{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "83edc883",
   "metadata": {},
   "source": [
    "# 13 · Proyecto final: resolver un reto de Kaggle\n",
    "\n",
    "[Kaggle](https://www.kaggle.com) organiza competiciones de aprendizaje automático. Este proyecto final resuelve\n",
    "uno de sus retos clásicos de iniciación (*Getting Started*), **House Prices: Advanced Regression Techniques**:\n",
    "predecir el precio de venta de viviendas en Ames (Iowa) a partir de 79 variables descriptivas. El flujo de\n",
    "trabajo es el de cualquier proyecto serio: entender los datos y la métrica, fijar una referencia, construir\n",
    "variables, validar bien, comparar modelos y solo entonces predecir.\n",
    "\n",
    "**Aprenderás**\n",
    "1. De dónde vienen los datos y si puedes usarlos (licencias)\n",
    "2. La métrica de la competición y por qué se calcula sobre el logaritmo del precio\n",
    "3. Una exploración que cambia decisiones: asimetría, valores atípicos, los predictores más fuertes\n",
    "4. Referencias y después un `Pipeline` de scikit-learn con ingeniería de variables\n",
    "5. Validación cruzada, comparación de modelos y mezcla\n",
    "6. Qué impulsa las predicciones y cómo enviarías una solución a Kaggle"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e01327fd",
   "metadata": {},
   "source": [
    "## 1. Los datos y si podemos usarlos\n",
    "Los conjuntos de datos de Kaggle tienen sus propias licencias, y **los datos de las competiciones se rigen por las\n",
    "reglas de cada competición**, que normalmente solo permiten usarlos en ella y prohíben redistribuirlos. Por eso un\n",
    "curso no debería volver a publicar los archivos de una competición de Kaggle.\n",
    "\n",
    "Los datos de esta competición son un subconjunto del **conjunto Ames Housing**, que Dean De Cock recopiló\n",
    "precisamente para la docencia y publicó con el *Journal of Statistics Education* (2011). El conjunto completo\n",
    "(2.930 ventas de 2006 a 2010) está disponible abiertamente, aquí a través de [OpenML](https://www.openml.org/d/43926)\n",
    "(licencia: pública). Usamos ese, lo citamos y dejamos los archivos de la competición en Kaggle, donde puedes\n",
    "descargarlos con tu propia cuenta para enviar una solución.\n",
    "\n",
    "> De Cock, D. (2011). *Ames, Iowa: Alternative to the Boston Housing Data as an End of Semester Regression\n",
    "> Project.* Journal of Statistics Education, 19(3)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2798bfa5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:40.329691Z",
     "iopub.status.busy": "2026-10-18T10:13:40.329222Z",
     "iopub.status.idle": "2026-10-18T10:13:43.650348Z",
     "shell.execute_reply": "2026-10-18T10:13:43.648188Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2930, 81)\n"
     ]
    },
    {
     "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>Neighborhood</th>\n",
       "      <th>Gr_Liv_Area</th>\n",
       "      <th>Overall_Qual</th>\n",
       "      <th>Year_Built</th>\n",
       "      <th>Total_Bsmt_SF</th>\n",
       "      <th>Garage_Cars</th>\n",
       "      <th>Sale_Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North_Ames</td>\n",
       "      <td>1656</td>\n",
       "      <td>Above_Average</td>\n",
       "      <td>1960</td>\n",
       "      <td>1080</td>\n",
       "      <td>2</td>\n",
       "      <td>215000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>North_Ames</td>\n",
       "      <td>896</td>\n",
       "      <td>Average</td>\n",
       "      <td>1961</td>\n",
       "      <td>882</td>\n",
       "      <td>1</td>\n",
