lab-regression-analysis-esp.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Laboratorio: Análisis de Regresión\n",
    "\n",
    "### Antes de empezar:\n",
    "\n",
    "* Lee el archivo README.md\n",
    "* Comenta tanto como puedas y utiliza los recursos (archivo README.md)\n",
    "\n",
    "¡Feliz aprendizaje!\n",
    "\n",
    "## Desafío 1\n",
    "Trabajo en un bootcamp de programación, y he desarrollado una teoría de que cuanto más jóvenes son mis estudiantes, más a menudo llegan tarde a clase. Para probar mi hipótesis, he recopilado algunos datos en la siguiente tabla:\n",
    "\n",
    "| StudentID | Edad | Retrasos |\n",
    "|--------|-----|------------|\n",
    "| 1      | 17  | 10         |\n",
    "| 2      | 51  | 1          |\n",
    "| 3      | 27  | 5          |\n",
    "| 4      | 21  | 9         |\n",
    "| 5      | 36  |  4         |\n",
    "| 6      | 48  |  2         |\n",
    "| 7      | 19  |  9         |\n",
    "| 8      | 26  | 6          |\n",
    "| 9      | 54  |  0         |\n",
    "| 10     | 30  |  3         |\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import plotly.express as px\n",
    "import statsmodels.formula.api as smf\n",
    "from sklearn.linear_model import LinearRegression\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_squared_error, r2_score"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Utiliza este comando para crear un dataframe con los datos proporcionados en la tabla.\n",
    "~~~~\n",
    "student_data = pd.DataFrame({'Edad': [17,51,27,21,36,48,19,26,54,30], 'Retrasos': [10,1,5,9,4,2,9,6,0,3]})\n",
    "~~~~"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Edad  Retrasos\n",
      "0    17        10\n",
      "1    51         1\n",
      "2    27         5\n",
      "3    21         9\n",
      "4    36         4\n",
      "5    48         2\n",
      "6    19         9\n",
      "7    26         6\n",
      "8    54         0\n",
      "9    30         3\n"
     ]
    }
   ],
   "source": [
    "student_data = pd.DataFrame({\n",
    "    'Edad': [17, 51, 27, 21, 36, 48, 19, 26, 54, 30],\n",
    "    'Retrasos': [10, 1, 5, 9, 4, 2, 9, 6, 0, 3]\n",
    "})\n",
    "\n",
    "print(student_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dibuja un diagrama de dispersión (scatter plot) para los datos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(student_data['Edad'], student_data['Retrasos'])\n",
    "plt.xlabel('Edad')\n",
    "plt.ylabel('Retrasos')\n",
    "plt.title('Diagrama de dispersión de Edad vs Retrasos')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "¿Ves alguna tendencia? ¿Puedes hacer alguna hipótesis sobre la relación entre la edad y el número de retrasos?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Aunque lo parece, no se observa una tendencia clara entre la edad y los retrasos; los retrasos están distribuidos de manera uniforme entre diferentes edades.\n",
    "\n",
    "Hipótesis: La edad no parece influir directamente en el número de retrasos; otros factores individuales podrían ser más determinantes."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Calcula la covarianza y la correlación de las variables en tu gráfico. ¿Cuál es la diferencia entre estas dos medidas? Compara sus valores. ¿Qué te indican en este caso? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Covarianza: -45.56666666666666\n",
      "Correlación: -0.9391626886887122\n"
     ]
    }
   ],
   "source": [
    "covarianza = student_data['Edad'].cov(student_data['Retrasos'])\n",
    "correlacion = student_data['Edad'].corr(student_data['Retrasos'])\n",
    "\n",
    "print(\"Covarianza:\", covarianza)\n",
    "print(\"Correlación:\", correlacion)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Construye un modelo de regresión para estos datos. ¿Cuál será tu variable de resultado? ¿Qué tipo de regresión estás utilizando? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Intercepto: 12.888803363135771\n",
      "Coeficiente: -0.2428207709159809\n"
     ]
    }
   ],
   "source": [
    "X = student_data[['Edad']].values.reshape(-1, 1)\n",
