diff --git a/workflows/archive/iclus_hc_create_collection_from_zarr.ipynb b/workflows/archive/iclus_hc_create_collection_from_zarr.ipynb
index eba8e73c0812da9760bec8a3cbb1c5fb09a2a88c..c0bee4fa7f93c86bc161976b53adde6f1e73672f 100644
--- a/workflows/archive/iclus_hc_create_collection_from_zarr.ipynb
+++ b/workflows/archive/iclus_hc_create_collection_from_zarr.ipynb
@@ -344,10 +344,10 @@
"# choose a size for the chunks - these are square chunks that are chunk_len x chunk_len\n",
"# this size worked on a dask cluster on my local computer\n",
"# I haven't been able to get it optimized to work on Nebari, so this will crash if you run the delayed function below\n",
- "chunk_len = 10000\n",
- "XX_chunked = XX.rechunk((chunk_len, chunk_len)).ravel()\n",
- "YY_chunked = YY.rechunk((chunk_len, chunk_len)).ravel()\n",
- "XX_chunked"
+ "# chunk_len = 10000\n",
+ "# XX_chunked = XX.rechunk((chunk_len, chunk_len)).ravel()\n",
+ "# YY_chunked = YY.rechunk((chunk_len, chunk_len)).ravel()\n",
+ "# XX_chunked"
]
},
{
@@ -990,9 +990,9 @@
],
"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": {
@@ -1004,7 +1004,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.10.0"
+ "version": "3.11.6"
}
},
"nbformat": 4,
diff --git a/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb b/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..3e67a08cdd9b294fc452fd2e8407c4a1a7d884c6
--- /dev/null
+++ b/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb
@@ -0,0 +1,1017 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "6c10e07b-1e60-4926-af1d-fa75dc78e5d4",
+ "metadata": {
+ "tags": []
+ },
+ "source": [
+ "# iclus_hd Zarr -> Collection Workflow\n",
+ "This is a workflow to build a [STAC collection](https://github.com/radiantearth/stac-spec/blob/master/collection-spec/collection-spec.md) from the zarr asset for the dataset named above. We use the [datacube extension](https://github.com/stac-extensions/datacube) to define the spatial and temporal dimensions of the zarr store, as well as the variables it contains.\n",
+ "\n",
+ "To simplify this workflow so that it can scale to many datasets, a few simplifying suggestions and assumptions are made:\n",
+ "1. For USGS data, we can use the CC0-1.0 license. For all other data we can use Unlicense. Ref: https://spdx.org/licenses/\n",
+ "2. I am assuming all coordinates are from the WGS84 datum if not specified."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "201e0945-de55-45ff-b095-c2af009a4e62",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import pystac\n",
+ "from pystac.extensions.datacube import CollectionDatacubeExtension, AssetDatacubeExtension, AdditionalDimension, DatacubeExtension\n",
+ "import xarray as xr\n",
+ "import cf_xarray\n",
+ "import os\n",
+ "import fsspec\n",
+ "import cf_xarray\n",
+ "import hvplot.xarray\n",
+ "import pandas as pd\n",
+ "import json\n",
+ "import numpy as np\n",
+ "import pyproj\n",
+ "from pyproj import Transformer\n",
+ "import cartopy.crs as ccrs\n",
+ "import cfunits\n",
+ "import json\n",
+ "import sys\n",
+ "sys.path.insert(1, '..')\n",
+ "import stac_helpers\n",
+ "import dask\n",
+ "import dask.array as da\n",
+ "from dask.distributed import Client, LocalCluster\n",
+ "import pyproj"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7a8b3517-7556-4092-9946-289fb347bce2",
+ "metadata": {},
+ "source": [
+ "## Collection ID"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "afab2f46-d8bd-4c9a-bb7e-922612da136d",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# name for STAC collection\n",
+ "collection_id = 'iclus_hd'"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "116b5837-8e85-4ae7-964a-803533ded714",
+ "metadata": {
+ "tags": []
+ },
+ "source": [
+ "## Asset Metadata Input"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "dd6fa323-132a-4794-8c80-576933f547a0",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# url to zarr store that you want to create a collection for\n",
+ "zarr_url = f's3://mdmf-workspace/gdp/{collection_id}.zarr/'\n",
