.93__py3-none-any.whl

terrakio_core/convenience_functions/{convenience_functions.py → zonal_stats.py}

@@ -1,30 +1,143 @@
-
-import os
+# Standard library imports
 import asyncio
-import tempfile
-import time
-import pandas as pd
-import geopandas as gpd
-from geopandas import GeoDataFrame
-from shapely.geometry import mapping
-from pathlib import Path
-from ..exceptions import APIError, ConfigurationError
-from ..helper.bounded_taskgroup import BoundedTaskGroup
-from ..helper.tiles import tiles
+import psutil
+import random
 import uuid
+from io import BytesIO
+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
-import random
-import psutil
-import copy
-from shapely.geometry import shape
+from geopandas import GeoDataFrame
+from shapely.geometry import box, mapping, shape
 from shapely.ops import transform
-from shapely.geometry import box
-import pyproj
 
-import pandas as pd
-import geopandas as gpd
+# Local imports
+from .geoquries import request_geoquery_list
+
+nest_asyncio.apply()
+class cloud_object(gpd.GeoDataFrame):
+    """
+    This class is a class used for cloud
+    """
+    def __init__(self, job_id: str, job_name: str, client=None):
+
+        super().__init__({
+            'geometry': [], 
+            'dataset': []
+        })
+
+        self.job_id = job_id
+        self.client = client
+        self.job_name = job_name
+
+    def head(self, n = 5):
+        """
+        Returns the first n files stored in the cloud bucket.
+        """
+        return asyncio.run(self._head_async(n))
+
+    async def _head_async(self, n = 5):
+        """
+        Returns the first n files stored in the cloud bucket.
+
+        Args:
+            n (int): Number of files to return. Default is 5.
+
+        Returns:
+            GeoDataFrame: A GeoDataFrame containing the first n files.
+        """
+
+        track_info = await self.client.mass_stats.track_job([self.job_id])
+        job_info = track_info[self.job_id]
+        status = job_info['status']
+        if status == "Completed":
+                payload = {
+                    "job_name": job_info["name"],
+                    "file_type": "raw",
+                    "bucket": job_info["bucket"],
+                }
+                result = await self.client._terrakio_request("POST", "mass_stats/download_files", json=payload)
+                download_urls = result["download_urls"][:n]
+                datasets = []
+
+                async with aiohttp.ClientSession() as session:
+                    for i, url in enumerate(download_urls):
+                        try:
+                            self.client.logger.info(f"Downloading dataset {i+1}/{len(download_urls)}...")
+                            async with session.get(url) as response:
+                                if response.status == 200:
+                                    content = await response.read()
+                                    dataset = xr.open_dataset(BytesIO(content))
+                                    datasets.append(dataset)
+                                    self.client.logger.info(f"Successfully processed dataset {i+1}")
+                                else:
+                                    self.client.logger.warning(f"Failed to download dataset {i+1}: HTTP {response.status}")
+                        except Exception as e:
+                            self.client.logger.error(f"Error downloading dataset {i+1}: {e}")
+                            continue
+                    if not datasets:
+                        self.client.logger.warning("No datasets were successfully downloaded")
+                        return gpd.GeoDataFrame({'geometry': [], 'dataset': []})
+                    try:
+                        json_response = await self.client._terrakio_request(
+                            "POST", "mass_stats/download_json", 
+                            params={"job_name": job_info['name']}
+                        )
+                        json_url = json_response["download_url"]
+                        
+                        async with session.get(json_url) as response:
+                            if response.status == 200:
+                                json_data = await response.json()
+                                self.client.logger.info("Successfully downloaded geometry data")
+                                
+                                geometries = []
+                                max_geometries = min(n, len(json_data), len(datasets))
+                                
+                                for i in range(max_geometries):
+                                    try:
+                                        geom_dict = json_data[i]["request"]["feature"]["geometry"]
+                                        shapely_geom = shape(geom_dict)
+                                        geometries.append(shapely_geom)
+                                    except (KeyError, ValueError) as e:
+                                        self.client.logger.warning(f"Error parsing geometry {i}: {e}")
+                                        continue
+                                
+                                min_length = min(len(datasets), len(geometries))
+                                if min_length == 0:
+                                    self.client.logger.warning("No matching datasets and geometries found")
+                                    return gpd.GeoDataFrame({'geometry': [], 'dataset': []})
+                                
+                                gdf = gpd.GeoDataFrame({
+                                    'geometry': geometries[:min_length],
+                                    'dataset': datasets[:min_length]
+                                })
+                                
+                                self.client.logger.info(f"Created GeoDataFrame with {len(gdf)} rows")
+                                try:
+                                    expanded_gdf = expand_on_variables_and_time(gdf)
+                                    return expanded_gdf
+                                except NameError:
+                                    self.client.logger.warning("expand_on_variables_and_time function not found, returning raw GeoDataFrame")
+                                    return gdf
+                                
+                            else:
+                                self.client.logger.warning(f"Failed to download geometry data: HTTP {response.status}")
+                                return gpd.GeoDataFrame({'geometry': [], 'dataset': []})
+                                    
+                    except Exception as e:
+                            self.client.logger.error(f"Error downloading geometry data: {e}")
+                            return gpd.GeoDataFrame({'geometry': [], 'dataset': []})
+        elif status in ["Failed", "Cancelled", "Error"]:
+            return "The zonal stats job(for preparing the data) has failed, please check the job status!"
+        else:
+            return "The zonal stats job(for preparing the data) is still runningm, please come back at a later time!"
 