       "      <td>105000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>North_Ames</td>\n",
       "      <td>1329</td>\n",
       "      <td>Above_Average</td>\n",
       "      <td>1958</td>\n",
       "      <td>1329</td>\n",
       "      <td>1</td>\n",
       "      <td>172000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>North_Ames</td>\n",
       "      <td>2110</td>\n",
       "      <td>Good</td>\n",
       "      <td>1968</td>\n",
       "      <td>2110</td>\n",
       "      <td>2</td>\n",
       "      <td>244000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Gilbert</td>\n",
       "      <td>1629</td>\n",
       "      <td>Average</td>\n",
       "      <td>1997</td>\n",
       "      <td>928</td>\n",
       "      <td>2</td>\n",
       "      <td>189900</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Neighborhood  Gr_Liv_Area   Overall_Qual  Year_Built  Total_Bsmt_SF  \\\n",
       "0   North_Ames         1656  Above_Average        1960           1080   \n",
       "1   North_Ames          896        Average        1961            882   \n",
       "2   North_Ames         1329  Above_Average        1958           1329   \n",
       "3   North_Ames         2110           Good        1968           2110   \n",
       "4      Gilbert         1629        Average        1997            928   \n",
       "\n",
       "   Garage_Cars  Sale_Price  \n",
       "0            2      215000  \n",
       "1            1      105000  \n",
       "2            1      172000  \n",
       "3            2      244000  \n",
       "4            2      189900  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np, pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.datasets import fetch_openml\n",
    "\n",
    "ames = fetch_openml(data_id=43926, as_frame=True, parser=\"auto\").frame   # se descarga una vez y queda en caché\n",
    "print(ames.shape)\n",
    "ames[[\"Neighborhood\", \"Gr_Liv_Area\", \"Overall_Qual\", \"Year_Built\", \"Total_Bsmt_SF\", \"Garage_Cars\", \"Sale_Price\"]].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33b53265",
   "metadata": {},
   "source": [
    "## 2. La métrica\n",
    "La competición puntúa la **raíz del error cuadrático medio entre los logaritmos** de los precios previstos y reales.\n",
    "En escala logarítmica, un error del 10% cuesta lo mismo en una casa barata que en una cara, que es como piensa un\n",
    "comprador en una mala estimación. Así que modelamos directamente `log(precio)`.\n",
    "\n",
    "Reservamos el 25% de las ventas como una \"clasificación\" privada que solo se toca una vez, al final."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d2339d54",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:43.655312Z",
     "iopub.status.busy": "2026-10-18T10:13:43.654741Z",
     "iopub.status.idle": "2026-10-18T10:13:44.425337Z",
     "shell.execute_reply": "2026-10-18T10:13:44.423515Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "entrenamiento 2197, prueba reservada 733\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x320 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "def rmse_log(y_true_log, y_pred_log):\n",
    "    return float(np.sqrt(np.mean((np.asarray(y_true_log) - np.asarray(y_pred_log)) ** 2)))\n",
    "\n",
    "df = ames.copy()\n",
    "df[\"log_price\"] = np.log(df.pop(\"Sale_Price\"))\n",
    "train, test = train_test_split(df, test_size=0.25, random_state=42)\n",
    "print(f\"entrenamiento {len(train)}, prueba reservada {len(test)}\")\n",
    "\n",
    "fig, ax = plt.subplots(1, 2, figsize=(10, 3.2))\n",
    "np.exp(train[\"log_price\"]).plot.hist(bins=50, ax=ax[0], title=\"precio de venta ($): asimétrico a la derecha\")\n",