+ "\n",
+ "# define keyword arguments needed for opening the dataset with xarray\n",
+ "# ref: https://github.com/stac-extensions/xarray-assets\n",
+ "xarray_opendataset_kwargs = {\"xarray:open_kwargs\":{\"chunks\":{},\"engine\":\"zarr\",\"consolidated\":True},\n",
+ " \"xarray:storage_options\": {\"anon\": True, \"client_kwargs\": {\"endpoint_url\":\"https://usgs.osn.mghpcc.org/\"}}}\n",
+ "# description for zarr url asset attached to collection (zarr_url)\n",
+ "asset_description = \"Open Storage Network Pod S3 API access to collection zarr group\"\n",
+ "# roles to tag zarr url asset with\n",
+ "asset_roles = [\"data\",\"zarr\",\"s3\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e1441cd4-e94c-4902-af46-8f1af470eb6b",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# url to zarr store that you want to create a collection for\n",
+ "zarr_url2 = f's3://nhgf-development/workspace/DataConversion/{collection_id}.zarr/'\n",
+ "\n",
+ "# define keyword arguments needed for opening the dataset with xarray\n",
+ "# ref: https://github.com/stac-extensions/xarray-assets\n",
+ "xarray_opendataset_kwargs2 = {\"xarray:open_kwargs\":{\"chunks\":{},\"engine\":\"zarr\",\"consolidated\":True},\n",
+ " \"xarray:storage_options\":{\"requester_pays\":True}}\n",
+ "# description for zarr url asset attached to collection (zarr_url)\n",
+ "asset_description2 = \"S3 access to collection zarr group\"\n",
+ "# roles to tag zarr url asset with\n",
+ "asset_roles2 = [\"data\",\"zarr\",\"s3\"]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b213b74f-ad17-4774-93b6-3b62be616b45",
+ "metadata": {
+ "tags": []
+ },
+ "source": [
+ "## Data Exploration"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "708f2cf5-79ab-49af-8067-de31d0d13ee6",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # open and view zarr dataset\n",
+ "# fs2 = fsspec.filesystem('s3', anon=True, endpoint_url='https://usgs.osn.mghpcc.org/')\n",
+ "# ds = xr.open_dataset(fs2.get_mapper(zarr_url), engine='zarr', \n",
+ "# backend_kwargs={'consolidated':True}, chunks={}, decode_times=False)\n",
+ "fs2 = fsspec.filesystem('s3', profile='osn-mdmf-workspace', endpoint_url='https://usgs.osn.mghpcc.org/')\n",
+ "ds = xr.open_dataset(fs2.get_mapper(zarr_url), engine='zarr', \n",
+ " backend_kwargs={'consolidated':True}, chunks={}, decode_times=False)\n",
+ "ds"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "996e60ba-13e4-453a-8534-e62ce747f0fa",
+ "metadata": {},
+ "source": [
+ "## Collection Metadata Input"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "482d204d-b5b6-40e5-ac42-55b459be1097",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# description of STAC collection\n",
+ "collection_description = ds.attrs['title']\n",
+ "print(f'collection description: {collection_description}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1c93d7c5-c265-48b3-a6f5-f95c404fcb30",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# license for dataset\n",
+ "collection_license = stac_helpers.license_picker(ds.attrs['license'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "0bc7e9b3-ad62-4b10-a18e-66b7ed2d35dc",
+ "metadata": {},
+ "source": [
+ "## Identify x, y, t dimensions of dataset\n",
+ "May require user input if dimensions cannot be auto-detected.\n",
+ "\n",
+ "**X and Y dims are indices only, but we will enter the geospatial vars of geoX and geoY here to detect the bounds of the dataset**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ab91268f-7200-4cb1-979a-c7d75531d2c0",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# dims_auto_extract = ['X', 'Y', 'T']\n",
+ "# dim_names_dict = {}\n",
+ "# for d in dims_auto_extract:\n",
+ "# dim_names_dict[d] = stac_helpers.extract_dim(ds, d)\n",
+ "dim_names_dict = {'X': 'geoX', 'Y': 'geoY', 'T': 'time'}\n",
+ "print(f\"Dimension dictionary: {dim_names_dict}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "810d7480-165d-41c0-bd09-163656a14003",
+ "metadata": {},
+ "source": [
