{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Comparing various online solvers\nAn example showing how different online solvers perform\non the hand-written digits dataset.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn import datasets\nfrom sklearn.linear_model import (\n    LogisticRegression,\n    PassiveAggressiveClassifier,\n    Perceptron,\n    SGDClassifier,\n)\nfrom sklearn.model_selection import train_test_split\n\nheldout = [0.95, 0.90, 0.75, 0.50, 0.01]\n# Number of rounds to fit and evaluate an estimator.\nrounds = 10\nX, y = datasets.load_digits(return_X_y=True)\n\nclassifiers = [\n    (\"SGD\", SGDClassifier(max_iter=110)),\n    (\"ASGD\", SGDClassifier(max_iter=110, average=True)),\n    (\"Perceptron\", Perceptron(max_iter=110)),\n    (\n        \"Passive-Aggressive I\",\n        PassiveAggressiveClassifier(max_iter=110, loss=\"hinge\", C=1.0, tol=1e-4),\n    ),\n    (\n        \"Passive-Aggressive II\",\n        PassiveAggressiveClassifier(\n            max_iter=110, loss=\"squared_hinge\", C=1.0, tol=1e-4\n        ),\n    ),\n    (\n        \"SAG\",\n        LogisticRegression(max_iter=110, solver=\"sag\", tol=1e-1, C=1.0e4 / X.shape[0]),\n    ),\n]\n\nxx = 1.0 - np.array(heldout)\n\nfor name, clf in classifiers:\n    print(\"training %s\" % name)\n    rng = np.random.RandomState(42)\n    yy = []\n    for i in heldout:\n        yy_ = []\n        for r in range(rounds):\n            X_train, X_test, y_train, y_test = train_test_split(\n                X, y, test_size=i, random_state=rng\n            )\n            clf.fit(X_train, y_train)\n            y_pred = clf.predict(X_test)\n            yy_.append(1 - np.mean(y_pred == y_test))\n        yy.append(np.mean(yy_))\n    plt.plot(xx, yy, label=name)\n\nplt.legend(loc=\"upper right\")\nplt.xlabel(\"Proportion train\")\nplt.ylabel(\"Test Error Rate\")\nplt.show()"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.9.21"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}