{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e436d1aa-ba07-43b5-a137-e236a0aad69e",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Medidas de Dispersión\n",
    "===\n",
    "\n",
    "* 18:39 min | Última modificación: Dicimebre 13, 2021 | [YouTube](https://youtu.be/0iGKLtAtFDs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0cfedb39-3ef3-4a4e-b4b9-0306f6a98a47",
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "31325b42-65f6-43bc-8408-4a999ce8449c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "579e5586-d2a5-4c1d-bdeb-08f228fd4734",
   "metadata": {},
   "source": [
    "## Definición del problema "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b9653db0-91ed-459b-91e4-dec7e3014213",
   "metadata": {},
   "source": [
    "El [conjunto de datos de la flor Iris](https://es.wikipedia.org/wiki/Iris_flor_conjunto_de_datos) contiene 150 muestras de las medidas del ancho y el largo del pétalo y del sépalo para las tres especies de esta flor (Iris setosa, Iris virginica e Iris versicolor). A partir de la muestra de datos se desean responder la siguiente pregunta:\n",
    "\n",
    "\n",
    "* **P2**.--- ¿Cuál es el rango típico de la longitud y ancho del pétalo y del sépalo para cada uno de los tipos de flores?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5fdd5619-3187-43c6-ae0b-430febf68673",
   "metadata": {},
   "source": [
    "## Carga de datos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f48de899-7ced-48f3-97f7-307146dfd3ab",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal_length  sepal_width  petal_length  petal_width species\n",
       "0           5.1          3.5           1.4          0.2  setosa\n",
       "1           4.9          3.0           1.4          0.2  setosa\n",
       "2           4.7          3.2           1.3          0.2  setosa\n",
       "3           4.6          3.1           1.5          0.2  setosa\n",
       "4           5.0          3.6           1.4          0.2  setosa"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal_length  sepal_width  petal_length  petal_width    species\n",
       "145           6.7          3.0           5.2          2.3  virginica\n",
       "146           6.3          2.5           5.0          1.9  virginica\n",
       "147           6.5          3.0           5.2          2.0  virginica\n",
       "148           6.2          3.4           5.4          2.3  virginica\n",
       "149           5.9          3.0           5.1          1.8  virginica"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# Se cargan los datos y se realiza una inspección\n",
    "# inicial de la tabla y los datos\n",
    "#\n",
    "iris = sns.load_dataset('iris')\n",
    "\n",
    "display(\n",
    "    iris.head(),\n",
    "    iris.tail()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "81e82104-76b4-4d8e-937a-698aaaabc646",
   "metadata": {},
   "source": [
    "## P2.--- ¿Cuál es el rango típico de la longitud y ancho del pétalo y del sépalo para cada uno de los tipos de flores?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c6681e6e-38d8-4645-aba7-39795aa7d9fc",
   "metadata": {},
   "source": [
    "Esta pregunta se refiere a una medida de la dispersión o variabilildad de los datos y a como se distribuyen."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7dbfe41-1da3-4dfa-a259-3367f61f9860",
   "metadata": {},
   "source": [
    "### Métricas basadas en la distancia respecto a las métricas de localización"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "06d5b4f3-7688-4b98-92c5-19f3e400cc03",
   "metadata": {},
   "source": [
    "**Desviación:** \n",
    "\n",
    "Diferencia entre el valor observado y el valor estimado de localización. En modelado sus sinónimos son errores o residuales."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b159f4f-6f3f-4381-9f07-861269a2822c",
   "metadata": {},
   "source": [
    "**Rango:** \n",
    "\n",
    "Diferencia entre el valor más grande y más pequeño de la muestra de los datos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2f810d1b-185d-47b2-9e3f-d6ddbc85ad92",
   "metadata": {},
   "outputs": [],
   "source": [
    "iris_melt = pd.melt(\n",
    "    iris,\n",
    "    id_vars=\"species\",\n",
    "    var_name=\"Variables\",\n",
    "    value_name=\"Values\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "28d390a6-531a-493a-8ea5-f9eedcae5604",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.catplot(\n",
    "    x=\"species\",\n",
    "    y=\"Values\",\n",
    "    data=iris_melt,\n",
    "    col=\"Variables\",\n",
    "    kind=\"swarm\",\n",
    "    col_wrap=2,\n",
    "    alpha=0.4,\n",
    "    s=7,\n",
    "    edgecolors=\"k\",\n",
    "    linewidth=1,\n",
    ")\n",
    "\n",
    "colors = ['tab:blue', 'tab:orange', 'tab:green']\n",
    "\n",
    "means = iris.groupby(\"species\").mean()\n",