-from typing import Optional
 
 def expand_on_time(gdf):
     """
@@ -90,6 +203,8 @@ def expand_on_time(gdf):
         result_gdf = gpd.GeoDataFrame(result_df, geometry='geometry')
         result_gdf = result_gdf.set_index(['geometry'])
     
+    result_gdf.attrs = gdf.attrs.copy()
+    
     return result_gdf
 
 def expand_on_variables(gdf):
@@ -143,7 +258,7 @@ def expand_on_variables(gdf):
             raise ValueError("Expected 'dataset' column for variable expansion")
     
     result_df = pd.DataFrame(rows)
-    
+
     if 'time' in result_df.columns:
         result_gdf = gpd.GeoDataFrame(result_df, geometry='geometry')
         result_gdf = result_gdf.set_index(['geometry', 'time'])
@@ -151,9 +266,10 @@ def expand_on_variables(gdf):
         result_gdf = gpd.GeoDataFrame(result_df, geometry='geometry')
         result_gdf = result_gdf.set_index(['geometry'])
     
+    result_gdf.attrs = gdf.attrs.copy()
+    
     return result_gdf
 
-
 def expand_on_variables_and_time(gdf):
     """
     Convenience function to expand on both variables and time.
@@ -169,7 +285,7 @@ def expand_on_variables_and_time(gdf):
         return expanded_on_variables_and_time
     except Exception as e:
         return expanded_on_time
-
+    
 def estimate_geometry_size_ratio(queries: list):
     """Calculate size ratios for all geometries relative to the first geometry using bounding box area."""
     
@@ -217,101 +333,6 @@ async def estimate_query_size(
         total_size_mb += first_query_dataset.nbytes * ratios[i] / (1024**2)
     return total_size_mb
 
-async def request_geoquery_list(
-        client,
-        quries: list[dict],
-        conc: int = 20,
-):
-    """
-    Execute multiple geo queries.
-    
-    Args:
-        client: The Terrakio client instance
-        quries: List of dictionaries containing query parameters
-        conc: The concurrency level for the requests
-        
-    Returns:
-        List of query results
-        
-    Raises:
-        ValueError: If the queries list is empty
-    """
-    if not quries:
-        raise ValueError("Queries list cannot be empty")
-    if conc > 100:
-        raise ValueError("Concurrency (conc) is too high. Please set conc to 100 or less.")
-
-    for i, query in enumerate(quries):
-        if 'expr' not in query:
-            raise ValueError(f"Query at index {i} is missing the required 'expr' key")
-        if 'feature' not in query:
-            raise ValueError(f"Query at index {i} is missing the required 'feature' key")
-        if 'in_crs' not in query:
-            raise ValueError(f"Query at index {i} is missing the required 'in_crs' key")
-    
-    completed_count = 0
-    lock = asyncio.Lock()
-    async def single_geo_query(query):
-        """
-        Execute multiple geo queries concurrently.
-        
-        Args:
-            quries: List of dictionaries containing query parameters
-        """
-        total_number_of_requests = len(quries)
-        nonlocal completed_count
-        try:
-            result = await client.geoquery(**query)
-            if isinstance(result, dict) and result.get("error"):
-                error_msg = f"Request failed: {result.get('error_message', 'Unknown error')}"
-                if result.get('status_code'):
-                    error_msg = f"Request failed with status {result['status_code']}: {result.get('error_message', 'Unknown error')}"
-                raise APIError(error_msg)
-            if isinstance(result, list):
-                result = result[0]
-                timestamp_number = result['request_count']
-                return timestamp_number
-            if not isinstance(result, xr.Dataset):
-                raise ValueError(f"Expected xarray Dataset, got {type(result)}")
-            
-            async with lock:
-                completed_count += 1
-                if completed_count % max(1, total_number_of_requests // 10) == 0:
-                    client.logger.info(f"Progress: {completed_count}/{total_number_of_requests} requests processed")
-            return result   
-        except Exception as e:
-            async with lock:
-                completed_count += 1
-            raise
-    
-    try:
-        async with BoundedTaskGroup(max_concurrency=conc) as tg:
-            tasks = [tg.create_task(single_geo_query(quries[idx])) for idx in range(len(quries))]
-        all_results = [task.result() for task in tasks]
-
-    except* Exception as eg:
-        for e in eg.exceptions:
-            if hasattr(e, 'response'):
-                raise APIError(f"API request failed: {e.response.text}")
-        raise
-    client.logger.info("All requests completed!")
-     
-    if not all_results:
-        raise ValueError("No valid results were returned for any geometry")
-    if isinstance(all_results, list) and type(all_results[0]) == int:
-        return sum(all_results)/len(all_results)
-    else:
-        geometries = []
-        for query in quries:
-            feature = query['feature']
-            geometry = shape(feature['geometry'])
-            geometries.append(geometry)
-        result_gdf = gpd.GeoDataFrame({
-            'geometry': geometries,
-            'dataset': all_results
-        })
-        return result_gdf
-
 async def estimate_timestamp_number(
         client,
         quries: list[dict],
@@ -388,9 +409,7 @@ def gdf_to_json(
     """
     mass_stats_requests = []
     
