From 8dfce89001a764f872b3c951fb1bfc4688dc6c52 Mon Sep 17 00:00:00 2001
From: amsnyder <asnyder@usgs.gov>
Date: Mon, 20 Nov 2023 14:19:13 -0600
Subject: [PATCH] additional modifications to item workflow
---
..._exploratory_workflow_conus404-daily.ipynb | 149 +++++++++++-------
1 file changed, 91 insertions(+), 58 deletions(-)
diff --git a/workflows/create_item_zarr_exploratory_workflow_conus404-daily.ipynb b/workflows/create_item_zarr_exploratory_workflow_conus404-daily.ipynb
index 01ad5803..c488783f 100644
--- a/workflows/create_item_zarr_exploratory_workflow_conus404-daily.ipynb
+++ b/workflows/create_item_zarr_exploratory_workflow_conus404-daily.ipynb
@@ -19,7 +19,9 @@
"cell_type": "code",
"execution_count": null,
"id": "201e0945-de55-45ff-b095-c2af009a4e62",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"import pystac\n",
@@ -36,7 +38,8 @@
"import metpy\n",
"import cartopy.crs as ccrs\n",
"import cfunits\n",
- "import json"
+ "import json\n",
+ "from shapely.geometry import Polygon, mapping"
]
},
{
@@ -51,7 +54,9 @@
"cell_type": "code",
"execution_count": null,
"id": "adf6c59d-58cd-48b1-a5fd-3bb205a3ef56",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# define folder location where your STAC catalog json file is\n",
@@ -72,7 +77,9 @@
"cell_type": "code",
"execution_count": null,
"id": "482d204d-b5b6-40e5-ac42-55b459be1097",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# url to zarr store that you want to create a collection for\n",
@@ -88,11 +95,7 @@
"asset_roles = [\"data\",\"zarr\",\"s3\"]\n",
"\n",
"# name for STAC collection\n",
- "item_id = 'conus404-daily'\n",
- "# description of STAC collection\n",
- "item_description = 'CONUS404 40 years of daily values for subset of model output variables derived from hourly values on cloud storage'\n",
- "# license for dataset\n",
- "item_license = 'CC0-1.0'"
+ "item_id = 'conus404-daily'"
]
},
{
@@ -109,7 +112,9 @@
"cell_type": "code",
"execution_count": null,
"id": "708f2cf5-79ab-49af-8067-de31d0d13ee6",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# open and view zarr dataset\n",
@@ -132,7 +137,9 @@
"cell_type": "code",
"execution_count": null,
"id": "ab91268f-7200-4cb1-979a-c7d75531d2c0",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"dims_auto_extract = ['X', 'Y', 'T']\n",
@@ -167,7 +174,9 @@
"cell_type": "code",
"execution_count": null,
"id": "4eb4d027-4266-4a0b-8f16-bacfbef06242",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# plot a map of a single variable\n",
@@ -190,7 +199,9 @@
"cell_type": "code",
"execution_count": null,
"id": "c7de2681-88c2-4597-857c-8f169c596f8b",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# enter lat, lon of point you want to plot time series for\n",
@@ -209,7 +220,7 @@
"id": "a8c3ed37-8564-400b-a7fb-25bd5e43d21c",
"metadata": {},
"source": [
- "## Create Collection Extent"
+ "## Create Item Geometry, BBox, Datetime"
]
},
{
@@ -217,14 +228,16 @@
"id": "69f0d837-68a5-4fed-9a14-5d75cfbb0da4",
"metadata": {},
"source": [
- "### Spatial Extent"
+ "### Spatial - Geometry and bbox"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d46805e0-8e94-4ebe-aa01-d9a2d7051459",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# pull out lat/lon bbox for data\n",
@@ -235,8 +248,14 @@
"#coord_bounds = [ds.lon.data.min().compute().astype(float), ds.lat.data.min().compute().astype(float), ds.lon.data.max().compute().astype(float), ds.lat.data.max().compute().astype(float)]\n",
"coord_bounds = [ds.lon.data.min().astype(float), ds.lat.data.min().astype(float), ds.lon.data.max().astype(float), ds.lat.data.max().astype(float)]\n",
"print(coord_bounds)\n",
- "# create a spatial extent object \n",
- "spatial_extent = pystac.SpatialExtent(bboxes=[coord_bounds])"
+ "# create a geometry object \n",
+ "footprint = mapping(Polygon([\n",
+ " [coord_bounds[0], coord_bounds[1]],\n",
+ " [coord_bounds[0], coord_bounds[3]],\n",
+ " [coord_bounds[2], coord_bounds[3]],\n",
+ " [coord_bounds[2], coord_bounds[1]]\n",
+ " ]))\n",
+ "print(footprint)"
]
},
{
@@ -244,32 +263,22 @@
"id": "a04c8fca-1d33-43ac-9e2b-62d7be2887f7",
"metadata": {},
"source": [
- "### Temporal Extent"
+ "### Temporal - datetime"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "41a84995-867c-4152-8c57-85e3758bbb77",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
"# pull out first and last timestamps\n",
"temporal_extent_lower = pd.Timestamp(ds[dim_names_dict['T']].data.min())\n",
