Update xenium morton code nb

Author: keller-mark

docs/notebooks/spatial_data_xenium_morton.ipynb

@@ -47,7 +47,6 @@
     "from vitessce.data_utils import (\n",
     "    sdata_morton_sort_points,\n",
     "    sdata_points_process_columns,\n",
-    "    sdata_points_write_bounding_box_attrs,\n",
     "    sdata_points_modify_row_group_size,\n",
     "    sdata_morton_query_rect,\n",
     ")"
@@ -59,7 +58,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from spatialdata import read_zarr"
+    "from spatialdata import read_zarr\n",
+    "from spatialdata.models import PointsModel"
    ]
   },
   {
@@ -70,7 +70,7 @@
    "source": [
     "data_dir = \"data\"\n",
     "zip_filepath = join(data_dir, \"xenium_rep1_io.spatialdata.zarr.zip\")\n",
-    "spatialdata_filepath = join(data_dir, \"xenium_rep1_io.spatialdata.zarr\")"
+    "spatialdata_filepath = join(data_dir, \"xenium_rep1_io2.spatialdata.zarr\")"
    ]
   },
   {
@@ -82,7 +82,7 @@
     "if not isdir(spatialdata_filepath):\n",
     "    if not isfile(zip_filepath):\n",
     "        os.makedirs(data_dir, exist_ok=True)\n",
-    "        urlretrieve('https://s3.embl.de/spatialdata/spatialdata-sandbox/xenium_rep1_io.zip', zip_filepath)\n",
+    "        urlretrieve('https://data-2.vitessce.io/sdata-datasets/xenium_rep1_io.spatialdata.zarr.zip', zip_filepath)\n",
     "    with zipfile.ZipFile(zip_filepath,\"r\") as zip_ref:\n",
     "        zip_ref.extractall(data_dir)\n",
     "        os.rename(join(data_dir, \"data.zarr\"), spatialdata_filepath)\n",
@@ -161,6 +161,15 @@
     "sdata.points['transcripts'].head()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "transformations = sdata['transcripts'].attrs['transform']"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -223,15 +232,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sdata[\"transcripts_with_morton_codes\"] = ddf\n",
-    "sdata.write_element(\"transcripts_with_morton_codes\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Step 4. Write bounding box metadata with `sdata_points_write_bounding_box_attrs`"
+    "del ddf.attrs['transform']"
    ]
   },
   {
@@ -240,14 +241,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sdata_points_write_bounding_box_attrs(sdata, \"transcripts_with_morton_codes\")"
+    "sdata[\"transcripts_with_morton_codes\"] = PointsModel.parse(ddf, feature_key=\"feature_name\", instance_key=\"cell_id\", transformations=transformations)\n",
+    "sdata.write_element(\"transcripts_with_morton_codes\")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Step 5. Modify the row group sizes of the Parquet files with `sdata_points_modify_row_group_size`"
+    "### Step 4. Modify the row group sizes of the Parquet files with `sdata_points_modify_row_group_size`"
    ]
   },
   {
@@ -278,7 +280,7 @@
     "import pyarrow.parquet as pq\n",
     "from os.path import join\n",
     "\n",
-    "parquet_file = pq.ParquetFile(join(sdata.path, \"points\", \"transcripts_with_morton_codes\", \"points.parquet\", \"part.0.parquet\"))\n",
+    "parquet_file = pq.ParquetFile(join(sdata.path, \"points\", \"transcripts_with_morton_codes\", \"points.parquet\", \"part.1.parquet\"))\n",
     "\n",
     "# Get the number of row groups in this part-0 file.\n",
     "num_groups = parquet_file.num_row_groups\n",
@@ -308,17 +310,28 @@
     "wrapper = SpatialDataWrapper(\n",
     "    sdata_path=spatialdata_filepath,\n",
     "    # The following paths are relative to the root of the SpatialData zarr store on-disk.\n",
-    "    image_path=\"images/rasterized\",\n",
+    "    image_path=\"images/morphology_focus\",\n",
     "    table_path=\"tables/table\",\n",
     "    obs_feature_matrix_path=\"tables/table/X\",\n",
-    "    obs_spots_path=\"shapes/cells\",\n",
+    "    obs_spots_path=\"shapes/cell_circles\",\n",
     "    coordinate_system=\"global\",\n",
     "    coordination_values={\n",
     "        # The following tells Vitessce to consider each observation as a \"spot\"\n",
     "        \"obsType\": \"cell\",\n",
     "    }\n",
     ")\n",
-    "dataset = vc.add_dataset(name='MERFISH').add_object(wrapper)\n",
+    "points_wrapper = SpatialDataWrapper(\n",
+    "    sdata_path=spatialdata_filepath,\n",
+    "    # The following paths are relative to the root of the SpatialData zarr store on-disk.\n",
+    "    obs_points_path=\"points/transcripts_with_morton_codes\",\n",
+    "    obs_feature_matrix_path=\"tables/dense_table/X\",\n",
+    "    coordinate_system=\"global\",\n",
+    "    coordination_values={\n",
+    "        \"obsType\": \"point\",\n",
+    "        \"featureType\": \"gene\",\n",
+    "    }\n",
+    ")\n",
+    "dataset = vc.add_dataset(name='MERFISH').add_object(wrapper).add_object(points_wrapper)\n",
     "\n",
     "# Add views (visualizations) to the configuration:\n",
     "spatial = vc.add_view(\"spatialBeta\", dataset=dataset)\n",
@@ -332,6 +345,12 @@
     "    }]),\n",
     "}, scope_prefix=get_initial_coordination_scope_prefix(\"A\", \"obsSpots\"))\n",
     "\n",
+    "vc.link_views_by_dict([spatial, layer_controller], {\n",
+    "    'pointLayer': CL([{\n",
+    "        'obsType': 'point',\n",
+    "    }]),\n",
+    "}, scope_prefix=get_initial_coordination_scope_prefix(\"A\", \"obsPoints\"))\n",
+    "\n",
     "vc.link_views([spatial, layer_controller, feature_list, obs_sets], ['obsType'], [wrapper.obs_type_label])\n",
     "\n",
     "# Layout the views\n",
@@ -379,7 +398,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.14"
+   "version": "3.12.5"
   }
  },
  "nbformat": 4,