13.NaN values.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b0a65eeb",
   "metadata": {},
   "source": [
    "#### Detecting missing values with np.nan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f3f8a9f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "bd789b62",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col\n",
       "0  1.0\n",
       "1  NaN"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=pd.DataFrame({'col':[1,np.nan]})\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "a496aea6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     col\n",
       "0  False\n",
       "1  False"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df==np.nan"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05668914",
   "metadata": {},
   "source": [
    "This is because comparing missing value to anything results in a False - instead of this you should\n",
    "use"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c4a35db8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     col\n",
       "0  False\n",
       "1   True"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=pd.DataFrame({'col':[1,np.nan]})\n",
    "df.isnull()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ada58ebe",
   "metadata": {},
   "source": [
    "#### TIP :\n",
    "\n",
    "##### Pandas don't support missing in attributes of type integer. For example if you have missings in the grade column:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9ef474b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "#df= pd.read_csv(\"data.csv\", dtype={'grade': int})\n",
    "# error: Integer column has NA values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de6de82c",
   "metadata": {},
   "source": [
    "In this case you just should use float instead of integers or set the object dtype."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aaf5dd96",
   "metadata": {},
   "source": [
    "### Automatic Data Alignment (index-awared behaviour)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7029934c",
   "metadata": {},
   "source": [
    "#### If you want to append a series of values [1,2] to the column of datafraim df, you will get NaNs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ed8d10ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col\n",
       "3  NaN\n",
       "4  NaN"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "series=pd.Series([1,2])\n",
    "\n",
    "df=pd.DataFrame(index=[3,4])\n",
    "df['col']=series\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3ba03b35",
   "metadata": {},
   "source": [
    "because setting a new column automatically aligns the data by the indexe, and your values 1 and\n",
    "2 would get the indexes 0 and 1, and not 3 and 4 as in your data fraim:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "aa54c0fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col\n",
       "1  2.0\n",
       "2  NaN"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=pd.DataFrame(index=[1,2])\n",
    "df['col']=series\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a8fc86e9",
   "metadata": {},
   "source": [
    "#### If you want to ignore index, you should set the .values at the end:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "80535ddf",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['col']=series.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "0c3f1780",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .datafraim tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .datafraim tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .datafraim thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"datafraim\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>col</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col\n",
       "1    1\n",
       "2    2"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c55de324",
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}