{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "source": [
    "## GRIB: missing values"
   ]
  },
  {
   "attachments": {},
   "cell_type": "raw",
   "metadata": {
    "editable": true,
    "raw_mimetype": "text/restructuredtext",
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "source": [
    "We :ref:`read <data-sources-file>` a GRIB file containing 2 messages with missing values. First we ensure the example file is available."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import earthkit.data as ekd\n",
    "ekd.download_example_file(\"missing.grib\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "fs = ekd.from_source(\"file\", \"missing.grib\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>centre</th>\n",
       "      <th>shortName</th>\n",
       "      <th>typeOfLevel</th>\n",
       "      <th>level</th>\n",
       "      <th>dataDate</th>\n",
       "      <th>dataTime</th>\n",
       "      <th>stepRange</th>\n",
       "      <th>dataType</th>\n",
       "      <th>number</th>\n",
       "      <th>gridType</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ecmf</td>\n",
       "      <td>2t</td>\n",
       "      <td>surface</td>\n",
       "      <td>0</td>\n",
       "      <td>20200513</td>\n",
       "      <td>1200</td>\n",
       "      <td>0</td>\n",
       "      <td>an</td>\n",
       "      <td>0</td>\n",
       "      <td>regular_ll</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ecmf</td>\n",
       "      <td>msl</td>\n",
       "      <td>surface</td>\n",
       "      <td>0</td>\n",
       "      <td>20200513</td>\n",
       "      <td>1200</td>\n",
       "      <td>0</td>\n",
       "      <td>an</td>\n",
       "      <td>0</td>\n",
       "      <td>regular_ll</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  centre shortName typeOfLevel  level  dataDate  dataTime stepRange dataType  \\\n",
       "0   ecmf        2t     surface      0  20200513      1200         0       an   \n",
       "1   ecmf       msl     surface      0  20200513      1200         0       an   \n",
       "\n",
       "   number    gridType  \n",
       "0       0  regular_ll  \n",
       "1       0  regular_ll  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fs.ls()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When can see how many missing values we have by inspecting the metadata:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 1]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fs.metadata(\"bitmapPresent\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[142, 13]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fs.metadata(\"numberOfMissingValues\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When data values are extracted as numpy arrays missing values are automatically replaced by np.nan:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of nans=142\n",
      "Number of nans=13\n"
     ]
    }
   ],
   "source": [
    "for f in fs:\n",
    "    v = f.values\n",
    "    print(f\"Number of nans={np.count_nonzero(np.isnan(v))}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dev_ecc",
   "language": "python",
   "name": "dev_ecc"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}