+ "## Get crs info"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b2520710-a8a0-466d-adef-9ed01ed3dccf",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "crs_var = 'crs'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b03d52f3-1367-4255-a561-52ee4fc9e92d",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# use pyproj to automatically extract crs info\n",
+ "crs = pyproj.CRS.from_cf(ds[crs_var].attrs)\n",
+ "\n",
+ "# alternatively, create the appropriate cartopy projection\n",
+ "# crs = ccrs.LambertConformal(central_longitude=crs_info.longitude_of_central_meridian, \n",
+ "# central_latitude=crs_info.latitude_of_projection_origin,\n",
+ "# standard_parallels=crs_info.standard_parallel)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "85b76e94-b1c3-499a-8679-947c30638a5f",
+ "metadata": {},
+ "source": [
+ "### Compare dataset crs var to generated proj4 string to make sure it looks ok"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "391b86aa-c5a8-4bae-9303-3a40ede8e8b6",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "ds[crs_var]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6bc00354-50d0-4e4c-ae42-1964fe7acba5",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "crs.to_proj4()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a8c3ed37-8564-400b-a7fb-25bd5e43d21c",
+ "metadata": {},
+ "source": [
+ "## Create Collection Extent"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "69f0d837-68a5-4fed-9a14-5d75cfbb0da4",
+ "metadata": {},
+ "source": [
+ "### Spatial Extent\n",
+ "##### WARNING - make sure data type is **float** NOT **numpy.float64**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d46805e0-8e94-4ebe-aa01-d9a2d7051459",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# pull out lat/lon bbox for data\n",
+ "# coordinates must be from WGS 84 datum\n",
+ "# left, bottom, right, top\n",
+ "\n",
+ "# Note: try changing around the commented out lines below to get type float ratherthan a numpy float\n",
+ "#spatial_bounds = [ds[dim_names_dict['X']].data.min().compute().astype(float), ds[dim_names_dict['Y']].data.min().compute().astype(float), ds[dim_names_dict['X']].data.max().compute().astype(float), ds[dim_names_dict['Y']].data.max().compute().astype(float)]\n",
+ "spatial_bounds = [ds[dim_names_dict['X']].data.min().compute().astype(float).tolist(), ds[dim_names_dict['Y']].data.min().compute().astype(float).tolist(), ds[dim_names_dict['X']].data.max().compute().astype(float).tolist(), ds[dim_names_dict['Y']].data.max().compute().astype(float).tolist()]\n",
+ "#spatial_bounds = [ds[dim_names_dict['X']].data.min().astype(float).item(), ds[dim_names_dict['Y']].data.min().astype(float).item(), ds[dim_names_dict['X']].data.max().astype(float).item(), ds[dim_names_dict['Y']].data.max().astype(float).item()]\n",
+ "print(spatial_bounds)\n",
+ "print(f'\\ncoord_bounds data type: {type(spatial_bounds[0])}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "66bdcbdc-ba22-4efd-bdc0-feda4e1546a3",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# uncomment if you wish to use dask\n",
+ "# XX, YY = dask.array.meshgrid(ds[dim_names_dict['X']].data, ds[dim_names_dict['Y']].data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "cd002502-6b03-4c13-94a0-4d529ae2e0b4",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# choose a size for the chunks - these are square chunks that are chunk_len x chunk_len\n",
+ "# this size worked on a dask cluster on my local computer\n",
+ "# I haven't been able to get it optimized to work on Nebari, so this will crash if you run the delayed function below\n",
+ "# chunk_len = 10000\n",
+ "# XX_chunked = XX.rechunk((chunk_len, chunk_len)).ravel()\n",
+ "# YY_chunked = YY.rechunk((chunk_len, chunk_len)).ravel()\n",
+ "# XX_chunked"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e0e2ebae-6f9d-4a0b-8fe8-ebf6fba2f85a",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "transformer = Transformer.from_crs(crs, \"EPSG:4326\", always_xy=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6d76fefd-fbfb-4e7e-a6a0-843744812cf4",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# uncomment if you wish to use dask\n",
