{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: scikit-learn in /Users/owen/.pyenv/versions/3.10.11/lib/python3.10/site-packages (1.3.0)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /Users/owen/.pyenv/versions/3.10.11/lib/python3.10/site-packages (from scikit-learn) (3.1.0)\n", "Requirement already satisfied: joblib>=1.1.1 in /Users/owen/.pyenv/versions/3.10.11/lib/python3.10/site-packages (from scikit-learn) (1.3.1)\n", "Requirement already satisfied: scipy>=1.5.0 in /Users/owen/.pyenv/versions/3.10.11/lib/python3.10/site-packages (from scikit-learn) (1.11.1)\n", "Requirement already satisfied: numpy>=1.17.3 in /Users/owen/.pyenv/versions/3.10.11/lib/python3.10/site-packages (from scikit-learn) (1.23.5)\n", "\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.1\u001b[0m\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49m/Users/owen/.pyenv/versions/3.10.11/bin/python3.10 -m pip install --upgrade pip\u001b[0m\n", "Note: you may need to restart the kernel to use updated packages.\n", "sklearn.__version__='1.3.0'\n" ] } ], "source": [ "%pip install scikit-learn\n", "import sklearn\n", "print(f\"{sklearn.__version__=}\")" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "ljmtcrVxoxfO" }, "outputs": [], "source": [ "from sklearn.datasets import load_iris\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import accuracy_score\n", "\n", "# Load the Iris dataset\n", "iris = load_iris()\n", "X, y = iris.data, iris.target\n", "\n", "# Split the data into training and test sets\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", "\n", "# Initialize the classifier\n", "classifier = RandomForestClassifier(n_estimators=100, random_state=42)\n", "\n", "# Train the classifier\n", "classifier.fit(X_train, y_train)\n", "\n", "# Make predictions on the test set\n", "predictions = classifier.predict(X_test)\n", "\n", "# Calculate the accuracy\n", "accuracy = accuracy_score(y_test, predictions)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "id": "NL58M19xo4PP" }, "outputs": [ { "data": { "text/plain": [ "['model.joblib']" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from joblib import dump\n", "dump(classifier, 'model.joblib')" ] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.10.11" } }, "nbformat": 4, "nbformat_minor": 4 }