giga-spatial 0.6.9__py3-none-any.whl → 0.7.1__py3-none-any.whl

{giga_spatial-0.6.9.dist-info → giga_spatial-0.7.1.dist-info}/METADATA

@@ -1,13 +1,29 @@
 Metadata-Version: 2.4
 Name: giga-spatial
-Version: 0.6.9
+Version: 0.7.1
 Summary: A package for spatial data download & processing
-Home-page: https://github.com/unicef/giga-spatial
 Author: Utku Can Ozturk
 Author-email: utkucanozturk@gmail.com
 License: AGPL-3.0-or-later
+Project-URL: Homepage, https://github.com/unicef/giga-spatial
+Project-URL: Documentation, https://unicef.github.io/giga-spatial/
+Project-URL: Source, https://github.com/unicef/giga-spatial
+Project-URL: Issue Tracker, https://github.com/unicef/giga-spatial/issues
+Project-URL: Discussions, https://github.com/unicef/giga-spatial/discussions
+Project-URL: Changelog, https://unicef.github.io/giga-spatial/changelog
 Keywords: gigaspatial,spatial,geospatial,gis,remote sensing,data processing,download,openstreetmap,osm,ghsl,grid,point of interest,POI,raster,vector,school connectivity,unicef,giga,mapping,analysis,python
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Telecommunications Industry
+Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: GIS
 Classifier: License :: OSI Approved :: GNU Affero General Public License v3
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.10
@@ -24,8 +40,9 @@ Requires-Dist: pycountry==24.6.1
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: rasterio==1.3.10
 Requires-Dist: Requests==2.32.3
-Requires-Dist: scipy==1.15.1
+Requires-Dist: scipy>=1.15.1
 Requires-Dist: Shapely>=2.0.7
+Requires-Dist: networkx>=3.2.1
 Requires-Dist: tqdm==4.65.0
 Requires-Dist: OWSLib==0.32.1
 Requires-Dist: pydantic-settings>=2.7.1
@@ -33,15 +50,16 @@ Requires-Dist: hdx-python-api>=6.3.8
 Requires-Dist: bs4==0.0.2
 Requires-Dist: sqlalchemy-trino==0.5.0
 Requires-Dist: dask>=2024.12.1
+Requires-Dist: h3>=4.2.0
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
-Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
 Dynamic: license-file
+Dynamic: project-url
 Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
@@ -53,6 +71,14 @@ Dynamic: summary
 
 # GigaSpatial
 
+[![License: AGPL v3](https://img.shields.io/badge/License-AGPL%20v3-brightgreen.svg)](https://opensource.org/license/agpl-v3)
+[![PyPI version](https://badge.fury.io/py/giga-spatial.svg)](https://badge.fury.io/py/giga-spatial)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/giga-spatial.svg?color=dark-green)](https://pypi.org/project/giga-spatial/)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![PyPI Downloads](https://static.pepy.tech/badge/giga-spatial)](https://pepy.tech/projects/giga-spatial)
+[![GitHub commit activity](https://img.shields.io/github/commit-activity/y/unicef/giga-spatial.svg?color=dark-green)](https://github.com/unicef/giga-spatial/graphs/contributors)
+
+
 ## About Giga
 
 [Giga](https://giga.global/) is a UNICEF-ITU initiative to connect every school to the Internet and every young person to information, opportunity and choice. 

