diff --git a/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb b/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb
index 3e67a08cdd9b294fc452fd2e8407c4a1a7d884c6..961f375c737f138a0da52cf5cbeb6cde0801014d 100644
--- a/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb
+++ b/workflows/archive/iclus_hd_create_collection_from_zarr.ipynb
@@ -333,7 +333,7 @@
},
"outputs": [],
"source": [
- "# uncomment if you wish to use dask\n",
+ "# # 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)"
]
},
@@ -346,9 +346,9 @@
},
"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",
+ "# # 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",
@@ -376,7 +376,7 @@
},
"outputs": [],
"source": [
- "# uncomment if you wish to use dask\n",
+ "# # 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}\")"
@@ -455,7 +455,7 @@
"metadata": {},
"source": [
"### Temporal Extent\n",
- "No time step in this dataset, so we will use null."
+ "Had to manually construct because xarray can't decode times"
]
},
{
@@ -470,8 +470,8 @@
"# 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",
+ "temporal_extent_lower = pd.Timestamp('2005-01-01 00:00')\n",
+ "temporal_extent_upper = pd.Timestamp('2100-01-01 00:00')\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]])"
@@ -589,6 +589,18 @@
"## Add datacube extension to collection"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7a50df9b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# reset dims to true dims\n",
+ "dim_names_dict = {'X': 'x', 'Y': 'y', 'T': 'time'}\n",
+ "print(f\"Dimension dictionary: {dim_names_dict}\")"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
@@ -698,8 +710,10 @@
},
"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}')"
+ "#time_step = pd.Timedelta(stac_helpers.get_step(ds, dim_names_dict['T'], time_dim=True)).isoformat()\n",
+ "# if time is yearly or monthly, you will need to manually construct it:\n",
+ "time_step = \"P5Y0M0DT0H0M0S\"\n",
+ "print(f'time step: {time_step}')"
]
},
{
@@ -846,7 +860,9 @@
"\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)."
+ "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).\n",
+ "\n",
+ "Removed reference system because x and y are indices - not geospatial."
]
},
{
@@ -878,9 +894,10 @@
"\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",
- "}"
+ "dims_dict = {dim_names_dict['T']: pystac.extensions.datacube.Dimension({'type': 'temporal', 'description': stac_helpers.get_long_name(ds, dim_names_dict['T']), 'extent': [temporal_extent_lower.strftime('%Y-%m-%dT%XZ'), temporal_extent_upper.strftime('%Y-%m-%dT%XZ')], 'step':time_step}),\n",
+ " dim_names_dict['X']: pystac.extensions.datacube.Dimension({'type': 'spatial', 'axis': 'x', 'description': stac_helpers.get_long_name(ds, dim_names_dict['X']), 'extent': [ds.x.min().item(), ds.x.max().item()], 'step': x_step}),\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': [ds.y.min().item(), ds.y.max().item()], 'step': y_step}),\n",
+ " }"
]
},
{
@@ -995,9 +1012,9 @@
],
"metadata": {
"kernelspec": {
- "display_name": "global-global-pangeo",
+ "display_name": "geo",
"language": "python",
- "name": "conda-env-global-global-pangeo-py"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
@@ -1009,7 +1026,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.6"
+ "version": "3.10.0"
}
},
"nbformat": 4,