    "train[\"log_price\"].plot.hist(bins=50, ax=ax[1], title=\"log del precio: casi normal\", color=\"#22c55e\")\n",
    "plt.tight_layout(); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6bd1632c",
   "metadata": {},
   "source": [
    "## 3. Una exploración que cambia decisiones"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ef05f80a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:44.429543Z",
     "iopub.status.busy": "2026-10-18T10:13:44.429136Z",
     "iopub.status.idle": "2026-10-18T10:13:45.555807Z",
     "shell.execute_reply": "2026-10-18T10:13:45.554230Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "correlaciones numéricas más fuertes con el log del precio:\n",
      " Gr_Liv_Area       0.68\n",
      "Garage_Cars       0.66\n",
      "Garage_Area       0.63\n",
      "Total_Bsmt_SF     0.61\n",
      "Year_Built        0.60\n",
      "First_Flr_SF      0.59\n",
      "Full_Bath         0.57\n",
      "Year_Remod_Add    0.57\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1100x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "num = train.select_dtypes(\"number\")\n",
    "top = num.corr()[\"log_price\"].drop(\"log_price\").sort_values(key=abs, ascending=False).head(8)\n",
    "print(\"correlaciones numéricas más fuertes con el log del precio:\\n\", top.round(2).to_string())\n",
    "\n",
    "fig, ax = plt.subplots(1, 2, figsize=(11, 3.6))\n",
    "ax[0].scatter(train[\"Gr_Liv_Area\"], np.exp(train[\"log_price\"]), s=6, alpha=.5)\n",
    "big = train[\"Gr_Liv_Area\"] > 4000\n",
    "ax[0].scatter(train.loc[big, \"Gr_Liv_Area\"], np.exp(train.loc[big, \"log_price\"]), s=30, color=\"#ef4444\", label=\"> 4000 pies²\")\n",
    "ax[0].set_xlabel(\"superficie habitable sobre rasante (pies²)\"); ax[0].set_ylabel(\"precio ($)\"); ax[0].legend()\n",
    "order = train.groupby(\"Neighborhood\", observed=True)[\"log_price\"].median().sort_values().index\n",
    "ax[1].boxplot([train.loc[train[\"Neighborhood\"] == n, \"log_price\"] for n in order], showfliers=False)\n",
    "ax[1].set_xticks(range(1, len(order) + 1)); ax[1].set_xticklabels(order, rotation=90, fontsize=6)\n",
    "ax[1].set_title(\"log del precio por barrio (ordenado por la mediana)\")\n",
    "plt.tight_layout(); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cdb65956",
   "metadata": {},
   "source": [
    "Dos hallazgos dan forma al modelo:\n",
    "- **El tamaño y la calidad dominan**, y el barrio desplaza todo el nivel de precios.\n",
    "- Unas pocas **casas muy grandes se vendieron a precios bajos** (en rojo, ventas parciales de inmuebles poco\n",
    "  comunes). La propia documentación de De Cock recomienda quitar las casas de más de 4.000 pies cuadrados en los\n",
    "  modelos docentes; las quitamos solo del *entrenamiento*, nunca del conjunto de prueba."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69ffc091",
   "metadata": {},
   "source": [
    "## 4. Referencias\n",
    "Todo modelo debe superar algo sencillo. El precio mediano y una regresión de una variable sobre la superficie\n",
    "habitable:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "725f60fc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:45.560418Z",
     "iopub.status.busy": "2026-10-18T10:13:45.560022Z",
     "iopub.status.idle": "2026-10-18T10:13:45.699238Z",
     "shell.execute_reply": "2026-10-18T10:13:45.697616Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "predecir la mediana          : RMSE(log) 0.4244\n",
      "regresión lineal sobre log(área): RMSE(log) 0.2797\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "train = train[train[\"Gr_Liv_Area\"] <= 4000]\n",