{giga_spatial-0.6.9.dist-info → giga_spatial-0.7.1.dist-info}/RECORD

@@ -1,50 +1,52 @@
-giga_spatial-0.6.9.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-gigaspatial/__init__.py,sha256=FSdOAp4_p3PglR9eAbJRAD3r0Xzv4uXsvcGDSQGm7Wo,22
-gigaspatial/config.py,sha256=pLbxGc08OHT2IfTBzZVuIJTPR2vvg3KTFfvciOtRswk,9304
+giga_spatial-0.7.1.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+gigaspatial/__init__.py,sha256=2KJZDSMOG7KS82AxYOrZ4ZihYxX0wjfUjDsIZh3L024,22
+gigaspatial/config.py,sha256=xqP800jaDMYE7-cgHXSGGwuF1fmo5Q56-DqpJ61p8a0,9382
 gigaspatial/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gigaspatial/core/io/__init__.py,sha256=stlpgEeHf5KIb2ZW8yEbdJK5iq6n_wX4DPmKyR9PK-w,317
-gigaspatial/core/io/adls_data_store.py,sha256=Zv-D_8d_2h57HnCUTJb0JWWjXqR_0XH4F8Nu_UFZK9E,11975
+gigaspatial/core/io/adls_data_store.py,sha256=Pr1FKpzFb2TSeidMSGhhNSDk1tFxAi4G1aPZ_No_xUs,15783
 gigaspatial/core/io/data_api.py,sha256=0TtXEfqIz9m1uC8ktcUhZZtx6ZIPY_SIXNnlIodcry8,3970
 gigaspatial/core/io/data_store.py,sha256=mi8fy78Dtwj4dpKkyDM6kTlna1lfCQ5ro2hUAOFr83A,3223
 gigaspatial/core/io/database.py,sha256=kR9ZHuIpZEjXmyj_PnMn6ManQ504kl_f1kJRjHuNWwk,11378
-gigaspatial/core/io/local_data_store.py,sha256=hcu7DNYa3AL6sEPMqguzxWal_bnP7CIpbwpoiyf5TCw,2933
+gigaspatial/core/io/local_data_store.py,sha256=ZMkj5IteQmGLy8G1L2qt4_WKxosA-F_0evF-oW-JRKo,3227
 gigaspatial/core/io/readers.py,sha256=gqFKGRCsAP_EBXipqGtT8MEV-x0u6SrCqaSiOC5YPTA,9284
 gigaspatial/core/io/writers.py,sha256=asb56ZHQEWO2rdilIq7QywDRk8yfebecWv1KwzUpaXI,4367
 gigaspatial/core/schemas/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gigaspatial/core/schemas/entity.py,sha256=QAhEW0-JgdWh9pjKGbB5ArvqtVK85ayYZJPgjdb-IKw,8590
 gigaspatial/generators/__init__.py,sha256=cKbMTW7Eh-oDPtM9OfGP14_ekVwc2_7Je7n_pr_anig,223
-gigaspatial/generators/poi.py,sha256=FMYH2yPFuCeYiwj-pHYe83bAxXPkQP28VDQx5L2eEnQ,35869
+gigaspatial/generators/poi.py,sha256=tlLqVsXOjl83OL3Z6yajz9BLtZVbhZF67A-el-F2oU4,42356
 gigaspatial/generators/zonal/__init__.py,sha256=egnpvGVeIOS2Zg516AT84tJnIqS4owxmMLLmBQJmK7Y,301
 gigaspatial/generators/zonal/admin.py,sha256=rgOyQX3f_g9qnXqrf-NkR2GEdwOqjNuPNe1H7AUVsfg,3698
-gigaspatial/generators/zonal/base.py,sha256=aoq9AmawPnxu04YI7hPmJzvBTyuUqBQuMZAEUdiVStg,22818
-gigaspatial/generators/zonal/geometry.py,sha256=JbaQ4WS6g45g3uBaATfJd7DS3wW-GPW0GW9FtsvGH-c,21284
+gigaspatial/generators/zonal/base.py,sha256=byyfv4dNpOMzszBMMbKQlZuHMlq2e84Hboh0W58f-8k,22959
+gigaspatial/generators/zonal/geometry.py,sha256=0EF3VXAVOcj5AtcubGWU325biLaZ76zt3Sf1uyKEE88,23358
 gigaspatial/generators/zonal/mercator.py,sha256=fA02j30PWB5BVjrbNGCMjiOw-ds182yK7R27z8mWFug,5291
 gigaspatial/grid/__init__.py,sha256=ypSSyZ4fYtMNc4IG7chSD7NkUfS2bv9KWRsKR1D9pDI,80
-gigaspatial/grid/mercator_tiles.py,sha256=mAYZDBJ1U0l3z9i4rh5OqiPhOGWcBYzUOI1cvQG_Ff4,11240
+gigaspatial/grid/h3.py,sha256=0d_rNNvwxc0LDD2qKCd2gTy_16_5sgPwJwk29z5pE9U,15310
+gigaspatial/grid/mercator_tiles.py,sha256=dzUDbXe0QHEC4s334IVT76d41D35dbd-QiN2LnkDdvA,11240
 gigaspatial/handlers/__init__.py,sha256=T0_6OxXQ59yTu9g2P6P9vnepudOWp_85R4WQKxRF94c,1618
-gigaspatial/handlers/base.py,sha256=wxkB8fniOIzgsg0WF9WkaZbAmFhNkqtZ_LGD8Ch53Mw,27238
+gigaspatial/handlers/base.py,sha256=JSZ64eWRoF17bKvVj2Bq3lFA00uJ4i6qlwp72O4HSv4,27885
