Grouping Datasets by Solar Day

Grouping Datasets by Solar Day.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How to manually group datasets by _solar day_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import datacube\n",
    "from datacube.api.query import query_group_by\n",
    "\n",
    "dc = datacube.Datacube()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## First, run a query to find all the relevant datasets.\n",
    "It may be better to search for \"nbar_scene\", as there'll be less contributing datasets for a particular area.\n",
    "\n",
    "This returns a python `list` of datasets, in no particular order."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Dataset <id=7f303131-955d-458d-a6ab-d5d07a9aad49 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170107235316500000_v1508306845.nc>,\n",
       " Dataset <id=89a2e0cb-3b2f-42c8-913b-adaa6bb65a6b type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-50/LS8_OLI_NBAR_3577_13_-50_20170107235316500000_v1508439326.nc>,\n",
       " Dataset <id=bee1bea1-0b7c-44bf-9156-b3011cc2bb06 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-51/LS8_OLI_NBAR_3577_12_-51_20170107235316500000_v1508439326.nc>,\n",
       " Dataset <id=b9649694-4777-4403-8450-a876e378d2d0 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170123235311500000_v1508306845.nc>,\n",
       " Dataset <id=1b614cb8-ca99-4cbd-9071-382dda2b8ce7 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-50/LS8_OLI_NBAR_3577_13_-50_20170123235311500000_v1508306845.nc>,\n",
       " Dataset <id=c8868edb-1ca9-4ee2-b427-0db421b78e34 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-51/LS8_OLI_NBAR_3577_12_-51_20170123235311500000_v1508439326.nc>,\n",
       " Dataset <id=81fe18d8-f9d6-48d3-bd78-d42982daad4d type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-51/LS8_OLI_NBAR_3577_13_-51_20170123235311500000_v1508439326.nc>]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "datasets = dc.find_datasets(product='ls8_nbar_albers', time=('2017-01-01', '2017-02-01'), lon=(147, 148), lat=(-45, -46))\n",
    "\n",
    "datasets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The use the `group_datasets` method, to group by solar day"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[0;31mSignature:\u001b[0m \u001b[0mdc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroup_datasets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdatasets\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgroup_by\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mDocstring:\u001b[0m\n",
       "Group datasets along defined non-spatial dimensions (ie. time).\n",
       "\n",
       ":param datasets: a list of datasets, typically from :meth:`find_datasets`\n",
       ":param GroupBy group_by: Contains:\n",
       "    - a function that returns a label for a dataset\n",
       "    - name of the new dimension\n",
       "    - unit for the new dimension\n",
       "    - function to sort by before grouping\n",
       ":rtype: xarray.DataArray\n",
       "\n",
       ".. seealso:: :meth:`find_datasets`, :meth:`load_data`, :meth:`query_group_by`\n",
       "\u001b[0;31mFile:\u001b[0m      /g/data/v10/public/modules/dea/20180309/lib/python3.6/site-packages/datacube/api/core.py\n",
       "\u001b[0;31mType:\u001b[0m      function\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dc.group_datasets?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<xarray.DataArray (time: 2)>\n",
       "array([(Dataset <id=7f303131-955d-458d-a6ab-d5d07a9aad49 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170107235316500000_v1508306845.nc>, Dataset <id=89a2e0cb-3b2f-42c8-913b-adaa6bb65a6b type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-50/LS8_OLI_NBAR_3577_13_-50_20170107235316500000_v1508439326.nc>, Dataset <id=bee1bea1-0b7c-44bf-9156-b3011cc2bb06 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-51/LS8_OLI_NBAR_3577_12_-51_20170107235316500000_v1508439326.nc>),\n",
       "       (Dataset <id=b9649694-4777-4403-8450-a876e378d2d0 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170123235311500000_v1508306845.nc>, Dataset <id=1b614cb8-ca99-4cbd-9071-382dda2b8ce7 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-50/LS8_OLI_NBAR_3577_13_-50_20170123235311500000_v1508306845.nc>, Dataset <id=c8868edb-1ca9-4ee2-b427-0db421b78e34 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-51/LS8_OLI_NBAR_3577_12_-51_20170123235311500000_v1508439326.nc>, Dataset <id=81fe18d8-f9d6-48d3-bd78-d42982daad4d type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-51/LS8_OLI_NBAR_3577_13_-51_20170123235311500000_v1508439326.nc>)],\n",
       "      dtype=object)\n",
       "Coordinates:\n",
       "  * time     (time) datetime64[ns] 2017-01-07T23:53:16.500000 ..."
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "group_by_solarday = query_group_by('solar_day')\n",
    "grouped = dc.group_datasets(datasets, group_by=group_by_solarday)\n",
    "grouped"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## This has returned a rather awkward data structure, which is an `xarray.DataArray`, with a time dimension, where each element of the array is the set of data which contributes to that *grouped* observation time\n",
    "\n",
    "We can see what the times are that we have ended up with."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['2017-01-07T23:53:16.500000000', '2017-01-23T23:53:11.500000000'],\n",
       "      dtype='datetime64[ns]')"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.time.data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## We can see all the datasets that contribute to the data for the first time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Dataset <id=7f303131-955d-458d-a6ab-d5d07a9aad49 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170107235316500000_v1508306845.nc>,\n",
       " Dataset <id=89a2e0cb-3b2f-42c8-913b-adaa6bb65a6b type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/13_-50/LS8_OLI_NBAR_3577_13_-50_20170107235316500000_v1508439326.nc>,\n",
       " Dataset <id=bee1bea1-0b7c-44bf-9156-b3011cc2bb06 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-51/LS8_OLI_NBAR_3577_12_-51_20170107235316500000_v1508439326.nc>)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.isel(time=0).data.item()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## And extract the first dataset from the first time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Dataset <id=7f303131-955d-458d-a6ab-d5d07a9aad49 type=ls8_nbar_albers location=/g/data/rs0/datacube/002/LS8_OLI_NBAR/12_-50/LS8_OLI_NBAR_3577_12_-50_20170107235316500000_v1508306845.nc>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped.isel(time=0).data.item()[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It's also possible to view the datasets on the DEA Dashboard, by copying the `id` to the end of the dashboard URL.\n",
    "\n",
    "eg. https://data.dea.gadevs.ga/dataset/7f303131-955d-458d-a6ab-d5d07a9aad49"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}