    "y_train, y_test = train[\"log_price\"], test[\"log_price\"]\n",
    "\n",
    "print(f\"predecir la mediana          : RMSE(log) {rmse_log(y_test, np.full(len(test), y_train.median())):.4f}\")\n",
    "lr = LinearRegression().fit(np.log(train[[\"Gr_Liv_Area\"]]), y_train)\n",
    "print(f\"regresión lineal sobre log(área): RMSE(log) {rmse_log(y_test, lr.predict(np.log(test[['Gr_Liv_Area']]))):.4f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ca8c963c",
   "metadata": {},
   "source": [
    "## 5. Ingeniería de variables dentro de un Pipeline\n",
    "La ingeniería de variables escrita como función dentro de un `Pipeline` de scikit-learn se aplica igual a los datos\n",
    "de entrenamiento, a las particiones de validación y a las casas nuevas, lo que evita el error más común en las\n",
    "competiciones: filtrar información de los datos con los que se evalúa."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d41eb340",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:45.704082Z",
     "iopub.status.busy": "2026-10-18T10:13:45.703683Z",
     "iopub.status.idle": "2026-10-18T10:13:45.753184Z",
     "shell.execute_reply": "2026-10-18T10:13:45.751136Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "95 columnas tras la ingeniería de variables; nuevas: ['Overall_Qual_n', 'Exter_Qual_n', 'Kitchen_Qual_n', 'Bsmt_Qual_n', 'Heating_QC_n', 'Fireplace_Qu_n', 'Garage_Qual_n', 'Total_SF', 'Total_Baths', 'Age_At_Sale', 'Years_Since_Remodel', 'Qual_x_Area', 'log_Gr_Liv_Area', 'log_Total_SF', 'log_Lot_Area']\n"
     ]
    }
   ],
   "source": [
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.compose import ColumnTransformer, make_column_selector\n",
    "from sklearn.preprocessing import FunctionTransformer, OneHotEncoder, StandardScaler\n",
    "\n",
    "QUALITY = [\"Very_Poor\", \"Poor\", \"Fair\", \"Below_Average\", \"Average\", \"Above_Average\", \"Good\",\n",
    "           \"Very_Good\", \"Excellent\", \"Very_Excellent\"]\n",
    "GRADE = {\"No_Basement\": 0, \"No_Garage\": 0, \"No_Fireplace\": 0, \"No_Pool\": 0, \"Poor\": 1, \"Fair\": 2,\n",
    "         \"Typical\": 3, \"Good\": 4, \"Excellent\": 5}\n",
    "\n",
    "def engineer(X: pd.DataFrame) -> pd.DataFrame:\n",
    "    X = X.drop(columns=[\"log_price\"], errors=\"ignore\").copy()\n",
    "    X[\"Overall_Qual_n\"] = X[\"Overall_Qual\"].astype(str).map({q: i for i, q in enumerate(QUALITY, 1)})\n",
    "    for col in [\"Exter_Qual\", \"Kitchen_Qual\", \"Bsmt_Qual\", \"Heating_QC\", \"Fireplace_Qu\", \"Garage_Qual\"]:\n",
    "        X[col + \"_n\"] = X[col].astype(str).map(GRADE).fillna(0)\n",
    "    X[\"Total_SF\"] = X[\"Total_Bsmt_SF\"] + X[\"First_Flr_SF\"] + X[\"Second_Flr_SF\"]\n",
    "    X[\"Total_Baths\"] = X[\"Full_Bath\"] + 0.5 * X[\"Half_Bath\"] + X[\"Bsmt_Full_Bath\"] + 0.5 * X[\"Bsmt_Half_Bath\"]\n",
    "    X[\"Age_At_Sale\"] = X[\"Year_Sold\"] - X[\"Year_Built\"]\n",
    "    X[\"Years_Since_Remodel\"] = X[\"Year_Sold\"] - X[\"Year_Remod_Add\"]\n",
    "    X[\"Qual_x_Area\"] = X[\"Overall_Qual_n\"] * X[\"Gr_Liv_Area\"]\n",
    "    for col in [\"Gr_Liv_Area\", \"Total_SF\", \"Lot_Area\"]:\n",
    "        X[\"log_\" + col] = np.log1p(X[col])\n",
    "    return X\n",
    "\n",
    "fe = FunctionTransformer(engineer)\n",
    "X_tr_preview = engineer(train)\n",
    "print(f\"{X_tr_preview.shape[1]} columnas tras la ingeniería de variables; nuevas: \"\n",
    "      f\"{[c for c in X_tr_preview.columns if c not in ames.columns]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2abe168b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:45.757286Z",
     "iopub.status.busy": "2026-10-18T10:13:45.756917Z",
     "iopub.status.idle": "2026-10-18T10:13:45.892065Z",
