Finished working on classificaiton general stuff. I also wrote a custom implementation of linear regression using the closed-form method (formula), and the gradient descent way as well. - machinelearning - Unnamed repository; edit this file 'description' to name the repository.

commit ad1fa0644b92e7d505f8d5d559a4ec9ae96c1ef1
parent d40d44c47be6e86d8bf6b91cca6c4eeaa554495f
Author: Andrew <andrewlaack1@gmail.com>
Date:   Tue,  4 Jun 2024 22:47:02 -0500

Finished working on classificaiton general stuff. I also wrote a custom implementation of linear regression using the closed-form method (formula), and the gradient descent way as well.

Diffstat:
A gradientDescent/GradientDescentLinearRegression.ipynb  | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
A linearRegression/LinearRegressionClosedForm.ipynb  | 160 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
M mnist/MNISTClassification.ipynb  | 2573 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--

3 files changed, 2756 insertions(+), 56 deletions(-)
diff --git a/gradientDescent/GradientDescentLinearRegression.ipynb b/gradientDescent/GradientDescentLinearRegression.ipynb
@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Custom implementation of gradient descent for use with linear regression.\n",
+    "# This would be used in the case of lots of features (100,000+)\n",
+    "# or lots of samples such that they don't all fit in memory.\n",
+    "import numpy as np\n",
+    "from sklearn.preprocessing import add_dummy_feature\n",
+    "\n",
+    "# init\n",
+    "m = 100\n",
+    "X = 2*np.random.rand(m,1)\n",
+    "y = 4+3 * X + np.random.randn(m,1)\n",
+    "X_b = add_dummy_feature(X)\n",
+    "\n",
+    "\n",
+    "# set learning rate and iterations\n",
+    "lr = .1\n",
+    "itrs = 1000\n",
+    "\n",
+    "# Calculate and move\n",
+    "m = len(X_b)\n",
+    "np.random.seed(42)\n",
+    "theta = np.random.randn(2,1)\n",
+    "\n",
+    "for itr in range(itrs):\n",
+    "    gradients = 2 / m * X_b.T @ (X_b @ theta - y)\n",
+    "    theta = theta - lr * gradients"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[4.20831857],\n",
+       "       [2.79226572]])"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "theta"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "notebook",
+   "language": "python",
+   "name": "notebook"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/linearRegression/LinearRegressionClosedForm.ipynb b/linearRegression/LinearRegressionClosedForm.ipynb
@@ -0,0 +1,160 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(0.0, 11.715194521705058)"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "np.random.seed(10)\n",
+    "m = 100\n",
+    "X = 2*np.random.rand(m,1)\n",
+    "y = 4+3 * X + np.random.randn(m,1)\n",
+    "\n",
+    "plt.scatter(x=X, y=y)\n",
+    "plt.ylim(bottom=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @ in python is matrix multiplication which works the same way\n",
+    "# as using np.dot()\n",
+    "\n",
+    "from sklearn.preprocessing import add_dummy_feature\n",
+    "\n",
+    "X_b = add_dummy_feature(X)\n",
+    "theta_best = np.linalg.inv(X_b.T @ X_b) @ X_b.T @ y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[4.24963579],\n",
+       "       [2.81740108]])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "theta_best"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Interesting, plt.plot() interpolates so you could just pass in whatever you\n",
+    "# want and it would give you the same line.\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "slope = theta_best[1][0]\n",
+    "intercept = theta_best[0][0]\n",
+    "\n",
+    "x_values = np.linspace(min(X), max(X), 2)\n",
+    "y_values = slope * x_values + intercept\n",
+    "\n",
+    "plt.scatter(x=X, y=y)\n",
+    "plt.plot(x_values, y_values, color='red')\n",
+    "plt.ylim(0)\n",
+    "# Show the plot\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(array([4.24963579]), array([[2.81740108]]))"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "\n",
+    "lin_reg = LinearRegression()\n",
+    "\n",
+    "lin_reg.fit(X,y)\n",
+    "lin_reg.intercept_,lin_reg.coef_"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "notebook",
+   "language": "python",
+   "name": "notebook"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/mnist/MNISTClassification.ipynb b/mnist/MNISTClassification.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 88,
    "metadata": {},
    "outputs": [
     {
@@ -57,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -69,13 +69,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/html": [
-       "<style>#sk-container-id-1 {\n",
+       "<style>#sk-container-id-5 {\n",
        "  /* Definition of color scheme common for light and dark mode */\n",
        "  --sklearn-color-text: black;\n",
        "  --sklearn-color-line: gray;\n",
@@ -105,15 +105,15 @@
        "  }\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 {\n",
+       "#sk-container-id-5 {\n",
        "  color: var(--sklearn-color-text);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 pre {\n",
+       "#sk-container-id-5 pre {\n",
        "  padding: 0;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "#sk-container-id-5 input.sk-hidden--visually {\n",
        "  border: 0;\n",
        "  clip: rect(1px 1px 1px 1px);\n",
        "  clip: rect(1px, 1px, 1px, 1px);\n",
@@ -125,7 +125,7 @@
        "  width: 1px;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "#sk-container-id-5 div.sk-dashed-wrapped {\n",
        "  border: 1px dashed var(--sklearn-color-line);\n",
        "  margin: 0 0.4em 0.5em 0.4em;\n",
        "  box-sizing: border-box;\n",
@@ -133,7 +133,7 @@
        "  background-color: var(--sklearn-color-background);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-container {\n",
+       "#sk-container-id-5 div.sk-container {\n",