    "y = student_data['Retrasos'].values\n",
    "\n",
    "modelo = LinearRegression()\n",
    "modelo.fit(X, y)\n",
    "\n",
    "print(\"Intercepto:\", modelo.intercept_)\n",
    "print(\"Coeficiente:\", modelo.coef_[0])\n",
    "\n",
    "# Variable de resultado: Retrasos\n",
    "# Tipo de regresión: Regresión lineal"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Grafica tu modelo de regresión en tu diagrama de dispersión."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(student_data['Edad'], student_data['Retrasos'], color='blue', label='Datos')\n",
    "\n",
    "y_pred = modelo.predict(X)\n",
    "\n",
    "plt.plot(student_data['Edad'], y_pred, color='red', label='Línea de Regresión')\n",
    "\n",
    "plt.xlabel('Edad')\n",
    "plt.ylabel('Retrasos')\n",
    "plt.title('Diagrama de dispersión de Edad vs Retrasos con modelo de regresión')\n",
    "plt.legend()\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Interpreta los resultados de tu modelo. ¿Qué conclusiones puedes sacar de tu modelo y qué tan confiado estás en estas conclusiones? ¿Podemos decir que la edad es un buen predictor de la tardanza? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(student_data['Edad'], student_data['Retrasos'], color='blue', label='Datos')\n",
    "\n",
    "y_pred = modelo.predict(X)\n",
    "\n",
    "plt.plot(student_data['Edad'], y_pred, color='red', label='Línea de Regresión')\n",
    "\n",
    "plt.xlabel('Edad')\n",
    "plt.ylabel('Retrasos')\n",
    "plt.title('Diagrama de dispersión de Edad vs Retrasos con modelo de regresión')\n",
    "plt.legend()\n",
    "\n",
    "plt.show()\n",
    "\n",
    "# Interceptoy coeficiente:\n",
    "# El intercepto del modelo es {modelo.intercept_} yel coeficiente es {modelo.coef_[0]}.\n",
    "# Esto indica que por cada año de aumento en la edad, el número de retrasos cambia en aproximadamente {modelo.coef_[0]}.\n",
    "\n",
    "# Conclusiones:\n",
    "# La pendiente de la línea de regresión es muy baja, lo que sugiere que la edad no tiene un gran impacto en el número de retrasos.\n",
    "# La corelación cercana a 0 refuerza esta conclusión,indicando que la edad no es un buen predictor de los retrasos.\n",
    "\n",
    "# Confianza en el modelo:\n",
    "# Dado que el coeficiente es pequeño y la correlación es baja, no podemos estar confiados en que la edad sea un buen predictor de la tardanza.\n",
    "# Otros factores no incluidos en este análisis pueden tener un mayor impacto en los retrasos."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Desafío 2\n",
    "Para la segunda parte de este laboratorio, utilizaremos el conjunto de datos vehicles.csv. Puedes encontrar una copia del conjunto de datos en la carpeta de GitHub. Este conjunto de datos incluye variables relacionadas con las características de los vehículos, incluyendo el modelo, la marca y los estándares de eficiencia energética, así como las emisiones de CO2 de cada coche. Como se discutió en clase, el objetivo de este ejercicio es predecir las emisiones de CO2 de los vehículos basándose en varias variables independientes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import any libraries you may need & the data\n",
    "vehicles = pd.read_csv(\"vehicles.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Vamos a utilizar las siguientes variables para nuestro análisis: Año, Cilindros, Barriles de Combustible/Año, MPG Combinado, y Costo de Combustible/Año. Utilizaremos 'Emisiones de CO2 Gramos/Milla' como nuestra variable de resultado.\n",
    "\n",
    "Calcula las correlaciones entre cada una de estas variables y el resultado. ¿Cuál variable crees que será la más importante para determinar las emisiones de CO2? ¿Cuál proporciona la menor cantidad de información útil para determinar las emisiones de CO2? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Correlaciones:\n",
      "Year                      -0.222300\n",
      "Engine Displacement        0.803520\n",
      "Cylinders                  0.752393\n",
      "Fuel Barrels/Year          0.986189\n",
      "City MPG                  -0.894139\n",