"temporal_extent_upper = pd.Timestamp(ds[dim_names_dict['T']].data.max())\n",
- "print(f'min: {temporal_extent_lower} \\nmax: {temporal_extent_upper}')\n",
- "# create a temporal extent object\n",
- "temporal_extent = pystac.TemporalExtent(intervals=[[temporal_extent_lower, temporal_extent_upper]])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "1b1e37c4-5348-46ad-abc9-e005b5d6c02b",
- "metadata": {},
- "outputs": [],
- "source": [
- "collection_extent = pystac.Extent(spatial=spatial_extent, temporal=temporal_extent)"
+ "print(f'min: {temporal_extent_lower} \\nmax: {temporal_extent_upper}')"
]
},
{
@@ -277,28 +286,28 @@
"id": "cfb71202-03df-45b5-ac2f-0dc2ee1ab780",
"metadata": {},
"source": [
- "## Create pystac collection"
+ "## Create pystac item"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7e96811b-95ae-406a-9728-55fc429d4e1f",
- "metadata": {},
+ "metadata": {
+ "tags": []
+ },
"outputs": [],
"source": [
- "if catalog.get_child(collection_id):\n",
- " collection = catalog.get_child(collection_id)\n",
- " print(\"existing collection opened\")\n",
- " collection.extent=collection_extent\n",
- " collection.description=collection_description\n",
- " collection.license=collection_license\n",
+ "if next(catalog.get_items(item_id), None):\n",
+ " item = next(catalog.get_items(item_id), None)()\n",
+ " print(\"existing item opened\")\n",
"else:\n",
- " collection = pystac.Collection(id=collection_id,\n",
- " description=collection_description,\n",
- " extent=collection_extent,\n",
- " license=collection_license)\n",
- " print(\"new collection created\")"
+ " item = pystac.Item(id=item_id,\n",
+ " geometry=footprint,\n",
+ " bbox=coord_bounds,\n",
+ " datetime=temporal_extent_upper,\n",
+ " properties={})\n",
+ " print(\"new item created\")"
]
},
{
@@ -306,7 +315,7 @@
"id": "a21c76e8-cd57-4eb5-a33f-7c668a3b3205",
"metadata": {},
"source": [
- "## Add zarr url asset to collection"
+ "## Add zarr url asset to item"
]
},
{
@@ -322,7 +331,7 @@
" media_type=\"application/vnd+zarr\",\n",
" roles=asset_roles,\n",
" extra_fields = xarray_opendataset_kwargs)\n",
- "collection.add_asset(asset_id, asset)"
+ "item.add_asset(asset_id, asset)"
]
},
{
@@ -330,7 +339,7 @@
"id": "f67cd5c9-db33-45c2-bc21-480cd67354f4",
"metadata": {},
"source": [
- "## Add datacube extension to collection"
+ "## Add datacube extension to item"
]
},
{
@@ -341,7 +350,7 @@
"outputs": [],
"source": [
"# instantiate extention on collection\n",
- "dc = DatacubeExtension.ext(collection, add_if_missing=True)"
+ "dc = DatacubeExtension.ext(item, add_if_missing=True)"
]
},
{
@@ -588,7 +597,19 @@
"id": "615ca168-75fb-4135-9941-0ef5fe4fd1cb",
"metadata": {},
"source": [
- "## Add STAC Collection to Catalog and Save"
+ "## Add STAC Item to Catalog and Save"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "161949f9-e839-4497-8314-cab8a3871669",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "json.dumps(item.to_dict())"
]
},
{
@@ -598,19 +619,31 @@
"metadata": {},
"outputs": [],
"source": [
- "if catalog.get_child(collection_id):\n",
- " collection.normalize_and_save(root_href=os.path.join(catalog_path, collection_id), catalog_type=pystac.CatalogType.SELF_CONTAINED)\n",
+ "if next(catalog.get_items(item_id), None):\n",
+ " #item.normalize_and_save(root_href=os.path.join(catalog_path, item_id), catalog_type=pystac.CatalogType.SELF_CONTAINED)\n",
+ " catalog.normalize_hrefs(catalog_path)\n",
+ " catalog.save(catalog_type=pystac.CatalogType.SELF_CONTAINED)\n",
"else:\n",
- " catalog.add_child(collection)\n",
- " catalog.normalize_and_save(root_href=catalog_path, catalog_type=pystac.CatalogType.SELF_CONTAINED)"
+ " catalog.add_item(item)\n",
+ " catalog.normalize_hrefs(catalog_path)\n",
+ " catalog.save(catalog_type=pystac.CatalogType.SELF_CONTAINED)\n",
+ " #catalog.normalize_and_save(root_href=catalog_path, catalog_type=pystac.CatalogType.SELF_CONTAINED)"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ca08bfcb-53c3-4573-bece-408da8964302",
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {
"kernelspec": {
- "display_name": "geo",
+ "display_name": "global-global-pangeo",
"language": "python",
- "name": "python3"
+ "name": "conda-env-global-global-pangeo-py"
},
"language_info": {
"codemirror_mode": {
@@ -622,7 +655,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.10.0"
+ "version": "3.10.13"
}
},
"nbformat": 4,
--
GitLab