        "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
        "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
        "     so we also need the `!important` here to be able to override the\n",
@@ -143,7 +143,7 @@
        "  position: relative;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "#sk-container-id-5 div.sk-text-repr-fallback {\n",
        "  display: none;\n",
        "}\n",
        "\n",
@@ -159,14 +159,14 @@
        "\n",
        "/* Parallel-specific style estimator block */\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "#sk-container-id-5 div.sk-parallel-item::after {\n",
        "  content: \"\";\n",
        "  width: 100%;\n",
        "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
        "  flex-grow: 1;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
+       "#sk-container-id-5 div.sk-parallel {\n",
        "  display: flex;\n",
        "  align-items: stretch;\n",
        "  justify-content: center;\n",
@@ -174,28 +174,28 @@
        "  position: relative;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "#sk-container-id-5 div.sk-parallel-item {\n",
        "  display: flex;\n",
        "  flex-direction: column;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "#sk-container-id-5 div.sk-parallel-item:first-child::after {\n",
        "  align-self: flex-end;\n",
        "  width: 50%;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "#sk-container-id-5 div.sk-parallel-item:last-child::after {\n",
        "  align-self: flex-start;\n",
        "  width: 50%;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "#sk-container-id-5 div.sk-parallel-item:only-child::after {\n",
        "  width: 0;\n",
        "}\n",
        "\n",
        "/* Serial-specific style estimator block */\n",
        "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
+       "#sk-container-id-5 div.sk-serial {\n",
        "  display: flex;\n",
        "  flex-direction: column;\n",
        "  align-items: center;\n",
@@ -213,14 +213,14 @@
        "\n",
        "/* Pipeline and ColumnTransformer style (default) */\n",
        "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
+       "#sk-container-id-5 div.sk-toggleable {\n",
        "  /* Default theme specific background. It is overwritten whether we have a\n",
        "  specific estimator or a Pipeline/ColumnTransformer */\n",
        "  background-color: var(--sklearn-color-background);\n",
        "}\n",
        "\n",
        "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "#sk-container-id-5 label.sk-toggleable__label {\n",
        "  cursor: pointer;\n",
        "  display: block;\n",
        "  width: 100%;\n",
@@ -230,7 +230,7 @@
        "  text-align: center;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "#sk-container-id-5 label.sk-toggleable__label-arrow:before {\n",
        "  /* Arrow on the left of the label */\n",
        "  content: \"▸\";\n",
        "  float: left;\n",
@@ -238,13 +238,13 @@
        "  color: var(--sklearn-color-icon);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {\n",
        "  color: var(--sklearn-color-text);\n",
        "}\n",
        "\n",
        "/* Toggleable content - dropdown */\n",
        "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "#sk-container-id-5 div.sk-toggleable__content {\n",
        "  max-height: 0;\n",
        "  max-width: 0;\n",
        "  overflow: hidden;\n",
@@ -253,12 +253,12 @@
        "  background-color: var(--sklearn-color-unfitted-level-0);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "#sk-container-id-5 div.sk-toggleable__content.fitted {\n",
        "  /* fitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-0);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "#sk-container-id-5 div.sk-toggleable__content pre {\n",
        "  margin: 0.2em;\n",
        "  border-radius: 0.25em;\n",
        "  color: var(--sklearn-color-text);\n",
@@ -266,79 +266,79 @@
        "  background-color: var(--sklearn-color-unfitted-level-0);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "#sk-container-id-5 div.sk-toggleable__content.fitted pre {\n",
        "  /* unfitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-0);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
        "  /* Expand drop-down */\n",
        "  max-height: 200px;\n",
        "  max-width: 100%;\n",
        "  overflow: auto;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
        "  content: \"▾\";\n",
        "}\n",
        "\n",
        "/* Pipeline/ColumnTransformer-specific style */\n",
        "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
        "  color: var(--sklearn-color-text);\n",
        "  background-color: var(--sklearn-color-unfitted-level-2);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "#sk-container-id-5 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
        "  background-color: var(--sklearn-color-fitted-level-2);\n",
        "}\n",
        "\n",
        "/* Estimator-specific style */\n",
        "\n",
        "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
        "  /* unfitted */\n",
        "  background-color: var(--sklearn-color-unfitted-level-2);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "#sk-container-id-5 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
        "  /* fitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-2);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
+       "#sk-container-id-5 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-5 div.sk-label label {\n",
        "  /* The background is the default theme color */\n",
        "  color: var(--sklearn-color-text-on-default-background);\n",
        "}\n",
        "\n",
        "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {\n",
        "  color: var(--sklearn-color-text);\n",
        "  background-color: var(--sklearn-color-unfitted-level-2);\n",
        "}\n",
        "\n",
