{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "Ob58--rXzt3u" }, "outputs": [], "source": [ "import os\n", "import pandas as pd\n", "import numpy as np\n", "import sklearn\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.tree import export_text, export_graphviz\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import confusion_matrix\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns" ] }, { "cell_type": "code", "source": [ "penguins = sns.load_dataset('penguins')\n", "print (penguins.shape)\n", "penguins.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 224 }, "id": "r34mWSSdz2KY", "outputId": "4cdac981-d319-4e38-a8bd-e2ec2bdd8276" }, "execution_count": 2, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "(344, 7)\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ " species island bill_length_mm bill_depth_mm flipper_length_mm \\\n", "0 Adelie Torgersen 39.1 18.7 181.0 \n", "1 Adelie Torgersen 39.5 17.4 186.0 \n", "2 Adelie Torgersen 40.3 18.0 195.0 \n", "3 Adelie Torgersen NaN NaN NaN \n", "4 Adelie Torgersen 36.7 19.3 193.0 \n", "\n", " body_mass_g sex \n", "0 3750.0 Male \n", "1 3800.0 Female \n", "2 3250.0 Female \n", "3 NaN NaN \n", "4 3450.0 Female " ], "text/html": [ "\n", "
\n", " | species | \n", "island | \n", "bill_length_mm | \n", "bill_depth_mm | \n", "flipper_length_mm | \n", "body_mass_g | \n", "sex | \n", "
---|---|---|---|---|---|---|---|
0 | \n", "Adelie | \n", "Torgersen | \n", "39.1 | \n", "18.7 | \n", "181.0 | \n", "3750.0 | \n", "Male | \n", "
1 | \n", "Adelie | \n", "Torgersen | \n", "39.5 | \n", "17.4 | \n", "186.0 | \n", "3800.0 | \n", "Female | \n", "
2 | \n", "Adelie | \n", "Torgersen | \n", "40.3 | \n", "18.0 | \n", "195.0 | \n", "3250.0 | \n", "Female | \n", "
3 | \n", "Adelie | \n", "Torgersen | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "NaN | \n", "
4 | \n", "Adelie | \n", "Torgersen | \n", "36.7 | \n", "19.3 | \n", "193.0 | \n", "3450.0 | \n", "Female | \n", "