{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression: Classification of Handwritten Digits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from sklearn.datasets import load_digits\n",
    "\n",
    "%matplotlib inline\n",
    "digits = load_digits()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "digits.images.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "digits.data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig = plt.figure(figsize=(6, 6))  # figure size in inches\n",
    "fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)\n",
    "\n",
    "# plot the digits: each image is 8x8 pixels\n",
    "for i in range(64):\n",
    "    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])\n",
    "    ax.imshow(digits.images[i], cmap=plt.cm.binary, interpolation='nearest')\n",
    "\n",
    "    # label the image with the target value\n",
    "    ax.text(0, 7, str(digits.target[i]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# split the data into training and validation sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(digits.data,\n",
    "                                                    digits.target,\n",
    "                                                    test_size=0.25,\n",
    "                                                    random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "''' build your LR model here and please specify the value of C and\\\n",
    "try 'multinomial' classifier with 'sag' solver '''\n",
    "\n",
    "# train the model\n",
    "clf = LogisticRegression(C=1e-2, multi_class=\"ovr\", solver='liblinear')\n",
    "\n",
    "# fit on the training dataset\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "# use the model to predict the labels of the test data\n",
    "predicted = clf.predict(X_test)\n",
    "expected = y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig = plt.figure(figsize=(6, 6))  # figure size in inches\n",
    "fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)\n",
    "\n",
    "# plot the digits: each image is 8x8 pixels\n",
    "for i in range(64):\n",
    "    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])\n",
    "    ax.imshow(X_test.reshape(-1, 8, 8)[i],\n",
    "              cmap=plt.cm.binary,\n",
    "              interpolation='nearest')\n",
    "\n",
    "    # label the image with the target value\n",
    "    if predicted[i] == expected[i]:\n",
    "        ax.text(0, 7, str(predicted[i]), color='green')\n",
    "    else:\n",
    "        ax.text(0, 7, str(predicted[i]), color='red')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quantitative Measurement on the Performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "matches = (predicted == expected)\n",
    "print('accuracy:%.3f' % (matches.sum() / float(len(matches))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import metrics\n",
    "print(metrics.classification_report(expected, predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(metrics.confusion_matrix(expected, predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.imshow(digits.images[0], cmap=plt.cm.binary, interpolation='nearest')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "digits.images[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.10.2"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}