nsrdb_full_disc_check.ipynb

nsrdb_full_disc_check.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import h5pyd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "domainpath = \"/nrel/nsrdb/full_disc/nsrdb_full_disc_2022.h5\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = h5pyd.File(domainpath)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<HDF5 dataset \"dni\": shape (52560, 9462460), type \"<u2\">"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dset = f[\"dni\"]\n",
    "dset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['chunks',\n",
       " 'data_source',\n",
       " 'elevation_correction',\n",
       " 'physical_max',\n",
       " 'physical_min',\n",
       " 'psm_scale_factor',\n",
       " 'psm_units',\n",
       " 'scale_factor',\n",
       " 'source_dir',\n",
       " 'spatial_interp_method',\n",
       " 'temporal_interp_method',\n",
       " 'units']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(dset.attrs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'class': 'H5D_CHUNKED_REF_INDIRECT',\n",
       " 'file_uri': 's3://nrel-pds-nsrdb/full_disc/nsrdb_full_disc_irradiance_2022.h5',\n",
       " 'dims': [2000, 500],\n",
       " 'chunk_table': 'd-988bc5aa-b7a591d0-c746-5cc34b-579ca6'}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dset.id.layout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "chunk_table_id = dset.id.layout[\"chunk_table\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<HDF5 dataset (\"anonymous\"): shape (27, 18925), type \"|V12\">"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chunk_table = f[f\"datasets/{chunk_table_id}\"]\n",
    "chunk_table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "510975"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chunk_count = np.prod(chunk_table.shape)\n",
    "chunk_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "allocated_count = 0\n",
    "arr = chunk_table[...]\n",
    "for row in arr:\n",
    "    for x in row:\n",
    "        if x:\n",
    "            allocated_count += 1\n",
    "allocated_count"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py39",
   "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": "3.9.15"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}