 gigaspatial/handlers/boundaries.py,sha256=jtWyQt3iAzS77mbAOi7mjh3cv_YCV3uB_r1h56gCfeY,20729
-gigaspatial/handlers/ghsl.py,sha256=aSEVQVANzJf8O8TiQYmfwyeM43ZaO65VJHmiuLSQfLs,30524
-gigaspatial/handlers/giga.py,sha256=F5ZfcE37a24X-c6Xhyt72C9eZZbyN_gV7w_InxKFMQQ,28348
+gigaspatial/handlers/ghsl.py,sha256=QvW7GeHWQSrPdxXxmR_61UcfBIHziNpCHCxRXg1nnug,31285
+gigaspatial/handlers/giga.py,sha256=tNy2O0YAdy4iYWjMNKUadV_W2HxcTsb-aG4te6wvMOk,28660
 gigaspatial/handlers/google_open_buildings.py,sha256=Liqk7qJhDtB4Ia4uhBe44LFcf-XVKBjRfj-pWlE5erY,16594
 gigaspatial/handlers/hdx.py,sha256=1m6oG1DeEC_RLFtb6CrTReWpbQ5uG2e8EIt-IUkZbaI,18122
+gigaspatial/handlers/healthsites.py,sha256=gJCnKDXE4Gu-3Z6Io0-EknXfSdOxBHdr4-JV0z9bul0,12829
 gigaspatial/handlers/mapbox_image.py,sha256=M_nkJ_b1PD8FG1ajVgSycCb0NRTAI_SLpHdzszNetKA,7786
 gigaspatial/handlers/maxar_image.py,sha256=kcc8uGljQB0Yh0MKBA7lT7KwBbNZwFzuyBklR3db1P4,10204
 gigaspatial/handlers/microsoft_global_buildings.py,sha256=bQ5WHIv3v0wWrZZUbZkKPRjgdlqIxlK7CV_0zSvdrTw,20292
 gigaspatial/handlers/ookla_speedtest.py,sha256=EcvSAxJZ9GPfzYnT_C85Qgy2ecc9ndf70Pklk53OdC8,6506
 gigaspatial/handlers/opencellid.py,sha256=KuJqd-5-RO5ZzyDaBSrTgCK2ib5N_m3RUcPlX5heWwI,10683
-gigaspatial/handlers/osm.py,sha256=vUbdUm6lO2f8YyU7o4qUSkWMxlZElp7EPBFlneRaeo0,16641
+gigaspatial/handlers/osm.py,sha256=gyY_a2OoRZjL14iOTEKLCPbKTcmSDHc72Q0hluaENrY,25464
 gigaspatial/handlers/overture.py,sha256=lKeNw00v5Qia7LdWORuYihnlKEqxE9m38tdeRrvag9k,4218
 gigaspatial/handlers/rwi.py,sha256=eAaplDysVeBhghJusYUKZYbKL5hW-klWvi8pWhILQkY,4962
 gigaspatial/handlers/unicef_georepo.py,sha256=ODYNvkU_UKgOHXT--0MqmJ4Uk6U1_mp9xgehbTzKpX8,31924
-gigaspatial/handlers/worldpop.py,sha256=jV166EP02Xdj8jiT8aQi4sexds8Qd3KRGHXqq70_Sdk,30161
+gigaspatial/handlers/worldpop.py,sha256=5gSAhTPs3l8cVflx_Vp4ZxhvcUKKb_r2hGmc_sXCgio,39893
 gigaspatial/processing/__init__.py,sha256=QDVL-QbLCrIb19lrajP7LrHNdGdnsLeGcvAs_jQpdRM,183
 gigaspatial/processing/algorithms.py,sha256=6fBCwbZrI_ISWJ7UpkH6moq1vw-7dBy14yXSLHZprqY,6591
-gigaspatial/processing/geo.py,sha256=8kD7-LQdGzKVfuZDWr3zK5uQhPzgxbZ3JBPosLRBJ5M,41390
+gigaspatial/processing/geo.py,sha256=ekGbU1sEn10zX3esYIEba6eZyhpx9WOjPlVEkspqcNk,41674
 gigaspatial/processing/sat_images.py,sha256=YUbH5MFNzl6NX49Obk14WaFcr1s3SyGJIOk-kRpbBNg,1429
-gigaspatial/processing/tif_processor.py,sha256=dZRhMGj5r7DIu8Bop31NPbN1IdOK1syIlCOFTjTiiyo,40024
+gigaspatial/processing/tif_processor.py,sha256=WzD3inLUdr50fl11WPF6czvG1d8s7y2qdTBOc5Yo2yw,66400
 gigaspatial/processing/utils.py,sha256=HC85vGKQakxlkoQAkZmeAXWHsenAwTIRn7jPKUA7x20,1500
-giga_spatial-0.6.9.dist-info/METADATA,sha256=I-m22v0wf9ySbuzobowQGdJGwT43xbevnubeVASudpU,7537
-giga_spatial-0.6.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-giga_spatial-0.6.9.dist-info/top_level.txt,sha256=LZsccgw6H4zXT7m6Y4XChm-Y5LjHAwZ2hkGN_B3ExmI,12
-giga_spatial-0.6.9.dist-info/RECORD,,
+giga_spatial-0.7.1.dist-info/METADATA,sha256=Fo_X_aPJg9Mv1GfX4esviiljEhcK4n7imbACWKrNo6s,9277
+giga_spatial-0.7.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+giga_spatial-0.7.1.dist-info/top_level.txt,sha256=LZsccgw6H4zXT7m6Y4XChm-Y5LjHAwZ2hkGN_B3ExmI,12
+giga_spatial-0.7.1.dist-info/RECORD,,