        "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "#sk-container-id-5 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
        "  color: var(--sklearn-color-text);\n",
        "  background-color: var(--sklearn-color-fitted-level-2);\n",
        "}\n",
        "\n",
        "/* Estimator label */\n",
        "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
+       "#sk-container-id-5 div.sk-label label {\n",
        "  font-family: monospace;\n",
        "  font-weight: bold;\n",
        "  display: inline-block;\n",
        "  line-height: 1.2em;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
+       "#sk-container-id-5 div.sk-label-container {\n",
        "  text-align: center;\n",
        "}\n",
        "\n",
        "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
+       "#sk-container-id-5 div.sk-estimator {\n",
        "  font-family: monospace;\n",
        "  border: 1px dotted var(--sklearn-color-border-box);\n",
        "  border-radius: 0.25em;\n",
@@ -348,18 +348,18 @@
        "  background-color: var(--sklearn-color-unfitted-level-0);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "#sk-container-id-5 div.sk-estimator.fitted {\n",
        "  /* fitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-0);\n",
        "}\n",
        "\n",
        "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "#sk-container-id-5 div.sk-estimator:hover {\n",
        "  /* unfitted */\n",
        "  background-color: var(--sklearn-color-unfitted-level-2);\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "#sk-container-id-5 div.sk-estimator.fitted:hover {\n",
        "  /* fitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-2);\n",
        "}\n",
@@ -446,7 +446,7 @@
        "\n",
        "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
        "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "#sk-container-id-5 a.estimator_doc_link {\n",
        "  float: right;\n",
        "  font-size: 1rem;\n",
        "  line-height: 1em;\n",
@@ -461,31 +461,31 @@
        "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "#sk-container-id-5 a.estimator_doc_link.fitted {\n",
        "  /* fitted */\n",
        "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
        "  color: var(--sklearn-color-fitted-level-1);\n",
        "}\n",
        "\n",
        "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "#sk-container-id-5 a.estimator_doc_link:hover {\n",
        "  /* unfitted */\n",
        "  background-color: var(--sklearn-color-unfitted-level-3);\n",
        "  color: var(--sklearn-color-background);\n",
        "  text-decoration: none;\n",
        "}\n",
        "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "#sk-container-id-5 a.estimator_doc_link.fitted:hover {\n",
        "  /* fitted */\n",
        "  background-color: var(--sklearn-color-fitted-level-3);\n",
        "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SGDClassifier(random_state=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;SGDClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.linear_model.SGDClassifier.html\">?<span>Documentation for SGDClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>SGDClassifier(random_state=10)</pre></div> </div></div></div></div>"
+       "</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SGDClassifier(random_state=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;SGDClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.linear_model.SGDClassifier.html\">?<span>Documentation for SGDClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>SGDClassifier(random_state=10)</pre></div> </div></div></div></div>"
       ],
       "text/plain": [
        "SGDClassifier(random_state=10)"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 90,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -504,7 +504,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [
     {
@@ -513,7 +513,7 @@
        "array([0.95135, 0.95335, 0.9631 ])"
       ]
      },
-     "execution_count": 35,
+     "execution_count": 91,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -526,7 +526,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [
     {
@@ -547,7 +547,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [
     {
@@ -556,7 +556,7 @@
        "array([0.90965, 0.90965, 0.90965])"
       ]
      },
-     "execution_count": 37,
+     "execution_count": 93,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -568,7 +568,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -580,7 +580,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 95,
    "metadata": {},
    "outputs": [
     {
@@ -590,7 +590,7 @@
        "       [ 1546,  3875]])"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 95,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -606,6 +606,2467 @@
     "cm = confusion_matrix(y_train_5, y_train_pred)\n",
     "cm"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7792077216971647\n",
+      "0.7148127651724774\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Use sklearn's recall and percision scores to get metrics for\n",
+    "# the model.\n",
+    "\n",
+    "from sklearn.metrics import precision_score, recall_score\n",
+    "print(precision_score(y_train_5, y_train_pred))\n",
+    "print(recall_score(y_train_5, y_train_pred))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.7456224745045218"
+      ]
+     },
+     "execution_count": 97,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import f1_score\n",
+    "\n",
+    "f1_score(y_train_5, y_train_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1714.44342755]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Get score of some_digit from the model\n",
+    "\n",
+    "# The default decision threshold for sgdclassifier is 0, but\n",
+    "# using decision_function we can get the number and do our own\n",
+    "# comparison to make it more or less permissive (precision vs recall) \n",