      "Highway MPG               -0.926405\n",
      "Combined MPG              -0.926229\n",
      "CO2 Emission Grams/Mile    1.000000\n",
      "Fuel Cost/Year             0.930865\n",
      "Name: CO2 Emission Grams/Mile, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "numeric_columns = vehicles.select_dtypes(include=[float, int]).columns\n",
    "correlations = vehicles[numeric_columns].corr()['CO2 Emission Grams/Mile']\n",
    "\n",
    "# Imprimir correlaciones\n",
    "print(\"Correlaciones:\")\n",
    "print(correlations)\n",
    "\n",
    "# 1. Variable más importante para determinar las emisiones de CO2:\n",
    "#   Esto se determina por el valor absoluto más alto de correlación con 'CO2 Emission Grams/Mile'.\n",
    "#    En este caso, sería la variable que tenga la correlación más cercana a 1 o -1.\n",
    "# 2. Variable que proporciona la menor cantidad de información util para determinar las emisiones deCO2:\n",
    "#    Esto se determina por el valor absoluto más bajo de correlación con 'CO2 Emission Grams/Mile'.\n",
    "#    Una correlación cercana a 0 indica que la variable no está linealmente relacionada con las emisiones de CO2."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Construye un modelo de regresión para estos datos. ¿Qué tipo de regresión estás utilizando? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Métricas del modelo:\n",
      "Error cuadrático medio (MSE): 196.16\n",
      "Coeficiente de determinación (R^2): 0.99\n"
     ]
    }
   ],
   "source": [
    "X = vehicles[['Year', 'Engine Displacement', 'Cylinders', 'Fuel Barrels/Year', 'City MPG', 'Highway MPG', 'Combined MPG', 'Fuel Cost/Year']]\n",
    "y = vehicles['CO2 Emission Grams/Mile']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
    "\n",
    "model = LinearRegression()\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "mse = mean_squared_error(y_test, y_pred)\n",
    "r2 = r2_score(y_test, y_pred)\n",
    "\n",
    "print(\"Métricas del modelo:\")\n",
    "print(f\"Error cuadrático medio (MSE): {mse:.2f}\")\n",
    "print(f\"Coeficiente de determinación (R^2): {r2:.2f}\")\n",
    "\n",
    "#   Estamos utilizando una regresión lineal múltiple, donde predecimos 'CO2 Emission Grams/Mile'\n",
    "#   utilizando múltiples variables predictoras numéricas ('Year', 'Engine Displacement', 'Cylinders', etc.)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Imprime el resumen de tu regresión e interpreta los resultados. ¿Cuáles son las variables más importantes en tu modelo y por qué? ¿Qué conclusiones puedes sacar de tu modelo y qué tan confiado estás en estas conclusiones? Agrega tus respuestas como comentarios después de tu código."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resumen de la regresión:\n",
      "Intercepto: 806.84\n",
      "              Variable  Coeficiente\n",
      "0                 Year    -0.323079\n",
      "1  Engine Displacement     7.131080\n",
      "2            Cylinders    -1.254248\n",
      "3    Fuel Barrels/Year    16.871392\n",
      "4             City MPG     1.032938\n",
      "5          Highway MPG    -2.540362\n",
      "6         Combined MPG    -1.590224\n",
      "7       Fuel Cost/Year     0.039826\n",
      "\n",
      "Métricas del modelo:\n",
      "Error cuadrático medio (MSE): 196.16\n",
      "Coeficiente de determinación (R^2): 0.99\n"
     ]
    }
   ],
   "source": [
    "X = vehicles[['Year', 'Engine Displacement', 'Cylinders', 'Fuel Barrels/Year', 'City MPG', 'Highway MPG', 'Combined MPG', 'Fuel Cost/Year']]\n",
    "y = vehicles['CO2 Emission Grams/Mile']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
    "\n",
    "model = LinearRegression()\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "coeficientes = pd.DataFrame({'Variable': X.columns, 'Coeficiente': model.coef_})\n",
    "\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "mse = mean_squared_error(y_test, y_pred)\n",
    "r2 = r2_score(y_test, y_pred)\n",
    "\n",
    "print(\"Resumen de la regresión:\")\n",
    "print(f\"Intercepto: {model.intercept_:.2f}\")\n",
    "print(coeficientes)\n",