+ "# cluster = LocalCluster(threads_per_worker=os.cpu_count())\n",
+ "# client = Client(cluster)\n",
+ "# print(f\"The link to view the client dashboard is:\\n> {client.dashboard_link}\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "950e428c-4623-4b43-83fe-4ef623304e94",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "#lon, lat = transformer.transform(XX.ravel(), YY.ravel())\n",
+ "@dask.delayed\n",
+ "def proc_func(XX_chunked, YY_chunked):\n",
+ " lon, lat = transformer.transform(XX_chunked, YY_chunked)\n",
+ " min_lon = lon.min()\n",
+ " min_lat = lat.min()\n",
+ " max_lon = lon.max()\n",
+ " max_lat = lat.max()\n",
+ " return min_lon, min_lat, max_lon, max_lat"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "58d545d2-54ed-4c7d-86aa-c47ac0b977c5",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# commented out because this will crash on nebari, but results from local computer are copied in the cell below\n",
+ "# result = proc_func(XX_chunked, YY_chunked).compute()\n",
+ "# min_lon = result[0]\n",
+ "# min_lat = result[1]\n",
+ "# max_lon = result[2]\n",
+ "# max_lat = result[3]\n",
+ "min_lon = -127.88612576329054\n",
+ "min_lat = 22.872641668268155\n",
+ "max_lon = -65.34617124487134\n",
+ "max_lat = 51.60365306185643"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "85a1ffa5-14fe-40c8-bd92-fc0b1646f903",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "print(f'lower left coordinates (WGS84): {min_lon}, {min_lat}')\n",
+ "print(f'upper right coordinates (WGS84): {max_lon}, {max_lat}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "72eb51cc-aff2-4b53-8ee2-df183a59d3d5",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# create a spatial extent object \n",
+ "spatial_extent = pystac.SpatialExtent(bboxes=[[min_lon, min_lat, max_lon, max_lat]])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a04c8fca-1d33-43ac-9e2b-62d7be2887f7",
+ "metadata": {},
+ "source": [
+ "### Temporal Extent\n",
+ "No time step in this dataset, so we will use null."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "41a84995-867c-4152-8c57-85e3758bbb77",
+ "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",
+ "temporal_extent_lower = None\n",
+ "temporal_extent_upper = None\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": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "collection_extent = pystac.Extent(spatial=spatial_extent, temporal=temporal_extent)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "20b00e88-5a13-46b3-9787-d9ac2d4e7bd6",
+ "metadata": {
+ "tags": []
+ },
+ "source": [
+ "## Open up NHGF STAC Catalog and create a collection"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "adf6c59d-58cd-48b1-a5fd-3bb205a3ef56",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# define folder location where your STAC catalog json file is\n",
+ "catalog_path = os.path.join('..', '..', 'catalog')\n",
+ "# open catalog\n",
+ "catalog = pystac.Catalog.from_file(os.path.join(catalog_path, 'catalog.json'))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7e96811b-95ae-406a-9728-55fc429d4e1f",
+ "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",
+ "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\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a21c76e8-cd57-4eb5-a33f-7c668a3b3205",
+ "metadata": {},
+ "source": [
+ "## Add zarr url asset to collection"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "094832af-d22b-4359-b0f6-cf687acce5cc",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "asset_id = \"zarr-s3-osn\"\n",
+ "asset = pystac.Asset(href=zarr_url,\n",
+ " description=asset_description,\n",
+ " media_type=\"application/vnd+zarr\",\n",
+ " roles=asset_roles,\n",
+ " extra_fields = xarray_opendataset_kwargs)\n",
+ "collection.add_asset(asset_id, asset)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "0c298d07-f234-4a08-986d-87f4a39e9ae6",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "asset_id2 = \"zarr-s3\"\n",