    "\n",
    "for i_axes in range(4):\n",
    "    ax = g.axes[i_axes]\n",
    "    x_lim = ax.get_xlim()\n",
    "    mean_values = means[means.columns[i_axes]]\n",
    "    for i, (color, mean_value) in enumerate(zip(colors, mean_values)):\n",
    "        g.axes[i_axes].hlines(mean_value, i-0.4, i+0.4,  ls='-', color=color, lw=4)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "07afde70-9772-4888-98f9-f06b1c94f903",
   "metadata": {},
   "source": [
    "**Varianza muestral:**\n",
    "\n",
    "$$s^2 = \\frac{1}{n-1} \\sum_{i=1}^n (x_i - \\bar{x})^2$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "808b45a4-5c7f-4ee6-98d0-d6b8d3e226a6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6856935123042507"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0.6856935123042506"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0.6811222222222223"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para una variable\n",
    "#\n",
    "from statistics import variance\n",
    "\n",
    "display(\n",
    "    iris.sepal_length.var(),\n",
    "    variance(iris.sepal_length),\n",
    "    np.var(iris.sepal_length),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fd8dcb83-d707-4d97-ab9d-0db28201c0dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal_length    0.685694\n",
       "sepal_width     0.189979\n",
       "petal_length    3.116278\n",
       "petal_width     0.581006\n",
       "dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para las columnas del dataframe\n",
    "#\n",
    "iris.var()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "dc9584f2-f98c-475a-bd17-f855315a996a",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>0.124249</td>\n",
       "      <td>0.143690</td>\n",
       "      <td>0.030159</td>\n",
       "      <td>0.011106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>0.266433</td>\n",
       "      <td>0.098469</td>\n",
       "      <td>0.220816</td>\n",
       "      <td>0.039106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>0.404343</td>\n",
       "      <td>0.104004</td>\n",
       "      <td>0.304588</td>\n",
       "      <td>0.075433</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa          0.124249     0.143690      0.030159     0.011106\n",
       "versicolor      0.266433     0.098469      0.220816     0.039106\n",
       "virginica       0.404343     0.104004      0.304588     0.075433"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo por especie\n",
    "#\n",
    "iris.groupby('species').var()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e0c2549-9126-4c82-931d-9ac84706a2c8",
   "metadata": {},
   "source": [
    "**Desviación estándar muestral**.\n",
    "\n",
    "Raíz cuadrada de la varianza muestral."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c01e1f83-8aef-468b-adf1-3b7bdf48c509",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.828066127977863"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0.8280661279778629"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0.8253012917851409"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para una variable\n",
    "#\n",
    "from statistics import stdev\n",
    "\n",
    "display(\n",
    "    iris.sepal_length.std(),\n",
    "    stdev(iris.sepal_length),\n",
    "    np.std(iris.sepal_length),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1416df48-140f-4eae-ba0d-3ed264427b02",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal_length    0.828066\n",
       "sepal_width     0.435866\n",
       "petal_length    1.765298\n",
       "petal_width     0.762238\n",
       "dtype: float64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para las columnas del dataframe\n",
    "#\n",
    "iris.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "30d04b76-5092-4714-92c5-506800e89d87",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>0.352490</td>\n",
       "      <td>0.379064</td>\n",
       "      <td>0.173664</td>\n",
       "      <td>0.105386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>0.516171</td>\n",
       "      <td>0.313798</td>\n",
       "      <td>0.469911</td>\n",
       "      <td>0.197753</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>0.635880</td>\n",
       "      <td>0.322497</td>\n",
       "      <td>0.551895</td>\n",
       "      <td>0.274650</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa          0.352490     0.379064      0.173664     0.105386\n",
       "versicolor      0.516171     0.313798      0.469911     0.197753\n",
       "virginica       0.635880     0.322497      0.551895     0.274650"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo por especie\n",
    "#\n",
    "iris.groupby('species').std()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58bfbf94-4db4-4215-8bb0-0e7daeb25f77",
   "metadata": {},
   "source": [