gigaspatial/__init__.py

@@ -1 +1 @@
-__version__ = "0.6.9"
+__version__ = "0.7.1"

gigaspatial/config.py

@@ -38,6 +38,7 @@ class Config(BaseSettings):
     GIGA_SCHOOL_MEASUREMENTS_API_KEY: str = Field(
         default="", alias="GIGA_SCHOOL_MEASUREMENTS_API_KEY"
     )
+    HEALTHSITES_API_KEY: str = Field(default="", alias="HEALTHSITES_API_KEY")
 
     ROOT_DATA_DIR: Path = Field(
         default=Path("."),

gigaspatial/core/io/adls_data_store.py

@@ -1,4 +1,5 @@
 from azure.storage.blob import BlobServiceClient
+import time
 import io
 import contextlib
 import logging
@@ -151,20 +152,45 @@ class ADLSDataStore(DataStore):
                     "\\", "/"
                 )
 
-                # Create a source blob client
-                source_blob_client = self.container_client.get_blob_client(blob.name)
+                # Use copy_file method to copy each file
+                self.copy_file(blob.name, new_blob_path, overwrite=True)
 
-                # Create a destination blob client
-                destination_blob_client = self.container_client.get_blob_client(
-                    new_blob_path
+            print(f"Copied directory from {source_dir} to {destination_dir}")
+        except Exception as e:
+            print(f"Failed to copy directory {source_dir}: {e}")
+
+    def copy_file(
+        self, source_path: str, destination_path: str, overwrite: bool = False
+    ):
+        """
+        Copies a single file from source to destination within the same container.
+
+        :param source_path: The source file path in the blob storage
+        :param destination_path: The destination file path in the blob storage
+        :param overwrite: If True, overwrite the destination file if it already exists
+        """
+        try:
+            if not self.file_exists(source_path):
+                raise FileNotFoundError(f"Source file not found: {source_path}")
+
+            if self.file_exists(destination_path) and not overwrite:
+                raise FileExistsError(
+                    f"Destination file already exists and overwrite is False: {destination_path}"
                 )
 
-                # Start the copy operation
-                destination_blob_client.start_copy_from_url(source_blob_client.url)
+            # Create source and destination blob clients
+            source_blob_client = self.container_client.get_blob_client(source_path)
+            destination_blob_client = self.container_client.get_blob_client(
+                destination_path
+            )
 