+ "asset2 = pystac.Asset(href=zarr_url2,\n",
+ " description=asset_description2,\n",
+ " media_type=\"application/vnd+zarr\",\n",
+ " roles=asset_roles2,\n",
+ " extra_fields = xarray_opendataset_kwargs2)\n",
+ "collection.add_asset(asset_id2, asset2)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f67cd5c9-db33-45c2-bc21-480cd67354f4",
+ "metadata": {},
+ "source": [
+ "## Add datacube extension to collection"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "fc00946d-2880-491d-9b3b-3aeeb4414d6c",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# instantiate extention on collection\n",
+ "dc = DatacubeExtension.ext(collection, add_if_missing=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "8bdd77a2-7587-485e-afb7-42af3a822241",
+ "metadata": {},
+ "source": [
+ "### Add cube dimensions (required field for extension)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "120a4914-3302-44a5-a282-0308ac84f040",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# list out dataset dimensions\n",
+ "# When writing data to Zarr, Xarray sets this attribute on all variables based on the variable dimensions. When reading a Zarr group, Xarray looks for this attribute on all arrays,\n",
+ "# raising an error if it can’t be found.\n",
+ "dims = list(ds.dims)\n",
+ "print(dims)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "e7dc357c-91ec-49ae-83e5-400f791f9792",
+ "metadata": {},
+ "source": [
+ "#### user input needed - you will need to look at the crs information and create a cartopy crs object after identifying the projection type:\n",
+ "reference list of cartopy projections: https://scitools.org.uk/cartopy/docs/latest/reference/projections.html"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ea452f62-5644-49b6-8a4e-7dc4f649fd1a",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# print out crs information in dataset\n",
+ "print(crs)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1b1d05ff-8e43-44a7-8343-178b112c4ad6",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # create the appropriate cartopy projection\n",
+ "# lcc = ccrs.LambertConformal(central_longitude=crs_info.longitude_of_central_meridian, \n",
+ "# central_latitude=crs_info.latitude_of_projection_origin,\n",
+ "# standard_parallels=crs_info.standard_parallel)\n",
+ "# # the datacube extension can accept reference_system information as a numerical EPSG code, \n",
+ "# # WKT2 (ISO 19162) string or PROJJSON object.\n",
+ "# # we will use a projjson, as was done by Microsoft Planetary Computer here:\n",
+ "# # https://planetarycomputer.microsoft.com/dataset/daymet-annual-na\n",
+ "# # https://planetarycomputer.microsoft.com/api/stac/v1/collections/daymet-annual-na\n",
+ "# projjson = json.loads(lcc.to_json())\n",
+ "\n",
+ "# alternatively, I think we could do this:\n",
+ "projjson = crs.to_json()\n",
+ "print(projjson)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "b6b88ee9-60c2-4d91-af74-c1c56b094826",
+ "metadata": {},
+ "source": [
+ "#### user review needed - looks at the steps pulled out and make sure they make sense"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "9e2bbcc5-e45a-4b8c-9d60-601f345e8134",
+ "metadata": {},
+ "source": [
+ "**Time** - no time step in this dataset"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "82f1e9bd-52ee-46f5-9e95-c2359d95fcf3",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# time_step = pd.Timedelta(stac_helpers.get_step(ds, dim_names_dict['T'], time_dim=True)).isoformat()\n",
+ "# print(f'time step: {time_step}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "64be65b2-de20-447a-a9c2-bd8eca3e440e",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for time steps: get all step values and locations\n",
+ "# time_step = stac_helpers.get_step(ds, dim_names_dict['T'], time_dim=True, debug=True, step_ix=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "bc8dff39-2a2e-44a0-9b30-987107c2d1e2",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for time steps, cont:\n",
