earthcode 0.1.1__tar.gz → 0.1.2__tar.gz

{earthcode-0.1.1 → earthcode-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: earthcode
-Version: 0.1.1
+Version: 0.1.2
 Summary: Tools for creating, validating, and searching EarthCODE Open Science Catalog metadata.
 Project-URL: Homepage, https://github.com/ESA-EarthCODE/earthcode-library
 Project-URL: Repository, https://github.com/ESA-EarthCODE/earthcode-library
@@ -65,18 +65,8 @@ To run:
 4. `pixi install`
 5. `pixi run jupyter lab`
 
-Semantic search uses a staged ONNX bundle. By default it fetches
-`model_O2.onnx` plus `tokenizer.json` from
-`https://pangeo-test-fires.s3.eu-west-2.amazonaws.com/self-hosted-models`
-into a local cache on first use.
-The default cache location is the platform-specific user cache dir for
-`earthcode`.
-
-Runtime knobs:
-- `EARTHCODE_MODEL_CACHE_DIR`: local cache root for staged bundles
-
 We have examples for:
 - `./examples/example_create_osc_entries.ipynb` - shows how to create OSC entries
 - `./examples/contribute_via_pr_osc.ipynb` - shows how to add newly created entries to the OSC, using a GitHub pull request
 - `./examples/contribute_via_osc_editor.ipynb` - shows how to add entries to the OSC, using a combination of this library and the OSC Editor (a GUI tool)
-- `./examples/earthcode_publishing_guide.ipynb` - is a simplified introduction to the OSC and the necessary steps to publish data
+- `./examples/earthcode_publishing_guide.ipynb` - is a simplified introduction to the OSC and the necessary steps to publish data

{earthcode-0.1.1 → earthcode-0.1.2}/README.md

@@ -16,18 +16,8 @@ To run:
 4. `pixi install`
 5. `pixi run jupyter lab`
 
-Semantic search uses a staged ONNX bundle. By default it fetches
-`model_O2.onnx` plus `tokenizer.json` from
-`https://pangeo-test-fires.s3.eu-west-2.amazonaws.com/self-hosted-models`
-into a local cache on first use.
-The default cache location is the platform-specific user cache dir for
-`earthcode`.
-
-Runtime knobs:
-- `EARTHCODE_MODEL_CACHE_DIR`: local cache root for staged bundles
-
 We have examples for:
 - `./examples/example_create_osc_entries.ipynb` - shows how to create OSC entries
 - `./examples/contribute_via_pr_osc.ipynb` - shows how to add newly created entries to the OSC, using a GitHub pull request
 - `./examples/contribute_via_osc_editor.ipynb` - shows how to add entries to the OSC, using a combination of this library and the OSC Editor (a GUI tool)
-- `./examples/earthcode_publishing_guide.ipynb` - is a simplified introduction to the OSC and the necessary steps to publish data
+- `./examples/earthcode_publishing_guide.ipynb` - is a simplified introduction to the OSC and the necessary steps to publish data

{earthcode-0.1.1 → earthcode-0.1.2}/earthcode/search.py

@@ -76,7 +76,7 @@ def _get_cached_model_bundle(model_cache_dir=None):
                 print()
 
     try:
-        for filename, uri in MODEL_ASSETS:
+        for filename, uri in MODEL_ASSETS: # was parallel before
             download_file(filename, uri)
     except Exception:
         shutil.rmtree(model_dir, ignore_errors=True)
@@ -280,6 +280,7 @@ def search(
                 "q": np.asarray(vec, dtype=np.float32),
                 "k": limit,
             },
+            disable_scoring_autoprojection=True,
             prefilter=True,
             limit=limit,
         ).to_table()

{earthcode-0.1.1 → earthcode-0.1.2}/pixi.lock

@@ -4058,8 +4058,8 @@ packages:
   timestamp: 1734368817583
 - pypi: ./
   name: earthcode
-  version: 0.1.0
-  sha256: 9d9247494c8184bb8846c3a9b0bf15b412435f48d8e3fa25c58971189c0e3fec
+  version: 0.1.1
+  sha256: 82130614dda8b649e3506de2147c7f48110d177362c1298c6ecb6b42d10f5267
   requires_dist:
   - pystac>=1.14.1,<2
   - xarray>=2025.12.0,<2026

{earthcode-0.1.1 → earthcode-0.1.2}/pixi.toml

@@ -12,7 +12,7 @@ version = "0.1.0"
 docs = "jupyter-book build ."
 