-    # Loop through each row in the GeoDataFrame
     for idx, row in gdf.iterrows():
-        # Create the request feature
         request_feature = {
             "expr": expr,
             "feature": {
@@ -404,29 +423,24 @@ def gdf_to_json(
             "geom_fix": geom_fix,
         }
         
-        # Determine group name and file name based on id_column
         if id_column is not None and id_column in gdf.columns:
-            # Use the value from the specified column as group and file name
             identifier = str(row[id_column])
             group_name = f"group_{identifier}"
             file_name = f"file_{identifier}"
         else:
-            # Use the index as group and file name
             group_name = f"group_{idx}"
             file_name = f"file_{idx}"
             
-        # Create the complete request entry
         request_entry = {
             "group": group_name,
             "file": file_name,
             "request": request_feature,
         }
         
-        # Add the request to our list
         mass_stats_requests.append(request_entry)
         
     return mass_stats_requests
-    
+
 async def handle_mass_stats(
     client,
     gdf: GeoDataFrame,
@@ -436,17 +450,24 @@ async def handle_mass_stats(
     resolution: int = -1,
     geom_fix: bool = False,
     id_column: Optional[str] = None,
-
 ):
-    request_json = gdf_to_json(gdf = gdf, expr = expr, in_crs = in_crs, out_crs = out_crs, resolution = resolution, geom_fix = geom_fix, id_column = id_column)
-    job_id =await client.mass_stats.execute_job(
-        name = "zonal_stats_job",
-        output = "netcdf",
-        config = {},
-        request_json = request_json,
-        overwrite = True,
+    request_json = gdf_to_json(gdf=gdf, expr=expr, in_crs=in_crs, out_crs=out_crs, 
+                              resolution=resolution, geom_fix=geom_fix, id_column=id_column)
+    
+    job_response = await client.mass_stats.execute_job(
+        name=f"zonal-stats-{str(uuid.uuid4())[:6]}",
+        output="netcdf",
+        config={},
+        request_json=request_json,
+        overwrite=True,
     )
-    return job_id
+    
+    # Extract the actual task ID from the response
+    if isinstance(job_response, dict) and 'task_id' in job_response:
+        return job_response['task_id']  # Return just the string ID
+    else:
+        return job_response  # In case it's already just the ID
+
 
 async def zonal_stats(
     client,
@@ -461,7 +482,6 @@ async def zonal_stats(
     id_column: Optional[str] = None,
 ):
     """Compute zonal statistics for all geometries in a GeoDataFrame."""
-
     if mass_stats:
         mass_stats_id = await handle_mass_stats(
             client = client,
@@ -471,9 +491,13 @@ async def zonal_stats(
             out_crs = out_crs,
             resolution = resolution,
             geom_fix = geom_fix,
-            id_column = id_column
+            id_column = id_column,
         )
-        return mass_stats_id
+        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 = []
     for i in range(len(gdf)):
         quries.append({
@@ -494,130 +518,9 @@ async def zonal_stats(
         raise ValueError(local_or_remote_result["reason"])
     else:
         gdf_with_datasets = await request_geoquery_list(client = client, quries = quries, conc = conc)
+        gdf_with_datasets.attrs["cloud_metadata"] = {
+            "is_cloud_backed": False,
+        } 
         gdf_with_datasets = expand_on_variables_and_time(gdf_with_datasets)
     return gdf_with_datasets
 