     "shell.execute_reply": "2026-10-18T10:13:45.890373Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import RidgeCV\n",
    "from sklearn.ensemble import HistGradientBoostingRegressor\n",
    "\n",
    "numeric = make_column_selector(dtype_include=\"number\")\n",
    "categorical = make_column_selector(dtype_exclude=\"number\")\n",
    "\n",
    "ridge = make_pipeline(\n",
    "    fe,\n",
    "    ColumnTransformer([(\"num\", StandardScaler(), numeric),\n",
    "                       (\"cat\", OneHotEncoder(handle_unknown=\"ignore\", min_frequency=10), categorical)]),\n",
    "    RidgeCV(alphas=np.logspace(-1, 3, 30)),\n",
    ")\n",
    "\n",
    "from sklearn.preprocessing import OrdinalEncoder\n",
    "\n",
    "# Trees take categories as integer codes. The encoder is fitted on the training data only, so a category\n",
    "# always gets the same code in training, validation and test (codes taken from each DataFrame's own\n",
    "# pandas categories would not be consistent), and an unseen category becomes \"missing\".\n",
    "cat_cols = list(X_tr_preview.select_dtypes(exclude=\"number\").columns)\n",
    "gbm = make_pipeline(\n",
    "    fe,\n",
    "    ColumnTransformer([(\"cat\", OrdinalEncoder(handle_unknown=\"use_encoded_value\", unknown_value=np.nan,\n",
    "                                              encoded_missing_value=np.nan), cat_cols)],\n",
    "                      remainder=\"passthrough\", verbose_feature_names_out=False).set_output(transform=\"pandas\"),\n",
    "    HistGradientBoostingRegressor(learning_rate=0.05, max_iter=600, max_leaf_nodes=15, min_samples_leaf=10,\n",
    "                                  l2_regularization=1.0, categorical_features=cat_cols, random_state=0),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7ccd591",
   "metadata": {},
   "source": [
    "## 6. Validación cruzada y comparación\n",
    "La validación cruzada de cinco particiones sobre el conjunto de entrenamiento estima cómo puntuaría cada modelo con\n",
    "casas no vistas, sin tocar el conjunto de prueba reservado."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2039e923",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:13:45.896948Z",
     "iopub.status.busy": "2026-10-18T10:13:45.896570Z",
     "iopub.status.idle": "2026-10-18T10:14:08.450043Z",
     "shell.execute_reply": "2026-10-18T10:14:08.447772Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ridge (lineal)       CV RMSE(log) 0.1171\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gradient boosting (árboles) CV RMSE(log) 0.1188\n",
      "mejor mezcla: 0.55 x Ridge + 0.45 x boosting -> RMSE(log) en validación cruzada 0.1137\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import KFold, cross_val_predict\n",
    "\n",
    "cv = KFold(5, shuffle=True, random_state=0)\n",
    "oof = {}\n",
    "for name, model in {\"Ridge (lineal)\": ridge, \"Gradient boosting (árboles)\": gbm}.items():\n",
    "    oof[name] = cross_val_predict(model, train, y_train, cv=cv)\n",
    "    print(f\"{name:<20} CV RMSE(log) {rmse_log(y_train, oof[name]):.4f}\")\n",
    "\n",
    "weights = np.linspace(0, 1, 21)\n",
    "blend_scores = [rmse_log(y_train, w * oof[\"Ridge (lineal)\"] + (1 - w) * oof[\"Gradient boosting (árboles)\"]) for w in weights]\n",
    "w_best = float(weights[int(np.argmin(blend_scores))])\n",
    "print(f\"mejor mezcla: {w_best:.2f} x Ridge + {1 - w_best:.2f} x boosting -> RMSE(log) en validación cruzada {min(blend_scores):.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b1a2c382",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:14:08.454622Z",