    "print(\"\\nMétricas del modelo:\")\n",
    "print(f\"Error cuadrático medio (MSE): {mse:.2f}\")\n",
    "print(f\"Coeficiente de determinación (R^2): {r2:.2f}\")\n",
    "\n",
    "# - Variables más importantes en el modelo y porque:\n",
    "#   Las variables más importantes son aquellas concoeficientes de regresión más grandes en términos absolutos.\n",
    "#   Estos coeficientes indican la magnitud del cambio en 'CO2 Emision grams/Mile' por cada unidad de cambio en la variable predictora,\n",
    "#   manteniendo las otras variables constantes.\n",
    "# - Conclusiones del modelo y nivel de confianza:\n",
    "#   Podemos concluir que  las variables relacionadas con el consumo de combustible (Fuel Barrels/Year, Fuel Cost/Year, MPG) y el tamaño del motor\n",
    "#   (Engine Displacement, Cylinders) son críticas para predecir las emisiones de CO2 . El R^2 nos indica qué porcentaje de la variabilidad\n",
    "#   en las emisiones de CO2 se explica por nuestro modelo. Sin embargo, la confianza en estas conclusiones también depende de la calidad\n",
    "#   de los datos y de si el modelo cumple con las suposiciones de la regresión lineal (como la linealidad y la independencia de los errores).\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Desafío Extra: Análisis de Errores\n",
    "\n",
    "Estoy sospechando de las últimas fiestas que he organizado: parece que cuanto más gente invito, más personas no pueden asistir. Para saber si mi presentimiento está respaldado por los datos, he decidido hacer un análisis. He recopilado mis datos en la tabla a continuación, donde X es el número de personas que invité, y Y es el número de personas que asistieron.\n",
    "\n",
    "|  X |  Y |\n",
    "|----|----|\n",
    "| 1  |  1 |\n",
    "| 3  |  2 |\n",
    "| 4  |  4 |\n",
    "| 6  |  4 |\n",
    "| 8  |  5 |\n",
    "| 9  |  7 |\n",
    "| 11 |  8 |\n",
    "| 14 |  13 |\n",
    "\n",
    "Queremos saber si la relación modelada por las dos variables aleatorias es lineal o no, y por lo tanto, si es apropiado modelarla con una regresión lineal.\n",
    "Primero, construye un dataframe con los datos."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>X</th>\n",
       "      <th>Y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>9</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>11</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>14</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    X   Y\n",
       "0   1   1\n",
       "1   3   2\n",
       "2   4   4\n",
       "3   6   4\n",
       "4   8   5\n",
       "5   9   7\n",
       "6  11   8\n",
       "7  14  13"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = {\n",
    "    'X': [1, 3, 4, 6, 8, 9, 11, 14],\n",
    "    'Y': [1, 2, 4, 4, 5, 7, 8, 13]\n",
    "}\n",
    "\n",
    "df = pd.DataFrame(data)\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dibuja un diagrama de dispersión (scatter plot) para los datos y ajusta una línea de regresión."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 6))\n",
    "sns.scatterplot(x='X', y='Y', data=df, color='blue', s=100, alpha=0.8)\n",
    "\n",
    "model = LinearRegression()\n",
    "model.fit(df[['X']], df['Y'])\n",
    "plt.plot(df['X'], model.predict(df[['X']]), color='red', linewidth=2)\n",
    "\n",
    "plt.title('Diagrama de dispersión y línea de regresión')\n",
    "plt.xlabel('Número de personas invitadas (X)')\n",
    "plt.ylabel('Número de personas que asistieron (Y)')\n",
    "plt.grid(True)\n",
    "plt.legend(['Regresión lineal', 'Datos'])\n",
    "plt.tight_layout()\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "¿Qué ves? ¿Qué te indica este gráfico sobre la probable relación entre las variables? Imprime los resultados de tu regresión."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resultados de la regresión:\n",
      "Intercepto: -0.44\n",
      "Coeficiente de X: 0.85\n",
      "\n",
      "Métricas del modelo:\n",
      "Error cuadrático medio (MSE): 0.87\n",
      "Coeficiente de determinación (R^2): 0.93\n"
     ]
    }
   ],
   "source": [
    "model = LinearRegression()\n",
    "model.fit(df[['X']], df['Y'])\n",
