LAB_feature_enginiere

LAB2_WEEK17_DAY3.ipynb

@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(r\"C:\\Users\\Win10\\Downloads\\learningSet.csv\",low_memory=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Valores nulos en las columnas numéricas:\n",
+      "AGE         23665\n",
+      "NUMCHLD     83026\n",
+      "INCOME      21286\n",
+      "WEALTH1     44732\n",
+      "MBCRAFT     52854\n",
+      "            ...  \n",
+      "RAMNT_23    87553\n",
+      "RAMNT_24    77674\n",
+      "NEXTDATE     9973\n",
+      "TIMELAG      9973\n",
+      "CLUSTER2      132\n",
+      "Length: 91, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Comprobar si hay valores nulos en las columnas numéricas\n",
+    "numeric_columns = df.select_dtypes(include=['number']).columns\n",
+    "null_counts_numeric = df[numeric_columns].isnull().sum()\n",
+    "print(\"Valores nulos en las columnas numéricas:\")\n",
+    "print(null_counts_numeric[null_counts_numeric > 0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Utilice métodos apropiados para limpiar las columnas GEOCODE2, WEALTH1, ADI, DMA,y MSA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1. GEOCODE2: Asumiremos que los valores nulos pueden ser reemplazados por una categoría 'N/A'\n",
+    "df['GEOCODE2'] = df['GEOCODE2'].fillna('N/A')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 2. WEALTH1: Reemplazar valores nulos con la mediana o la moda (usaremos la mediana aquí)\n",
+    "df['WEALTH1'] = df['WEALTH1'].fillna(df['WEALTH1'].median())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3. ADI: Reemplazar valores nulos con la mediana\n",
+    "df['ADI'] = df['ADI'].fillna(df['ADI'].median())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 4. DMA: Reemplazar valores nulos con la mediana\n",
+    "df['DMA'] = df['DMA'].fillna(df['DMA'].median())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 5. MSA: Reemplazar valores nulos con la mediana\n",
+    "df['MSA'] = df['MSA'].fillna(df['MSA'].median())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Valores nulos después de la limpieza:\n",
+      "GEOCODE2    0\n",
+      "WEALTH1     0\n",
+      "ADI         0\n",
+      "DMA         0\n",
+      "MSA         0\n",
+      "dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Verificar nuevamente los valores nulos después de la limpieza\n",
+    "print(\"\\nValores nulos después de la limpieza:\")\n",
+    "print(df[['GEOCODE2', 'WEALTH1', 'ADI', 'DMA', 'MSA']].isnull().sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}