 [dependencies]
-python = ">=3.12,<3.14"
+python = ">=3.12"
 pystac = ">=1.14.1,<2"
 xarray = ">=2025.12.0,<2026"
 shapely = ">=2.1.2,<3"
@@ -30,6 +30,9 @@ onnxruntime = ">=1.24.1,<2"
 platformdirs = ">=4.5.0,<5"
 tokenizers = ">=0.22.2,<1"
 
+[target.osx-arm64.dependencies]
+python = ">=3.12,<3.14"
+
 [feature.dev.dependencies]
 jupyter-book = ">=1.0.4,<2"
 jupyterlab = ">=4.5.0,<5"

{earthcode-0.1.1 → earthcode-0.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "earthcode"
-version = "0.1.1"
+version = "0.1.2"
 description = "Tools for creating, validating, and searching EarthCODE Open Science Catalog metadata."
 readme = "README.md"
 requires-python = ">=3.12"

{earthcode-0.1.1 → earthcode-0.1.2}/tests/test_search.py

@@ -78,6 +78,7 @@ def test_bbox_intersects_hits_expected_product():
     ids = [r.id for r in results]
     assert "binary-wet-snow-s14science-snow" in ids
 
+    # Test that containment differs from intersects
     results_containment = search(
         "snow data", limit=10, bbox=alps_bbox, intersects=False
     )
@@ -87,17 +88,18 @@ def test_bbox_intersects_hits_expected_product():
 
 
 def test_combined_filters():
+    # Test theme filter
     land_results = search("forest fires", theme="land", limit=5)
     assert len(land_results) > 0
 
-    ocean_results = search(
-        "forest fires", theme="oceans", keyword="forest fires", limit=5
-    )
+    ocean_results = search("forest fires", theme="oceans", keyword="forest fires", limit=5)
     assert len(ocean_results) == 0
 
+    # Test variable filter
     results = search(variable="burned-area", type="products", limit=5)
     ids = {r.id for r in results}
     assert "seasfire-cube" in ids
 
+    # Test keyword filter
     results = search(keyword="seasonal fire modeling", type="products", limit=5)
     assert "seasfire-cube" in [r.id for r in results]

earthcode-0.1.1/.ipynb_checkpoints/dev-checkpoint.ipynb

@@ -1,91 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "09da950a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from earthcode.search import search\n",
-    "res = search(\"waposal\")\n",
-    "res"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b42735c7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[<Collection id=waposal-waves>,\n",
-       " <Collection id=cloud-od-livas>,\n",
-       " <Collection id=dust-od-livas>,\n",
-       " <Collection id=swot-east-greenland-current>,\n",
-       " <Collection id=tropospheric-ozone-column-tropomi-sunlit>,\n",
-       " <Collection id=aerosol-dust-od-livas>,\n",
-       " <Collection id=cliima-cloud-od-livas>,\n",
-       " <Collection id=smos-l3-africa-smos-vegetation>,\n",
-       " <Collection id=rdsar-satellite-sar-altimeter-open-ocean-cp4o>,\n",
-       " <Collection id=clima-strat-aerosol-cloud-op-livas>]"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "res = search(\"waposal\")\n",
-    "res"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4c313d50",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# search individual stac collection from the osc\n",
-    "# index all items for that collection (skipping collections within it) basically flattening the structure of the stac collection so that it's the osc collection -> items\n",
-    "# have the ability to search them and then open them with xarray somehow \n",
-    "# in some cases there might be 300k items in a collection!\n",
-    "\n",
-    "\n",
-    "# e.g. https://opensciencedata.esa.int/products/waposal-waves/collection example links to https://opensciencedata.esa.int/external/s3.waw4-1.cloudferro.com/EarthCODE/Catalogs/waposal/collection\n",
-    "# which then contains a bunch of items e.g. https://opensciencedata.esa.int/external/s3.waw4-1.cloudferro.com/EarthCODE/Catalogs/waposal/waposal-az-cs2/waposal-az-cs2\n",
-    "# which then links to the data\n",
-    "\n",
-    "\n",
-    "#I should be able to do the same functionality as a stac api with this library\n",
-    "\n",
-    "# the key question is if I should keep the stac items in a geoparquet file on cloud or in the same lancedb file"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "pangeo",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.13.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}