{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "markdown", "source": [ "#Perform a practical on Decision Tree algorithm" ], "metadata": { "id": "ZqNhDEhh0gBI" } }, { "cell_type": "code", "source": [ "import pandas as pd\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import accuracy_score\n", "from sklearn.datasets import load_iris\n", "\n", "# Load a sample dataset (Iris dataset)\n", "iris = load_iris()\n", "X = iris.data\n", "y = iris.target\n", "\n", "# Split the dataset into training and testing sets\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Create a Decision Tree Classifier\n", "decision_tree = DecisionTreeClassifier()\n", "\n", "# Train the classifier\n", "decision_tree.fit(X_train, y_train)\n", "\n", "# Make predictions on the test set\n", "y_pred = decision_tree.predict(X_test)\n", "\n", "# Evaluate the accuracy of the classifier\n", "accuracy = accuracy_score(y_test, y_pred)\n", "print(f\"Accuracy: {accuracy}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "FvU31UVD0pa_", "outputId": "e33c7b08-1bda-4d6c-9965-a7336ffaee41" }, "execution_count": 1, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Accuracy: 1.0\n" ] } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "e04deb07", "outputId": "3e38824e-2e89-4aee-9bd2-3e1eadab15cc" }, "source": [ "from sklearn.tree import export_graphviz\n", "import graphviz\n", "\n", "# Export the decision tree to a DOT file\n", "dot_data = export_graphviz(decision_tree, out_file=None,\n", " feature_names=iris.feature_names,\n", " class_names=iris.target_names,\n", " filled=True, rounded=True,\n", " special_characters=True)\n", "\n", "# Visualize the tree using graphviz\n", "graph = graphviz.Source(dot_data)\n", "display(graph)" ], "execution_count": 2, "outputs": [ { "output_type": "display_data", "data": { "image/svg+xml": "\n\n\n\n\n\nTree\n\n\n\n0\n\npetal width (cm) ≤ 0.8\ngini = 0.667\nsamples = 120\nvalue = [40, 41, 39]\nclass = versicolor\n\n\n\n1\n\ngini = 0.0\nsamples = 40\nvalue = [40, 0, 0]\nclass = setosa\n\n\n\n0->1\n\n\nTrue\n\n\n\n2\n\npetal length (cm) ≤ 4.75\ngini = 0.5\nsamples = 80\nvalue = [0, 41, 39]\nclass = versicolor\n\n\n\n0->2\n\n\nFalse\n\n\n\n3\n\npetal width (cm) ≤ 1.65\ngini = 0.053\nsamples = 37\nvalue = [0, 36, 1]\nclass = versicolor\n\n\n\n2->3\n\n\n\n\n\n6\n\npetal width (cm) ≤ 1.75\ngini = 0.206\nsamples = 43\nvalue = [0, 5, 38]\nclass = virginica\n\n\n\n2->6\n\n\n\n\n\n4\n\ngini = 0.0\nsamples = 36\nvalue = [0, 36, 0]\nclass = versicolor\n\n\n\n3->4\n\n\n\n\n\n5\n\ngini = 0.0\nsamples = 1\nvalue = [0, 0, 1]\nclass = virginica\n\n\n\n3->5\n\n\n\n\n\n7\n\npetal length (cm) ≤ 4.95\ngini = 0.5\nsamples = 8\nvalue = [0, 4, 4]\nclass = versicolor\n\n\n\n6->7\n\n\n\n\n\n14\n\npetal length (cm) ≤ 4.85\ngini = 0.056\nsamples = 35\nvalue = [0, 1, 34]\nclass = virginica\n\n\n\n6->14\n\n\n\n\n\n8\n\ngini = 0.0\nsamples = 2\nvalue = [0, 2, 0]\nclass = versicolor\n\n\n\n7->8\n\n\n\n\n\n9\n\npetal width (cm) ≤ 1.55\ngini = 0.444\nsamples = 6\nvalue = [0, 2, 4]\nclass = virginica\n\n\n\n7->9\n\n\n\n\n\n10\n\ngini = 0.0\nsamples = 3\nvalue = [0, 0, 3]\nclass = virginica\n\n\n\n9->10\n\n\n\n\n\n11\n\npetal length (cm) ≤ 5.45\ngini = 0.444\nsamples = 3\nvalue = [0, 2, 1]\nclass = versicolor\n\n\n\n9->11\n\n\n\n\n\n12\n\ngini = 0.0\nsamples = 2\nvalue = [0, 2, 0]\nclass = versicolor\n\n\n\n11->12\n\n\n\n\n\n13\n\ngini = 0.0\nsamples = 1\nvalue = [0, 0, 1]\nclass = virginica\n\n\n\n11->13\n\n\n\n\n\n15\n\nsepal width (cm) ≤ 3.1\ngini = 0.444\nsamples = 3\nvalue = [0, 1, 2]\nclass = virginica\n\n\n\n14->15\n\n\n\n\n\n18\n\ngini = 0.0\nsamples = 32\nvalue = [0, 0, 32]\nclass = virginica\n\n\n\n14->18\n\n\n\n\n\n16\n\ngini = 0.0\nsamples = 2\nvalue = [0, 0, 2]\nclass = virginica\n\n\n\n15->16\n\n\n\n\n\n17\n\ngini = 0.0\nsamples = 1\nvalue = [0, 1, 0]\nclass = versicolor\n\n\n\n15->17\n\n\n\n\n\n", "text/plain": [ "" ] }, "metadata": {} } ] } ] }