     "iopub.status.busy": "2026-10-18T10:14:08.454281Z",
     "iopub.status.idle": "2026-10-18T10:14:08.717288Z",
     "shell.execute_reply": "2026-10-18T10:14:08.715727Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x320 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6, 3.2))\n",
    "plt.plot(weights, blend_scores, \"o-\"); plt.axvline(w_best, ls=\"--\", color=\"grey\")\n",
    "plt.xlabel(\"peso de Ridge\"); plt.ylabel(\"RMSE (log) en validación cruzada\"); plt.title(\"Mezclar dos modelos distintos\")\n",
    "plt.tight_layout(); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a0c552ab",
   "metadata": {},
   "source": [
    "El modelo lineal y el conjunto de árboles cometen errores de distinto tipo, así que promediarlos supera a cada uno\n",
    "por separado. Es el truco más fiable en las competiciones con datos tabulares.\n",
    "\n",
    "## 7. La evaluación final, una sola vez\n",
    "Se ajustan los dos modelos con todo el conjunto de entrenamiento y se puntúan las casas reservadas exactamente una vez."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ca028628",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:14:08.721674Z",
     "iopub.status.busy": "2026-10-18T10:14:08.721286Z",
     "iopub.status.idle": "2026-10-18T10:14:15.491910Z",
     "shell.execute_reply": "2026-10-18T10:14:15.490449Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE(log) en la prueba reservada, menor es mejor:\n",
      " Mezcla                         0.1101\n",
      "Gradient boosting (árboles)    0.1108\n",
      "Ridge (lineal)                 0.1167\n",
      "regresión sobre log(área)      0.2797\n",
      "referencia: mediana            0.4244\n",
      "\n",
      "mezcla: error absoluto mediano del 5.2% del precio; el 80% de las casas dentro de un 9.8%\n"
     ]
    }
   ],
   "source": [
    "ridge.fit(train, y_train); gbm.fit(train, y_train)\n",
    "pred = {\"Ridge (lineal)\": ridge.predict(test), \"Gradient boosting (árboles)\": gbm.predict(test)}\n",
    "pred[\"Mezcla\"] = w_best * pred[\"Ridge (lineal)\"] + (1 - w_best) * pred[\"Gradient boosting (árboles)\"]\n",
    "board = pd.Series({\"referencia: mediana\": rmse_log(y_test, np.full(len(test), y_train.median())),\n",
    "                   \"regresión sobre log(área)\": rmse_log(y_test, lr.predict(np.log(test[[\"Gr_Liv_Area\"]]))),\n",
    "                   **{k: rmse_log(y_test, v) for k, v in pred.items()}}).sort_values()\n",
    "print(\"RMSE(log) en la prueba reservada, menor es mejor:\\n\", board.round(4).to_string())\n",
    "err = np.exp(pred[\"Mezcla\"]) / np.exp(y_test) - 1\n",
    "print(f\"\\nmezcla: error absoluto mediano del {np.median(np.abs(err)):.1%} del precio; \"\n",
    "      f\"el 80% de las casas dentro de un {np.quantile(np.abs(err), .8):.1%}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5dd5e130",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:14:15.495504Z",
     "iopub.status.busy": "2026-10-18T10:14:15.495135Z",
     "iopub.status.idle": "2026-10-18T10:22:42.349004Z",
     "shell.execute_reply": "2026-10-18T10:22:42.346889Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1100x380 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(1, 2, figsize=(11, 3.8))\n",
    "ax[0].scatter(np.exp(y_test), np.exp(pred[\"Mezcla\"]), s=8, alpha=.6)\n",
    "lims = [np.exp(y_test).min(), np.exp(y_test).max()]\n",
    "ax[0].plot(lims, lims, \"--\", color=\"grey\"); ax[0].set_xlabel(\"precio real ($)\"); ax[0].set_ylabel(\"previsto ($)\")\n",
    "ax[0].set_title(\"casas reservadas\")\n",
    "\n",
    "from sklearn.inspection import permutation_importance\n",
    "X_test_only = test.drop(columns=\"log_price\")\n",
