non_coordinate_dimensions.ipynb

non_coordinate_dimensions.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1188c1b6-fff3-4fa9-acbf-53fb9b4ccca0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import h5py\n",
    "import xarray as xr\n",
    "from xarray.tests.test_dataset import create_test_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5c8dc6ff-e78c-4af1-812f-8acb5058873c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<xarray.Dataset> Size: 28kB\n",
      "Dimensions:  (dim2: 80, dim3: 10, time: 20, dim1: 20)\n",
      "Coordinates:\n",
      "  * dim2     (dim2) float64 640B 0.0 0.5 1.0 1.5 2.0 ... 38.0 38.5 39.0 39.5\n",
      "  * dim3     (dim3) <U1 40B 'a' 'b' 'c' 'd' 'e' 'f' 'g' 'h' 'i' 'j'\n",
      "  * time     (time) datetime64[ns] 160B 2000-01-01 2000-01-02 ... 2000-01-20\n",
      "    numbers  (dim3) int64 80B 1 1 1 2 2 0 1 2 0 0\n",
      "Dimensions without coordinates: dim1\n",
      "Data variables:\n",
      "    var1     (dim1, dim2) float64 13kB 0.845 -1.061 -0.4623 ... 0.2738 -0.5301\n",
      "    var2     (dim1, dim2) float64 13kB -0.8353 0.5596 0.3257 ... 2.753 1.234\n",
      "    var3     (dim3, dim1) float64 2kB -1.641 -0.4739 -0.7058 ... 1.417 1.049\n"
     ]
    }
   ],
   "source": [
    "ds = create_test_data(dim_sizes=(20, 80, 10))\n",
    "filepath = \"non_coord_dim.nc\"\n",
    "ds.to_netcdf(filepath, engine=\"h5netcdf\")\n",
    "print(ds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b2fc2980-11ab-48b2-8b4e-57b5f13864df",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f = h5py.File(filepath)\n",
    "f[\"dim1\"].id.get_storage_size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "15103286-0094-4a74-a476-06297294d9e2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<xarray.Dataset> Size: 4B\n",
      "Dimensions:  ()\n",
      "Data variables:\n",
      "    empty    float32 4B ...\n"
     ]
    }
   ],
   "source": [
    "empty_filepath = \"empty_variable.nc\"\n",
    "f_empty = h5py.File(empty_filepath, \"w\")\n",
    "f_empty.create_dataset(\"empty\", shape=(), dtype=\"float32\")\n",
    "empty_ds = xr.open_dataset(empty_filepath)\n",
    "print(empty_ds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "21c1c5d8-ab19-47f2-a027-0837b90d4933",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f_empty[\"empty\"].id.get_storage_size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "16a150c8-9fdc-4fbe-95fd-a96bb8f8112d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def determine_non_coordinate_dims(h5py_handle):\n",
    "    dimension_names = []\n",
    "    for name, obj in h5py_handle.items():\n",
    "        if \"_Netcdf4Dimid\" in obj.attrs:\n",
    "            dimension_names.append(name)\n",
    "    for name, obj in h5py_handle.items():\n",
    "        if obj.id.get_storage_size() == 0 and name in dimension_names:\n",
    "            print(f\"{name} is a dim without coordinates\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "9868576f-c5a2-4de6-88a0-fe30a47e2b5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dim1 is a dim without coordinates\n"
     ]
    }
   ],
   "source": [
    "determine_non_coordinate_dims(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "0b23028e-9b66-41a9-bde5-86010dce3d80",
   "metadata": {},
   "outputs": [],
   "source": [
    "determine_non_coordinate_dims(f_empty)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.13.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}