    "**Desviación media absoluta (MAD):**\n",
    "\n",
    "Norma L1 o distancia de Manhattan.\n",
    "\n",
    "$$\\text{MAD} = \\frac{1}{n} \\sum_{i=1}^n |x_i - \\bar{x}|$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "14b0a922-00ef-4205-84b5-e9dcab8e8ed8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6875555555555557"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "1.0378200000000002"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para una variable\n",
    "#\n",
    "from scipy.stats import median_absolute_deviation\n",
    "\n",
    "display(\n",
    "    iris.sepal_length.mad(),\n",
    "    median_absolute_deviation(iris.sepal_length)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b9e498dd-fe7a-4de9-9cb2-351ed4b890a5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal_length    0.687556\n",
       "sepal_width     0.336782\n",
       "petal_length    1.562747\n",
       "petal_width     0.658133\n",
       "dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo para las columnas del dataframe\n",
    "#\n",
    "iris.mad()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "aea3d3d4-59d7-4411-bc59-002e645430a0",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>0.27072</td>\n",
       "      <td>0.28736</td>\n",
       "      <td>0.13152</td>\n",
       "      <td>0.08256</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>0.42144</td>\n",
       "      <td>0.25480</td>\n",
       "      <td>0.37920</td>\n",
       "      <td>0.15712</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>0.50256</td>\n",
       "      <td>0.24216</td>\n",
       "      <td>0.44000</td>\n",
       "      <td>0.22808</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa           0.27072      0.28736       0.13152      0.08256\n",
       "versicolor       0.42144      0.25480       0.37920      0.15712\n",
       "virginica        0.50256      0.24216       0.44000      0.22808"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo por especie\n",
    "#\n",
    "iris.groupby('species').mad()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0eeab3aa-9b3a-4af6-8c7d-4adfec0b1d71",
   "metadata": {},
   "source": [
    "**Desviación absoluta de la mediana:** \n",
    "\n",
    "Ya que la varianza y la desviación media absoluta no son robusta a outliers, se puede realizar un estimado de la desviación usando la mediana $m$ de la muestra:\n",
    "\n",
    "$$\\text{Mediana}(|x_1 - m|,\\; |x_2 - m|,\\;...,\\;|x_n - m|)$$ \n",
    "\n",
    "\n",
    "También es posible computar la varianza muestral truncada en analogía a la media truncada."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "afb93286-5759-4341-b501-4c7065528483",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal_length    0.687556\n",
       "sepal_width     0.336782\n",
       "petal_length    1.562747\n",
       "petal_width     0.658133\n",
       "dtype: float64"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def madm(df):\n",
    "    d = df._get_numeric_data().copy()\n",
    "    m = d.median()\n",
    "    for c in d.columns:\n",
    "        d[c] = d[c] - m[c]\n",
    "    return d.mad()\n",
    "\n",
    "\n",
    "madm(iris)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "076c4bf1-54e6-4ba4-9753-201887858bce",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>0.270</td>\n",
       "      <td>0.284</td>\n",
       "      <td>0.130</td>\n",
       "      <td>0.066</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>0.420</td>\n",
       "      <td>0.250</td>\n",
       "      <td>0.376</td>\n",
       "      <td>0.154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>0.492</td>\n",
       "      <td>0.238</td>\n",
       "      <td>0.440</td>\n",
       "      <td>0.226</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa             0.270        0.284         0.130        0.066\n",
       "versicolor         0.420        0.250         0.376        0.154\n",
       "virginica          0.492        0.238         0.440        0.226"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo por especie\n",
    "#\n",
    "def madm(x):\n",
    "    m = x.median()\n",
    "    x = x - m\n",
    "    x = x.abs()\n",
    "    return x.mean()\n",
    "    \n",
    "\n",
    "iris.groupby('species').agg(madm)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fdff3e82-3f1f-471a-bb76-c3b1d2bfccb6",
   "metadata": {},
   "source": [
    "### Métricas basadas en la distribución de los datos"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e2c8e4d2-5c00-4a41-a5b7-f5eed72239cd",
   "metadata": {},
   "source": [
    "**Función de Densidad Acumulada Empírica (ECDF)**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "1a26e811-b9c2-48e0-906f-8cfd0ec50ed0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def ecdf(ax, data, param_dict=None):\n",
    "    \n",