    "imp = permutation_importance(gbm, X_test_only, y_test, n_repeats=5, random_state=0, scoring=\"neg_root_mean_squared_error\")\n",
    "top = pd.Series(imp.importances_mean, index=X_test_only.columns).sort_values().tail(10)\n",
    "top.plot.barh(ax=ax[1], color=\"#4f46e5\"); ax[1].set_title(\"en qué se apoya el modelo de boosting (permutación)\")\n",
    "plt.tight_layout(); plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8488b94b",
   "metadata": {},
   "source": [
    "## 8. Enviar la solución a Kaggle\n",
    "Un envío a Kaggle es un CSV con una fila por cada casa del archivo de prueba de la competición: `Id,SalePrice`. Así\n",
    "lo producirías:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2d30c069",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-18T10:22:42.353428Z",
     "iopub.status.busy": "2026-10-18T10:22:42.352972Z",
     "iopub.status.idle": "2026-10-18T10:22:42.365775Z",
     "shell.execute_reply": "2026-10-18T10:22:42.363388Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Id  SalePrice\n",
      "  1   163755.0\n",
      "  2   109983.0\n",
      "  3   188201.0\n",
      "  4   123558.0\n",
      "  5   106777.0\n"
     ]
    }
   ],
   "source": [
    "submission = pd.DataFrame({\"Id\": range(1, len(test) + 1), \"SalePrice\": np.exp(pred[\"Mezcla\"]).round(0)})\n",
    "print(submission.head().to_string(index=False))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8228e1b",
   "metadata": {},
   "source": [
    "Para competir de verdad:\n",
    "1. Crea una cuenta en Kaggle, abre la competición *House Prices: Advanced Regression Techniques* y **acepta sus\n",
    "   reglas**; después descarga `train.csv` y `test.csv` (o usa la herramienta de línea de órdenes `kaggle`).\n",
    "2. Los archivos de la competición escriben las columnas de otra forma (`GrLivArea` en lugar de `Gr_Liv_Area`), usan\n",
    "   algunos códigos de categoría distintos y marcan \"sin sótano\" y similares como valores ausentes. Renombra las\n",
    "   columnas, rellena esos valores y reutiliza el mismo pipeline.\n",
    "3. Ajusta con todos los datos de entrenamiento de Kaggle, predice `test.csv`, escribe `submission.csv` y súbelo.\n",
    "\n",
    "Puntuaciones en torno a 0,12 de RMSE(log) son típicas de un buen modelo mezclado como este; la cabeza de la\n",
    "clasificación está cerca de 0,10, a base de un trabajo cuidadoso con las variables y muchos modelos mezclados.\n",
    "\n",
    "## Qué marcó la diferencia\n",
    "| Paso | Por qué importó |\n",
    "|---|---|\n",
    "| leer la licencia | material del curso legal y reutilizable |\n",
    "| modelar el logaritmo del precio | encaja con la métrica y doma la asimetría |\n",
    "| quitar del entrenamiento los atípicos documentados | unas pocas casas enormes y baratas distorsionan un modelo lineal |\n",
    "| variables dentro de un Pipeline | el mismo procesamiento en todas partes, sin filtraciones |\n",
    "| validación cruzada antes del conjunto de prueba | una estimación honesta, y el conjunto de prueba sigue siendo un verdadero examen final |\n",
    "| mezclar familias de modelos distintas | sus errores se compensan en parte |\n",
    "\n",
    "## Ejercicios\n",
    "1. Añade una codificación por objetivo de `Neighborhood` (el logaritmo medio del precio por barrio, calculado solo dentro de las particiones de validación cruzada) y mide el cambio.\n",
    "2. Ajusta `learning_rate` y `max_leaf_nodes` del modelo de boosting con `RandomizedSearchCV`.\n",
    "3. Usa `Longitude` y `Latitude` (incluidas en este conjunto) para añadir una variable de \"distancia al centro de la ciudad\"."
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