-            print(f"Copied directory from {source_dir} to {destination_dir}")
+            # Start the server-side copy operation
+            destination_blob_client.start_copy_from_url(source_blob_client.url)
+
+            print(f"Copied file from {source_path} to {destination_path}")
         except Exception as e:
-            print(f"Failed to copy directory {source_dir}: {e}")
+            print(f"Failed to copy file {source_path}: {e}")
+            raise
 
     def exists(self, path: str) -> bool:
         blob_client = self.blob_service_client.get_blob_client(
@@ -285,8 +311,20 @@ class ADLSDataStore(DataStore):
         return False
 
     def rmdir(self, dir: str) -> None:
-        blobs = self.list_files(dir)
-        self.container_client.delete_blobs(*blobs)
+        # Normalize directory path to ensure it targets all children
+        dir_path = dir.rstrip("/") + "/"
+
+        # Azure Blob batch delete has a hard limit on number of sub-requests
+        # per batch (currently 256). Delete in chunks to avoid
+        # ExceedsMaxBatchRequestCount errors.
+        blobs = list(self.list_files(dir_path))
+        if not blobs:
+            return
+
+        BATCH_LIMIT = 256
+        for start_idx in range(0, len(blobs), BATCH_LIMIT):
+            batch = blobs[start_idx : start_idx + BATCH_LIMIT]
+            self.container_client.delete_blobs(*batch)
 
     def mkdir(self, path: str, exist_ok: bool = False) -> None:
         """
@@ -323,3 +361,58 @@ class ADLSDataStore(DataStore):
         )
         if blob_client.exists():
             blob_client.delete_blob()
+
+    def rename(
+        self,
+        source_path: str,
+        destination_path: str,
+        overwrite: bool = False,
+        delete_source: bool = True,
+        wait: bool = True,
+        timeout_seconds: int = 300,
+        poll_interval_seconds: int = 1,
+    ) -> None:
+        """
+        Rename (move) a single file by copying to the new path and deleting the source.
+
+        :param source_path: Existing blob path
+        :param destination_path: Target blob path
+        :param overwrite: Overwrite destination if it already exists
+        :param delete_source: Delete original after successful copy
+        :param wait: Wait for the copy operation to complete
+        :param timeout_seconds: Max time to wait for copy to succeed
+        :param poll_interval_seconds: Polling interval while waiting
+        """
+
+        if not self.file_exists(source_path):
+            raise FileNotFoundError(f"Source file not found: {source_path}")
+
+        if self.file_exists(destination_path) and not overwrite:
+            raise FileExistsError(
+                f"Destination already exists and overwrite is False: {destination_path}"
+            )
+
+        # Use copy_file method to copy the file
+        self.copy_file(source_path, destination_path, overwrite=overwrite)
+
+        if wait:
+            # Wait for copy to complete if requested
+            dest_client = self.container_client.get_blob_client(destination_path)
+            deadline = time.time() + timeout_seconds
+            while True:
+                props = dest_client.get_blob_properties()
+                status = getattr(props.copy, "status", None)
+                if status == "success":
+                    break
+                if status in {"aborted", "failed"}:
+                    raise IOError(
+                        f"Copy failed with status {status} from {source_path} to {destination_path}"
+                    )
+                if time.time() > deadline:
+                    raise TimeoutError(
+                        f"Timed out waiting for copy to complete for {destination_path}"
+                    )
+                time.sleep(poll_interval_seconds)
+
+        if delete_source:
+            self.remove(source_path)

gigaspatial/core/io/local_data_store.py

@@ -1,5 +1,6 @@
 from pathlib import Path
 import os
+import shutil
 from typing import Any, List, Generator, Tuple, Union, IO
 
 from .data_store import DataStore
@@ -79,6 +80,13 @@ class LocalDataStore(DataStore):
         if full_path.is_file():
             os.remove(full_path)
 
+    def copy_file(self, src: str, dst: str) -> None:
+        """Copy a file from src to dst."""
+        src_path = self._resolve_path(src)
+        dst_path = self._resolve_path(dst)
+        self.mkdir(str(dst_path.parent), exist_ok=True)
+        shutil.copy2(src_path, dst_path)
+
     def rmdir(self, directory: str) -> None:
         full_path = self._resolve_path(directory)
         if full_path.is_dir():