    "    if param_dict is None:\n",
    "        param_dict = {}\n",
    "        \n",
    "    props = {\n",
    "        'marker': '.',\n",
    "        'linestyle': 'none',\n",
    "    }\n",
    "    \n",
    "    props = {**props, **param_dict}\n",
    "    \n",
    "    x = np.sort(data)\n",
    "    y = np.arange(1, len(data) + 1) / (len(data) + 1)\n",
    "    out = ax.plot(x, y, **props)\n",
    "    return out\n",
    "    \n",
    "    \n",
    "_, ax = plt.subplots(1, 1)\n",
    "ecdf(ax, iris.sepal_length[iris.species == 'virginica'])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "8020456b-db05-44a0-a45d-fdc822c19228",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 804.75x720 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(\n",
    "    kind=\"ecdf\",\n",
    "    x=\"Values\",\n",
    "    hue='species',\n",
    "    data=iris_melt,\n",
    "    col=\"Variables\",\n",
    "    col_wrap=2,\n",
    "    marker='o',\n",
    "    linestyle=None,\n",
    "    alpha=0.4,\n",
    "    markersize=7,\n",
    "    markeredgecolor=\"k\",\n",
    "    linewidth=1,\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf1347d4-2656-4459-aa23-a752ef5baa58",
   "metadata": {},
   "source": [
    "**Estadísticos de orden:** Métricas calculadas sobre los datos ordenados."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67c73d08-2592-4c99-a1a1-17d08e2bc8c2",
   "metadata": {},
   "source": [
    "* **Percentil** $p$: Valor para el cual el $p$ por ciento de los datos son menores o iguales. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba3cb4ab-94a2-474c-a16b-3c91341ed4ff",
   "metadata": {},
   "source": [
    "* **decil** $d$: Valor para el cual el $d$ por ciento de los datos son menores o iguales. $d$ es un múltiplo de 10."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17f7dd7d-7e96-477c-8c02-11dbeec1cda1",
   "metadata": {},
   "source": [
    "* **Cuartil inferior:** Valor para el cual el 25% de las observaciones son más pequeñas (percentil del 25%)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae2df12a-aa44-4d88-a247-760d697111a0",
   "metadata": {},
   "source": [
    "* **Cuartil superior:** Valor para el cual el 25% de las observaciones son más grandes (percentil del 75%)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "72c44524-aa04-48d9-9ded-a778ed77adcf",
   "metadata": {},
   "source": [
    "* **Rango intercuartil (IQR):**\n",
    "\n",
    "$$\\text{IQR} = \\text{Cuartil superior} - \\text{Cuartil inferior}$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "066ae75b-c9eb-4616-8558-22376df3417b",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0.25</th>\n",
       "      <td>5.1</td>\n",
       "      <td>2.8</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0.75</th>\n",
       "      <td>6.4</td>\n",
       "      <td>3.3</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sepal_length  sepal_width  petal_length  petal_width\n",
       "0.25           5.1          2.8           1.6          0.3\n",
       "0.75           6.4          3.3           5.1          1.8"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo de los cuartiles\n",
    "#\n",
    "iris.quantile(\n",
    "    # -------------------------------------------------------------------------\n",
    "    # the quantile(s) to compute\n",
    "    q=[0.25, 0.75],\n",
    "    # -------------------------------------------------------------------------\n",
    "    # Specifies the interpolation method to use, when the desired quantile lies\n",
    "    # between two data points i and j:\n",
    "    # {‘linear’, ‘lower’, ‘higher’, ‘midpoint’, ‘nearest’}\n",
    "    interpolation='linear',\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "4717ad6b-8d77-4765-b9ee-524883711f94",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sepal_length    5.1\n",
       "sepal_width     2.8\n",
       "petal_length    1.6\n",
       "petal_width     0.3\n",
       "Name: 0.25, dtype: float64"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "sepal_length    6.4\n",
       "sepal_width     3.3\n",
       "petal_length    5.1\n",
       "petal_width     1.8\n",
       "Name: 0.75, dtype: float64"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# Cálculo de cuartiles\n",
    "#\n",
    "display(\n",
    "    iris.quantile(0.25),\n",
    "    iris.quantile(0.75)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "c6a610e2-41bc-4baf-a2d5-364f50f065a3",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>4.800</td>\n",
       "      <td>3.200</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>5.600</td>\n",
       "      <td>2.525</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>6.225</td>\n",
       "      <td>2.800</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa             4.800        3.200           1.4          0.2\n",
