{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "SFKpZAp1Bsrm" }, "source": [ "Pontificia Universidad Católica de Chile
\n", "Departamento de Ciencia de la Computación
\n", "IIC2613 - Inteligencia Artificial
\n", "
\n", "\n", "---\n", "
\n", "

Ayudantía 7: Intro a ML, uso de pandas, numpy, y sklearn

\n", "

\n", " Ayudantes: Bernardita Alliende y Celeste Vargas
\n", " Primer Semestre 2025
\n", " 12 de mayo de 2025\n", "

\n", "
\n", "
\n", "\n", "
\n", "\n", "---\n" ] }, { "cell_type": "markdown", "metadata": { "id": "ihvQd6N5q0Pe" }, "source": [ "### 1 Importar las librerías necesarias" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "PT8GG144tz8P" }, "outputs": [], "source": [ "# Liberías para manejar los datos\n", "import pandas as pd\n", "import seaborn as sns # librería para obtener el conjunto de datos que usaremos\n", "from sklearn.model_selection import train_test_split\n", "\n", "# Libería para graficar\n", "import matplotlib.pyplot as plt\n", "\n", "# Libería para calcular las métricas de los modelos\n", "from sklearn.metrics import classification_report, accuracy_score\n", "\n", "# Libería para obtener la matriz de confusión\n", "from sklearn.metrics import confusion_matrix\n", "\n", "# Librería para usar KNN\n", "from sklearn.neighbors import KNeighborsClassifier" ] }, { "cell_type": "markdown", "metadata": { "id": "gMFnBO8uuVU7" }, "source": [ "### 2 Cargar el conjunto de datos" ] }, { "cell_type": "markdown", "metadata": { "id": "KO8eFBW-6j4J" }, "source": [ "Vamos a usar un dataset que viene precargado en la librería sns. Este es un buen conjunto de datos para hacer pruebas rápidas." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "BdHIx_bOt5xP", "outputId": "d91b82c7-255a-41ae-c01e-ccd73438691f" }, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " survived pclass sex age sibsp parch fare embarked class \\\n", "0 0 3 male 22.0 1 0 7.2500 S Third \n", "1 1 1 female 38.0 1 0 71.2833 C First \n", "2 1 3 female 26.0 0 0 7.9250 S Third \n", "3 1 1 female 35.0 1 0 53.1000 S First \n", "4 0 3 male 35.0 0 0 8.0500 S Third \n", "\n", " who adult_male deck embark_town alive alone \n", "0 man True NaN Southampton no False \n", "1 woman False C Cherbourg yes False \n", "2 woman False NaN Southampton yes True \n", "3 woman False C Southampton yes False \n", "4 man True NaN Southampton no True " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
survivedpclasssexagesibspparchfareembarkedclasswhoadult_maledeckembark_townalivealone
003male22.0107.2500SThirdmanTrueNaNSouthamptonnoFalse
111female38.01071.2833CFirstwomanFalseCCherbourgyesFalse
213female26.0007.9250SThirdwomanFalseNaNSouthamptonyesTrue
311female35.01053.1000SFirstwomanFalseCSouthamptonyesFalse
403male35.0008.0500SThirdmanTrueNaNSouthamptonnoTrue
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "titanic", "summary": "{\n \"name\": \"titanic\",\n \"rows\": 891,\n \"fields\": [\n {\n \"column\": \"survived\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"pclass\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 1,\n \"max\": 3,\n \"num_unique_values\": 3,\n \"samples\": [\n 3,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sex\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"female\",\n \"male\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.526497332334044,\n \"min\": 0.42,\n \"max\": 80.0,\n \"num_unique_values\": 88,\n \"samples\": [\n 0.75,\n 22.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sibsp\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 0,\n \"max\": 8,\n \"num_unique_values\": 7,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"parch\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 6,\n \"num_unique_values\": 7,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"fare\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 49.693428597180905,\n \"min\": 0.0,\n \"max\": 512.3292,\n \"num_unique_values\": 248,\n \"samples\": [\n 11.2417,\n 51.8625\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"embarked\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"S\",\n \"C\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"class\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Third\",\n \"First\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"who\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"man\",\n \"woman\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"adult_male\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"deck\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"C\",\n \"E\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"embark_town\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Southampton\",\n \"Cherbourg\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"alive\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"yes\",\n \"no\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"alone\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 2 } ], "source": [ "titanic = sns.load_dataset('titanic') # la función load_dataset viene en la librería sns\n", "titanic.head()" ] }, { "cell_type": "markdown", "metadata": { "id": "pP8Afh6cudF8" }, "source": [ "### 3 Preprocesamiento de los