automatic chunk size

anomaly-chunksize.ipynb

anomaly-chunksizesimplifyed.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.array as da\n",
    "import numpy as np\n",
    "import dask\n",
    "import xarray as xr\n",
    "import math\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "freq=\"1D\"\n",
    "dask.config.set({\"array.chunk-size\": '256MB'})\n",
    "timesteps=20834; lat=320; lon=384\n",
    "shape=(timesteps,lon,lat)\n",
    "chunks=(-1,'auto','auto')\n",
    "lats = xr.DataArray(np.linspace(start=-90, stop=90, num=lat), dims=[\"lat\"])\n",
    "lons = xr.DataArray(np.linspace(start=-180, stop=180, num=lon), dims=[\"lon\"])\n",
    "times = xr.DataArray(pd.date_range(start=\"1980-01-01\", freq=freq, periods=timesteps), dims=[\"time\"])\n",
    "random_data =da.random.RandomState(0).standard_normal(shape, chunks=chunks  )\n",
    "ds = xr.DataArray( random_data, dims=[\"time\", \"lon\", \"lat\"], coords={\"time\": times, \"lon\": lons, \"lat\": lats}, name=\"sst\").to_dataset()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dask.array<standard_normal, shape=(20834, 384, 320), dtype=float64, chunksize=(20834, 32, 32)>"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When specifying chunk size as 370MB in dask, dask array creates chunksize 187MB."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/todaka/miniconda3/envs/pangeobench/lib/python3.6/site-packages/xarray/core/indexing.py:1195: PerformanceWarning: Slicing with an out-of-order index is generating 58 times more chunks\n",
      "  return self.array[key]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Frozen(SortedKeysDict({'time': (60, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 90, 92, 92, 91, 91, 92, 92, 91, 45), 'lon': (32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32), 'lat': (32, 32, 32, 32, 32, 32, 32, 32, 32, 32)}))"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "climate= ds.groupby(\"time.season\").mean(dim=\"time\")\n",
    "anomaly=ds.groupby(\"time.season\") - climate\n",
    "anomaly.chunks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Frozen(SortedKeysDict({'season': (1, 1, 1, 1), 'lon': (32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32), 'lat': (32, 32, 32, 32, 32, 32, 32, 32, 32, 32)}))"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "climate.chunks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pangeobench",
   "language": "python",
   "name": "pangeobench"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

auto_chunkstest.ipynb

automatic_chunksize.ipynb