+    "y_scores = sgd_clf.decision_function([some_digit])\n",
+    "print(y_scores)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get the scores of all samples.\n",
+    "y_scores = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3, method='decision_function')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import precision_recall_curve\n",
+    "threshold = 3000\n",
+    "precisions, recalls, thresholds = precision_recall_curve(y_train_5, y_scores)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x7f322fa5a310>"
+      ]
+     },
+     "execution_count": 101,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(thresholds, precisions[:-1] , linewidth=2, label='precision')\n",
+    "plt.plot(thresholds, recalls[:-1], linewidth=2, label='recall')\n",
+    "plt.vlines(threshold, 0, 1.0, \"k\", \"dotted\", label=\"threshold\")\n",
+    "plt.legend()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7f322f3a86d0>]"
+      ]
+     },
+     "execution_count": 102,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(recalls, precisions, linewidth=2, label=\"Precision/Recall curve\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2734.164532015349\n"
+     ]
+    }
+   ],
+   "source": [
+    "# First threshold for which there is at least a .9 precision level in the array.\n",
+    "idx_for_90_precision = (precisions >=.9).argmax()\n",
+    "threshold_for_90_precision = thresholds[idx_for_90_precision]\n",
+    "print(threshold_for_90_precision)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import roc_curve\n",
+    "\n",
+    "fpr, tpr, thresholds = roc_curve(y_train_5, y_scores)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7f322f3e4290>]"
+      ]
+     },
+     "execution_count": 105,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "idx_for_threshold_at_90 = (thresholds <= threshold_for_90_precision).argmax()\n",
+    "tpr_90, fpr_90 = tpr[idx_for_threshold_at_90], fpr[idx_for_threshold_at_90]\n",
+    "plt.plot(fpr, tpr, linewidth=2, label=\"ROC curve\")\n",
+    "plt.plot([0, 1], [0, 1], 'k:', label=\"Random classifier's ROC curve\")\n",
+    "plt.plot([fpr_90], [tpr_90], \"ko\", label=\"Threshold for 90% precision\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.9422161876011032"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import roc_auc_score\n",
+    "roc_auc_score(y_train_5, y_scores)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "\n",
+    "forest_clf = RandomForestClassifier(random_state=10)\n",
+    "\n",
+    "y_probs_forest = cross_val_predict(forest_clf, X_train, y_train_5, cv=3, method='predict_proba')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0.13, 0.87],\n",
+       "       [0.99, 0.01]])"
+      ]
+     },
+     "execution_count": 108,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_probs_forest[:2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_scores_forest = y_probs_forest[:, 1]\n",
+    "precisions_forest, recalls_forest, thresholds_forest = precision_recall_curve(\n",
+    "y_train_5, y_scores_forest)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(recalls_forest, precisions_forest, \"b-\", linewidth=2,\n",
+    "label=\"Random Forest\")\n",
+    "plt.plot(recalls, precisions, \"--\", linewidth=2, label=\"SGD\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-6 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-6 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-6 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-6 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-6 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-6 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-6 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-6 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-6 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-6 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(random_state=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>SVC(random_state=10)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "SVC(random_state=10)"
+      ]
+     },
+     "execution_count": 111,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Train support vector models on mnist dataset.\n",
+    "\n",
+    "# Since svm is binary classification this used OvO under the hood to train\n",
+    "# 45 different binary classifiers as svms don't scale well with large datasets\n",
+    "# hence stopping us from using OvR classification strategy.\n",
+    "\n",
+    "from sklearn.svm import SVC\n",
+    "\n",
+    "svm_clf = SVC(random_state=10)\n",
+    "svm_clf.fit(X_train[:2000], y_train[:2000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['5'], dtype=object)"
+      ]
+     },
+     "execution_count": 112,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "svm_clf.predict([some_digit])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[ 3.79  0.73  6.06  8.3  -0.29  9.3   1.75  2.77  7.21  4.82]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "some_digit_scores = svm_clf.decision_function([some_digit])\n",
+    "print(some_digit_scores.round(2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'], dtype=object)"
+      ]
+     },
+     "execution_count": 114,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "svm_clf.classes_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-7 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-7 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-7 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-7 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-7 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-7 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-7 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-7 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-7 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-7 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>OneVsRestClassifier(estimator=SVC(random_state=10))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;OneVsRestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.multiclass.OneVsRestClassifier.html\">?<span>Documentation for OneVsRestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>OneVsRestClassifier(estimator=SVC(random_state=10))</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC(random_state=10)</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC(random_state=10)</pre></div> </div></div></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "OneVsRestClassifier(estimator=SVC(random_state=10))"