+ "# # please choose one of the index locations printed above\n",
+ "# # this will print the time steps adjacent to it\n",
+ "# ix = 3343\n",
+ "# ds.isel(time=slice(ix-1,ix+3)).time"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "9aa6c8ff-8d9b-40a7-a281-39b502bd5a3d",
+ "metadata": {},
+ "source": [
+ "**X/lon**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "a8ba7695-ca45-4db2-bd46-c465f4e37eff",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "x_step = stac_helpers.get_step(ds, dim_names_dict['X'])\n",
+ "print(f'x step: {x_step}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "fac4c9f2-a952-4c7f-aa32-862957372d6f",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for spatial steps: get all step values and locations\n",
+ "# x_dim=dim_names_dict['X']\n",
+ "# x_step = stac_helpers.get_step(ds, x_dim, debug=True, step_ix=1)\n",
+ "# print(f'\\nx dim name (for next cell): {x_dim}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "8d0b5a2d-dc58-4ad6-b890-859ce6bb08de",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for spatial steps, cont:\n",
+ "# # please choose one of the index locations printed above\n",
+ "# # this will print the time steps adjacent to it\n",
+ "# ix = 5\n",
+ "# ds.isel(x=slice(ix-1,ix+3)).x"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "21b5cca4-8bb4-498d-ae6b-6b8545fffe56",
+ "metadata": {},
+ "source": [
+ "**Y/lat**\n",
+ "y goes from largest to smallest here, instead of the usual smallest to largest\n",
+ "As a result, the y step is negative. I can't find anything in the documentation telling me that I can't use negative numbers, so I will keep it negative to indicate the direction that the y axis moves in."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7405583b-ecb9-44b0-8815-048e42e55a42",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "y_step = stac_helpers.get_step(ds, dim_names_dict['Y'])\n",
+ "print(f'y step: {y_step}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ece0fe37-b54c-4721-aa9b-33d2998d191b",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for spatial steps: get all step values and locations\n",
+ "# y_dim=dim_names_dict['Y']\n",
+ "# y_step = stac_helpers.get_step(ds, y_dim, debug=True, step_ix=1)\n",
+ "# print(f'\\nx dim name (for next cell): {x_dim}')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "abdafb8f-5217-4b82-91b6-eec8183c9128",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # debugging for spatial steps, cont:\n",
+ "# # please choose one of the index locations printed above\n",
+ "# # this will print the time steps adjacent to it\n",
+ "# ix = 5\n",
+ "# ds.isel(y=slice(ix-1,ix+3)).y"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "00a5e041-081d-428d-ac2e-75d16de205e6",
+ "metadata": {},
+ "source": [
+ "#### user input needed - you will need to copy all of the dimensions printed below into the dict and fill in the appropriate attributes(type, axis, extent, etc.):\n",
+ "\n",
+ "Please see [datacube spec](https://github.com/stac-extensions/datacube?tab=readme-ov-file#dimension-object) for details on required fields.\n",
+ "\n",
+ "If you have a dimension like \"bnds\" that is used on variables like time_bnds, lon_bnds, lat_bnds to choose either the lower or upper bound, you can use and [additional dimension object](https://github.com/stac-extensions/datacube?tab=readme-ov-file#additional-dimension-object). We recommend making the type \"count\" as Microsoft Planetary Computer did [here](https://github.com/stac-extensions/datacube/blob/9e74fa706c9bdd971e01739cf18dcc53bdd3dd4f/examples/daymet-hi-annual.json#L76)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "acd45d3c-7845-47e6-9b7d-e35627a7ca9a",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "print(dims)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5a443497-67a9-4dce-a8e9-b08d31a88223",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# create a dictionary of datacube dimensions you would like to assign to this dataset\n",