       "versicolor         5.600        2.525           4.0          1.2\n",
       "virginica          6.225        2.800           5.1          1.8"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.groupby(\"species\").quantile(0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b8c937b4-3187-4f4d-b4b1-f6cf5eabff10",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>5.2</td>\n",
       "      <td>3.675</td>\n",
       "      <td>1.575</td>\n",
       "      <td>0.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>6.3</td>\n",
       "      <td>3.000</td>\n",
       "      <td>4.600</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>6.9</td>\n",
       "      <td>3.175</td>\n",
       "      <td>5.875</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa               5.2        3.675         1.575          0.3\n",
       "versicolor           6.3        3.000         4.600          1.5\n",
       "virginica            6.9        3.175         5.875          2.3"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.groupby(\"species\").quantile(0.75)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "b9bbe714-9f9a-459c-a112-07e6ae582ddd",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>setosa</th>\n",
       "      <td>0.400</td>\n",
       "      <td>0.475</td>\n",
       "      <td>0.175</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>versicolor</th>\n",
       "      <td>0.700</td>\n",
       "      <td>0.475</td>\n",
       "      <td>0.600</td>\n",
       "      <td>0.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>virginica</th>\n",
       "      <td>0.675</td>\n",
       "      <td>0.375</td>\n",
       "      <td>0.775</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            sepal_length  sepal_width  petal_length  petal_width\n",
       "species                                                         \n",
       "setosa             0.400        0.475         0.175          0.1\n",
       "versicolor         0.700        0.475         0.600          0.3\n",
       "virginica          0.675        0.375         0.775          0.5"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.groupby(\"species\").quantile(0.75) - iris.groupby(\"species\").quantile(0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "4404f6ed-8e29-456b-a97d-5c6659ab6c04",
   "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>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>150.000000</td>\n",
       "      <td>150.000000</td>\n",
       "      <td>150.000000</td>\n",
       "      <td>150.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5.843333</td>\n",
       "      <td>3.057333</td>\n",
       "      <td>3.758000</td>\n",
       "      <td>1.199333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.828066</td>\n",
       "      <td>0.435866</td>\n",
       "      <td>1.765298</td>\n",
       "      <td>0.762238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.300000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.100000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>5.100000</td>\n",
       "      <td>2.800000</td>\n",
       "      <td>1.600000</td>\n",
       "      <td>0.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5.800000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.350000</td>\n",
       "      <td>1.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.400000</td>\n",
       "      <td>3.300000</td>\n",
       "      <td>5.100000</td>\n",
       "      <td>1.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>7.900000</td>\n",
       "      <td>4.400000</td>\n",
       "      <td>6.900000</td>\n",
       "      <td>2.500000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       sepal_length  sepal_width  petal_length  petal_width\n",
       "count    150.000000   150.000000    150.000000   150.000000\n",
       "mean       5.843333     3.057333      3.758000     1.199333\n",
       "std        0.828066     0.435866      1.765298     0.762238\n",
       "min        4.300000     2.000000      1.000000     0.100000\n",
       "25%        5.100000     2.800000      1.600000     0.300000\n",
       "50%        5.800000     3.000000      4.350000     1.300000\n",
       "75%        6.400000     3.300000      5.100000     1.800000\n",
       "max        7.900000     4.400000      6.900000     2.500000"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# El método describe de pandas computa los principales estadísticos para las\n",
    "# columnas numéricas del dataframe\n",
    "#\n",
    "iris.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "02c43469-e0e3-412e-99d2-63825b036fa5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sepal_length\n",
      "            count   mean       std  min    25%  50%  75%  max\n",
      "species                                                      \n",