datos" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "QXeUugKFuNyL", "outputId": "1ce139f2-832d-445a-9ff2-ca21db79d143", "colab": { "base_uri": "https://localhost:8080/" } }, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ ":2: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " titanic['age'].fillna(titanic['age'].median(), inplace=True) # .fillna es una función de pandas\n", ":3: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " titanic['embarked'].fillna(titanic['embarked'].mode()[0], inplace=True)\n" ] } ], "source": [ "# Imputar valores faltantes\n", "titanic['age'].fillna(titanic['age'].median(), inplace=True) # .fillna es una función de pandas\n", "titanic['embarked'].fillna(titanic['embarked'].mode()[0], inplace=True)\n", "\n", "# Codificar variables categóricas\n", "titanic['sex'] = titanic['sex'].map({'male': 0, 'female': 1}) # re escribimos la columna sex\n", "titanic['embarked'] = titanic['embarked'].map({'C': 0, 'Q': 1, 'S': 2}) # las letras son la inicial de la ciudad de embarque\n", "\n", "# Seleccionar características y la variable objetivo\n", "features = ['pclass', 'sex', 'age', 'sibsp', 'parch', 'fare', 'embarked']\n", "target = 'survived' # queremos predecir si sobrevivirán\n", "\n", "X = titanic[features]\n", "y = titanic[target]\n" ] }, { "cell_type": "markdown", "metadata": { "id": "1YMU6lXaxr62" }, "source": [ "Por último, dividimos los datos en los sets de Train y Tets. En este ejemplo no usaremos el set de validación." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "b7aeiWfJxrXM" }, "outputs": [], "source": [ "# Dividir el conjunto de datos en entrenamiento y prueba\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # train_test_split es una función de sklearn para dividir el set de datos en el conjunto de entranamiento y el conjunto de prueba" ] }, { "cell_type": "markdown", "metadata": { "id": "0SXTV42jvQCK" }, "source": [ "### 4 Clasificación con KNN" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 638 }, "id": "ONJAYtQJvUK5", "outputId": "5c6e8e6f-a955-4486-b543-8dc382f1ecdf" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy: 0.6983240223463687\n", "Classification Report:\n", " precision recall f1-score support\n", "\n", " 0 0.73 0.78 0.75 105\n", " 1 0.65 0.58 0.61 74\n", "\n", " accuracy 0.70 179\n", " macro avg 0.69 0.68 0.68 179\n", "weighted avg 0.70 0.70 0.70 179\n", "\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 5 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ], "source": [ "# Primero instanciamos al clasificador\n", "model = KNeighborsClassifier(n_neighbors=1)\n", "\n", "# \"Entrenamos\" al clasificador\n", "model.fit(X_train, y_train)\n", "\n", "# Obtenemos las predicciones\n", "y_pred = model.predict(X_test)\n", "\n", "\n", "# Evaluación, las funciones accuracy_score y classification_report son parte de sklearn\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n", "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n", "\n", "# Mostramos la matriz de confusión\n", "cf_matrix = confusion_matrix(y_test, y_pred)\n", "sns.heatmap(cf_matrix, annot=True)\n", "# recordando que la variable a predecir es sobrevive o no y toma los valores 1 ó 0 respectivamente." ] }, { "cell_type": "markdown", "metadata": { "id": "uQ0kWsHnCQKu" }, "source": [ "Las filas corresponden a las clases reales, y las columnas corresponden a las clases predichas. ¿Qué representaría el cuadrante (0,1)? ¿Y el (0,0)?" ] }, { "cell_type": "markdown", "source": [ "| | **Predicción: No Sobrevive (0)** | **Predicción: Sobrevive (1)** |\n", "|------------------------|----------------------------------|-------------------------------|\n", "| **Real: No Sobrevive (0)** | TN (True Negative) | FP (False Positive) |\n", "| **Real: Sobrevive (1)** | FN (False Negative) | TP (True Positive) |" ], "metadata": { "id": "3if9Js9HxBaz" } }, { "cell_type": "markdown", "metadata": { "id": "JoNdzbohyV6Z" }, "source": [ "Probemos con otros número de vecinos" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "uLiUsQhFyYjI", "outputId": "7ebdab6a-99f7-4dfe-9063-26d3fbd887ea" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy usando 1 vecinos: 0.6983240223463687\n", "Accuracy usando 3 vecinos: 0.7150837988826816\n", "Accuracy usando 4 vecinos: 0.7262569832402235\n", "Accuracy usando 5 vecinos: 0.7039106145251397\n", "Accuracy usando 7 vecinos: 0.7262569832402235\n", "Accuracy usando 9 vecinos: 0.7206703910614525\n", "Accuracy usando 11 vecinos: 0.7374301675977654\n", "Accuracy usando 15 vecinos: 0.7262569832402235\n" ] } ], "source": [ "number_of_n_neighbors = [1, 3, 4, 5, 7, 9, 11, 15]\n", "\n", "for n_neighbors in number_of_n_neighbors:\n", " # Primero instanciamos al clasificador\n", " neigh = KNeighborsClassifier(n_neighbors=n_neighbors)\n", "\n", " # \"Entrenamos\" al clasificador\n", " neigh.fit(X_train, y_train)\n", "\n", " # Obtenemos las predicciones\n", " y_pred = neigh.predict(X_test)\n", "\n", " # Evaluación, las funciones accuracy_score y classification_report son parte de sklearn\n", " print(f\"Accuracy usando {n_neighbors} vecinos:\", accuracy_score(y_test, y_pred))\n", " # recordando que la variable a predecir es sobrevive o no y toma los valores 1 ó 0 respectivamente." ] }, { "cell_type": "code", "source": [], "metadata": { "id": "-SEO-pNHxdbK" }, "execution_count": null, "outputs": [] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 0 }