+ "# dimension name should come from the dims printed in above cell\n",
+ "\n",
+ "# x, y, t dimension info is pulled out automatically using the dim dict we created above\n",
+ "# all other dims listed in above cell need to be manually written in\n",
+ "\n",
+ "# we do not recommend including redundant dimensions (do not include x,y if you have lon,lat)\n",
+ "# note that the extent of each dimension should be pulled from the dataset\n",
+ "dims_dict = {dim_names_dict['X']: pystac.extensions.datacube.Dimension({'type': 'spatial', 'axis': 'x', 'description': stac_helpers.get_long_name(ds, dim_names_dict['X']), 'extent': [spatial_bounds[0], spatial_bounds[2]], 'step': x_step, 'reference_system': projjson}),\n",
+ " dim_names_dict['Y']: pystac.extensions.datacube.Dimension({'type': 'spatial', 'axis': 'y', 'description': stac_helpers.get_long_name(ds, dim_names_dict['Y']), 'extent': [spatial_bounds[1], spatial_bounds[3]], 'step': y_step, 'reference_system': projjson}),\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "0f277883-a3fd-425f-966a-ca2140d0ef2f",
+ "metadata": {},
+ "source": [
+ "### Add cube variables (optional field for extension)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e9272931-fc0b-4f2a-9546-283033e9cde8",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# drop metpy_crs coordinate we have added\n",
+ "if 'metpy_crs' in ds.coords:\n",
+ " ds = ds.drop_vars('metpy_crs')\n",
+ "\n",
+ "# pull list of vars from dataset\n",
+ "vars = list(ds.variables)\n",
+ "\n",
+ "# spec says that the keys of cube:dimensions and cube:variables should be unique together; a key like lat should not be both a dimension and a variable.\n",
+ "# we will drop all values in dims from vars\n",
+ "vars = [v for v in vars if v not in dims]\n",
+ "\n",
+ "# Microsoft Planetary Computer includes coordinates and crs as variables here:\n",
+ "# https://planetarycomputer.microsoft.com/dataset/daymet-annual-na\n",
+ "# https://planetarycomputer.microsoft.com/api/stac/v1/collections/daymet-annual-na\n",
+ "# we will keep those in the var list\n",
+ "\n",
+ "# create dictionary of dataset variables and associated dimensions\n",
+ "vars_dict={}\n",
+ "for v in vars:\n",
+ " unit = stac_helpers.get_unit(ds, v)\n",
+ " var_type = stac_helpers.get_var_type(ds, v, crs_var)\n",
+ " long_name = stac_helpers.get_long_name(ds, v)\n",
+ " vars_dict[v] = pystac.extensions.datacube.Variable({'dimensions':list(ds[v].dims), 'type': var_type, 'description': long_name, 'unit': unit})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "11ad5352-884c-4472-8864-4570a96f66e5",
+ "metadata": {},
+ "source": [
+ "### Finalize extension"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "10141fd4-91d6-491d-878b-02653720891d",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# add dimesions and variables to collection extension\n",
+ "dc.apply(dimensions=dims_dict, variables=vars_dict)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "615ca168-75fb-4135-9941-0ef5fe4fd1cb",
+ "metadata": {},
+ "source": [
+ "## Add STAC Collection to Catalog and Save"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e2120a55-3d04-4122-a93f-29afcdb8cb1b",
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# # helper to find items of wrong type\n",
+ "# d = collection.to_dict()\n",
+ "# print(*stac_helpers.find_paths(d))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "4b75791b-6b2d-40be-b7c6-330a60888fb5",
+ "metadata": {
+ "tags": []
+ },
+ "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",
+ "else:\n",
+ " catalog.add_child(collection)\n",
+ " catalog.normalize_and_save(root_href=catalog_path, catalog_type=pystac.CatalogType.SELF_CONTAINED)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d6f676b5-e892-4bfb-8d73-2828addd838c",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "global-global-pangeo",
+ "language": "python",
+ "name": "conda-env-global-global-pangeo-py"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.11.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}