      "setosa       50.0  5.006  0.352490  4.3  4.800  5.0  5.2  5.8\n",
      "versicolor   50.0  5.936  0.516171  4.9  5.600  5.9  6.3  7.0\n",
      "virginica    50.0  6.588  0.635880  4.9  6.225  6.5  6.9  7.9\n",
      "\n",
      "sepal_width\n",
      "            count   mean       std  min    25%  50%    75%  max\n",
      "species                                                        \n",
      "setosa       50.0  3.428  0.379064  2.3  3.200  3.4  3.675  4.4\n",
      "versicolor   50.0  2.770  0.313798  2.0  2.525  2.8  3.000  3.4\n",
      "virginica    50.0  2.974  0.322497  2.2  2.800  3.0  3.175  3.8\n",
      "\n",
      "petal_length\n",
      "            count   mean       std  min  25%   50%    75%  max\n",
      "species                                                       \n",
      "setosa       50.0  1.462  0.173664  1.0  1.4  1.50  1.575  1.9\n",
      "versicolor   50.0  4.260  0.469911  3.0  4.0  4.35  4.600  5.1\n",
      "virginica    50.0  5.552  0.551895  4.5  5.1  5.55  5.875  6.9\n",
      "\n",
      "petal_width\n",
      "            count   mean       std  min  25%  50%  75%  max\n",
      "species                                                    \n",
      "setosa       50.0  0.246  0.105386  0.1  0.2  0.2  0.3  0.6\n",
      "versicolor   50.0  1.326  0.197753  1.0  1.2  1.3  1.5  1.8\n",
      "virginica    50.0  2.026  0.274650  1.4  1.8  2.0  2.3  2.5\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for column in iris._get_numeric_data().columns:\n",
    "    print(column)\n",
    "    print(iris.groupby(\"species\")[column].describe())\n",
    "    print(\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "1e92bfbb-25a0-4a1c-99b1-3659e1045326",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    150.000000\n",
       "mean       5.843333\n",
       "std        0.828066\n",
       "min        4.300000\n",
       "25%        5.100000\n",
       "50%        5.800000\n",
       "75%        6.400000\n",
       "max        7.900000\n",
       "Name: sepal_length, dtype: float64"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Método describe aplicado a una columna particular\n",
    "#\n",
    "iris.sepal_length.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "97ab0698-9880-4bea-8045-6075a99b9b3d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "descriptive_stats = iris.sepal_length.describe()\n",
    "\n",
    "q75 = iris.sepal_length.describe()['75%']\n",
    "q25 = iris.sepal_length.describe()['25%']\n",
    "iqr = q75 - q25\n",
    "\n",
    "upper_outliers = q75 + 1.5 * iqr\n",
    "lower_outliers = q25 - 1.5 * iqr\n",
    "\n",
    "sns.set(color_codes=True)\n",
    "\n",
    "sns.kdeplot(iris['sepal_length'], shade=True)\n",
    "plt.axvline(iris.sepal_length.mean())\n",
    "plt.axvline(iris.sepal_length.median(), color='r')\n",
    "plt.axvline(q25, color='g')\n",
    "plt.axvline(q75, color='g')\n",
    "plt.axvline(upper_outliers, color = 'b')\n",
    "plt.axvline(lower_outliers, color = 'b')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6bf1868e-5aad-43bc-bb33-7e1a2f0034c2",
   "metadata": {},
   "source": [
    "**Diagramas de caja y bigote**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "ac13a773-eaf5-4557-96f2-e54752dcad54",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#\n",
    "# La caja central representa los cuartiles del 25% y 75%.\n",
    "# La línea centra de la caja representa la mediana\n",
    "# Los bigotes están ubicados a 1.5 veces el rango interquartil.\n",
    "# Los puntos por fuera de los bigotes representan outliers.\n",
    "#\n",
    "sns.catplot(\n",
    "    x=\"species\",\n",
    "    y=\"Values\",\n",
    "    data=iris_melt,\n",
    "    col=\"Variables\",\n",
    "    kind=\"box\",\n",
    "    col_wrap=2,\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "400d2afe-2eb6-4a9a-98c6-c74419f481ec",
   "metadata": {},
   "source": [
    "**Medidas de forma**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "2b7b4cb0-2c05-484f-b12a-adf38a450f8b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.3149109566369728"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "0.3117530585022963"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from scipy.stats import skew\n",
    "\n",
    "display(\n",
    "    iris.sepal_length.skew(),\n",
    "    skew(iris.sepal_length),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "bda964a1-9f6d-4435-b2a6-a696a31d0e97",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.5520640413156395"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "-0.5735679489249765"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from scipy.stats import kurtosis\n",
    "\n",
    "display(\n",
    "    iris.sepal_length.kurt(),\n",
    "    kurtosis(iris.sepal_length),\n",
    ")"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}