compressed_encoding.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8332bd3f-a657-42b9-9067-210d4de0e565",
   "metadata": {},
   "outputs": [],
   "source": [
    "import xarray as xr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "223fd220-fca1-4a70-9c4a-f7484370c888",
   "metadata": {},
   "outputs": [],
   "source": [
    "zlib_url = \"zlib.nc\"\n",
    "url = \"air.nc\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "24b2ef34-6027-4e42-8e2e-69abea557b89",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/seanharkins/micromamba/envs/virtualizarr-notebooks/lib/python3.12/site-packages/IPython/core/interactiveshell.py:3577: SerializationWarning: saving variable air with floating point data as an integer dtype without any _FillValue to use for NaNs\n",
      "  exec(code_obj, self.user_global_ns, self.user_ns)\n"
     ]
    }
   ],
   "source": [
    "ds = xr.tutorial.open_dataset(\"air_temperature\")\n",
    "encoding = {}\n",
    "encoding_config = {\"zlib\": True, \"complevel\": 1}\n",
    "for var_name in ds.variables:\n",
    "    encoding[var_name] = encoding_config\n",
    "ds.to_netcdf(zlib_url, encoding=encoding)\n",
    "ds.to_netcdf(url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "23b7bf88-6673-45cf-a81b-f273627b24ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'dtype': dtype('int64'),\n",
       " 'zlib': True,\n",
       " 'szip': False,\n",
       " 'zstd': False,\n",
       " 'bzip2': False,\n",
       " 'blosc': False,\n",
       " 'shuffle': True,\n",
       " 'complevel': 1,\n",
       " 'fletcher32': False,\n",
       " 'contiguous': False,\n",
       " 'chunksizes': (2920,),\n",
       " 'preferred_chunks': {'time': 2920},\n",
       " 'source': '/Users/seanharkins/Downloads/kerchunk_test/zlib.nc',\n",
       " 'original_shape': (2920,),\n",
       " 'units': 'nanoseconds since 2013-01-01 00:02:06.757437440',\n",
       " 'calendar': 'proleptic_gregorian'}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds_zlib = xr.open_dataset(\"zlib.nc\")\n",
    "ds_zlib[\"time\"].encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6a0a7fc5-1e83-4cc4-85b5-72f959462bd5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'dtype': dtype('float32'),\n",
       " 'zlib': False,\n",
       " 'szip': False,\n",
       " 'zstd': False,\n",
       " 'bzip2': False,\n",
       " 'blosc': False,\n",
       " 'shuffle': False,\n",
       " 'complevel': 0,\n",
       " 'fletcher32': False,\n",
       " 'contiguous': True,\n",
       " 'chunksizes': None,\n",
       " 'source': '/Users/seanharkins/Downloads/kerchunk_test/air.nc',\n",
       " 'original_shape': (2920,),\n",
       " '_FillValue': np.float32(nan),\n",
       " 'units': 'hours since 1800-01-01',\n",
       " 'calendar': 'standard'}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds_air = xr.open_dataset(url)\n",
    "ds_air[\"time\"].encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1aa29746-4ce4-4fb0-bc36-14f1a9ce7fbc",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}