-async def create_dataset_file(
-    client,
-    aoi: str,
-    expression: str,
-    output: str,
-    download_path: str,
-    in_crs: str = "epsg:4326",
-    to_crs: str = "epsg:4326",
-    res: float = 0.0001,
-    region: str = None,
-    overwrite: bool = False,
-    skip_existing: bool = False,
-    non_interactive: bool = True,
-    name: str | None = None,
-    poll_interval: int = 30,
-    max_file_size_mb: int = 5120,
-    tile_size: int = 1024,
-    mask: bool = True
-) -> dict:
-    
-    if not name:
-        name = f"file-gen-{uuid.uuid4().hex[:8]}"
-    
-    body, reqs, groups = tiles(
-        name = name, 
-        aoi = aoi, 
-        expression = expression,
-        output = output,
-        tile_size = tile_size,
-        crs = in_crs,
-        res = res,
-        region = region,
-        to_crs = to_crs,
-        mask = mask,
-        overwrite = overwrite,
-        skip_existing = skip_existing,
-        non_interactive = non_interactive
-    )
-    with tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False) as tempreq:
-        tempreq.write(reqs)
-        tempreqname = tempreq.name
-
-    task_id = await client.mass_stats.execute_job(
-        name=body["name"],
-        region=body["region"],
-        output=body["output"],
-        config = {},
-        overwrite=body["overwrite"],
-        skip_existing=body["skip_existing"],
-        request_json=tempreqname,
-    )
-
-    start_time = time.time()
-    status = None
-    client.logger.info(f"Tracking data generation job {task_id['task_id']}...")
-    while True:
-        try:
-            taskid = task_id['task_id']
-            trackinfo = await client.mass_stats.track_job([taskid])
-            status = trackinfo[taskid]['status']
-            if status == 'Completed':
-                client.logger.info('Data generated successfully!')
-                break
-            elif status in ['Failed', 'Cancelled', 'Error']:
-                raise RuntimeError(f"Job {taskid} failed with status: {status}")
-            else:
-                elapsed_time = time.time() - start_time
-                client.logger.info(f"Job status: {status} - Elapsed time: {elapsed_time:.1f}s")
-                await asyncio.sleep(poll_interval)
-                
-                
-        except KeyboardInterrupt:
-            client.logger.info(f"\nInterrupted! Job {taskid} is still running in the background.")
-            raise
-        except Exception as e:
-            client.logger.info(f"\nError tracking job: {e}")
-            raise
-
-    os.unlink(tempreqname)
-
-    combine_result = await client.mass_stats.combine_tiles(body["name"], body["overwrite"], body["output"], max_file_size_mb=max_file_size_mb)
-    combine_task_id = combine_result.get("task_id")
-
-    combine_start_time = time.time()
-    client.logger.info(f"Tracking file generation job {combine_task_id}...")
-    while True:
-        try:
-            trackinfo = await client.mass_stats.track_job([combine_task_id])
-            if body["output"] == "netcdf":
-                download_file_name = trackinfo[combine_task_id]['folder'] + '.nc'
-            elif body["output"] == "geotiff":
-                download_file_name = trackinfo[combine_task_id]['folder'] + '.tif'
-            bucket = trackinfo[combine_task_id]['bucket']
-            combine_status = trackinfo[combine_task_id]['status']
-            if combine_status == 'Completed':
-                client.logger.info('File/s generated successfully!')
-                break
-            elif combine_status in ['Failed', 'Cancelled', 'Error']:
-                raise RuntimeError(f"File generation job {combine_task_id} failed with status: {combine_status}")
-            else:
-                elapsed_time = time.time() - combine_start_time
-                client.logger.info(f"File generation job status: {combine_status} - Elapsed time: {elapsed_time:.1f}s")
-                time.sleep(poll_interval)
-        except KeyboardInterrupt:
-            client.logger.info(f"\nInterrupted! File generation job {combine_task_id} is still running in the background.")
-            raise
-        except Exception as e:
-            client.logger.info(f"\nError tracking file generation job: {e}")
-            raise
-
-    if download_path:
-        await client.mass_stats.download_file(
-            job_name=body["name"],
-            bucket=bucket,
-            file_type='processed',
-            folder='file-gen',
-            page_size=100,
-            output_path=download_path,
-        )
-    else:
-        path = f"{body['name']}/outputs/merged/{download_file_name}"
-        client.logger.info(f"Dataset file/s is available at {path}")
-
-    return {"generation_task_id": task_id, "combine_task_id": combine_task_id}