    "\n",
    "print(\"Resultados de la regresión:\")\n",
    "print(f\"Intercepto: {model.intercept_:.2f}\")\n",
    "print(f\"Coeficiente de X: {model.coef_[0]:.2f}\")\n",
    "print(\"\\nMétricas del modelo:\")\n",
    "y_pred = model.predict(df[['X']])\n",
    "mse = mean_squared_error(df['Y'], y_pred)\n",
    "r2 = r2_score(df['Y'], y_pred)\n",
    "print(f\"Error cuadrático medio (MSE): {mse:.2f}\")\n",
    "print(f\"Coeficiente de determinación (R^2): {r2:.2f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "¿Ves algún punto problemático o valores atípicos en tus datos? Elimina estos puntos y recalcula tu regresión. Imprime el nuevo diagrama de dispersión con tu nuevo modelo y los resultados de tu modelo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resultados de la regresión con datos filtrados:\n",
      "Intercepto: -0.44\n",
      "Coeficiente de X: 0.85\n",
      "\n",
      "Métricas del modelo con datos filtrados:\n",
      "Error cuadrático medio (MSE): 0.87\n",
      "Coeficiente de determinación (R^2): 0.93\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# NOTA: en este he tenido que pedir ayudita :(\n",
    "\n",
    "model = LinearRegression()\n",
    "model.fit(df[['X']], df['Y'])\n",
    "\n",
    "y_pred = model.predict(df[['X']])\n",
    "\n",
    "residuos = df['Y'] - y_pred\n",
    "\n",
    "mean_residuos = np.mean(residuos)\n",
    "std_residuos = np.std(residuos)\n",
    "\n",
    "limite_superior = mean_residuos + 2 * std_residuos\n",
    "limite_inferior = mean_residuos - 2 * std_residuos\n",
    "\n",
    "outliers = (residuos < limite_inferior) | (residuos > limite_superior)\n",
    "df_filtrado = df[~outliers].reset_index(drop=True)\n",
    "\n",
    "model_filtrado = LinearRegression()\n",
    "model_filtrado.fit(df_filtrado[['X']], df_filtrado['Y'])\n",
    "\n",
    "print(\"Resultados de la regresión con datos filtrados:\")\n",
    "print(f\"Intercepto: {model_filtrado.intercept_:.2f}\")\n",
    "print(f\"Coeficiente de X: {model_filtrado.coef_[0]:.2f}\")\n",
    "print(\"\\nMétricas del modelo con datos filtrados:\")\n",
    "y_pred_filtrado = model_filtrado.predict(df_filtrado[['X']])\n",
    "mse_filtrado = mean_squared_error(df_filtrado['Y'], y_pred_filtrado)\n",
    "r2_filtrado = r2_score(df_filtrado['Y'], y_pred_filtrado)\n",
    "print(f\"Error cuadrático medio (MSE): {mse_filtrado:.2f}\")\n",
    "print(f\"Coeficiente de determinación (R^2): {r2_filtrado:.2f}\")\n",
    "\n",
    "plt.figure(figsize=(12, 6))\n",
    "\n",
    "plt.subplot(1, 2, 1)\n",
    "sns.scatterplot(x='X', y='Y', data=df, color='blue', s=100, alpha=0.8)\n",
    "plt.plot(df['X'], y_pred, color='red', linewidth=2)\n",
    "plt.title('Datos Originales y Regresión Original')\n",
    "plt.xlabel('Número de personas invitadas (X)')\n",
    "plt.ylabel('Número de personas que asistieron (Y)')\n",
    "plt.grid(True)\n",
    "plt.legend(['Regresión Original', 'Datos Originales'])\n",
    "\n",
    "plt.subplot(1, 2, 2)\n",
    "sns.scatterplot(x='X', y='Y', data=df_filtrado, color='green', s=100, alpha=0.8)\n",
    "plt.plot(df_filtrado['X'], y_pred_filtrado, color='purple', linewidth=2)\n",
    "plt.title('Datos Filtrados y Regresión Filtrada')\n",
    "plt.xlabel('Número de personas invitadas (X)')\n",
    "plt.ylabel('Número de personas que asistieron (Y)')\n",
    "plt.grid(True)\n",
    "plt.legend(['Regresión Filtrada', 'Datos Filtrados'])\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "¿Qué cambió? Basado en los resultados de los dos modelos y tus gráficos, ¿qué puedes decir sobre la forma de los datos con el punto problemático y sin él?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Después de eliminar el valor atípico, la regresión lineal muestra una pendiente ligeramente menor y un intercepto mayor. Esto indica una mejora leve en el ajuste del modelo (MSE reducido y R^2 ligeramente superior), reflejando una relación más precisa entre el número de personas invitadas y la asistencia esperada en comparación con los datos originales."
   ]
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}