+      ]
+     },
+     "execution_count": 115,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Force the use of OvR instead of OvO for SVM classification\n",
+    "\n",
+    "from sklearn.multiclass import OneVsRestClassifier\n",
+    "\n",
+    "ovr_clf = OneVsRestClassifier(SVC(random_state=10))\n",
+    "ovr_clf.fit(X_train[:2000] , y_train[:2000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['5'], dtype='<U1')"
+      ]
+     },
+     "execution_count": 116,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ovr_clf.predict([some_digit])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10),\n",
+       " SVC(random_state=10)]"
+      ]
+     },
+     "execution_count": 117,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ovr_clf.estimators_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 122,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['5'], dtype='<U1')"
+      ]
+     },
+     "execution_count": 122,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sgd_clf = SGDClassifier(random_state=10)\n",
+    "sgd_clf.fit(X_train, y_train)\n",
+    "sgd_clf.predict([some_digit])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 123,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[-19186., -26450., -11131.,   -750., -23963.,   4276., -26292.,\n",
+       "         -8538.,  -9102., -20551.]])"
+      ]
+     },
+     "execution_count": 123,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sgd_clf.decision_function([some_digit]).round()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 124,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.88375, 0.8717 , 0.8697 ])"
+      ]
+     },
+     "execution_count": 124,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cross_val_score(sgd_clf, X_train, y_train, cv=3, scoring=\"accuracy\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Standardize the white levels and train again to see the difference this makes.\n",
+    "\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "scaler = StandardScaler()\n",
+    "X_train_scaled = scaler.fit_transform(X_train.astype('float64'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/andrew/gitRepos/myvenv/lib/python3.11/site-packages/sklearn/linear_model/_stochastic_gradient.py:723: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
+      "  warnings.warn(\n",
+      "/home/andrew/gitRepos/myvenv/lib/python3.11/site-packages/sklearn/linear_model/_stochastic_gradient.py:723: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "array([0.90335, 0.90015, 0.90045])"
+      ]
+     },
+     "execution_count": 127,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cross_val_score(sgd_clf, X_train_scaled, y_train, cv=3, scoring='accuracy')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 128,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/andrew/gitRepos/myvenv/lib/python3.11/site-packages/sklearn/linear_model/_stochastic_gradient.py:723: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
+      "  warnings.warn(\n",
+      "/home/andrew/gitRepos/myvenv/lib/python3.11/site-packages/sklearn/linear_model/_stochastic_gradient.py:723: ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import ConfusionMatrixDisplay\n",
+    "\n",
+    "y_train_pred = cross_val_predict(sgd_clf, X_train_scaled, y_train, cv=3)\n",
+    "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Normalize outputs so the colors are based on percent and not totals\n",
+    "\n",
+    "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
+    "normalize=\"true\", values_format=\".0%\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 132,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Unweight correct labels and weight by row\n",
+    "\n",
+    "sample_weight = (y_train_pred != y_train)\n",
+    "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
+    "sample_weight=sample_weight,\n",
+    "normalize=\"true\", values_format=\".0%\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 135,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-8 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-8 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-8 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-8 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-8 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-8 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-8 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-8 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-8 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-8 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" checked><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;KNeighborsClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.neighbors.KNeighborsClassifier.html\">?<span>Documentation for KNeighborsClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>KNeighborsClassifier()</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "KNeighborsClassifier()"
+      ]
+     },
+     "execution_count": 135,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "\n",
+    "# True if greater than or equal to 7 for label\n",
+    "y_train_large = (y_train >= '7')\n",
+    "\n",
+    "# True if od number\n",
+    "y_train_odd = (y_train.astype('int8') % 2 == 1)\n",
+    "y_multilabel = np.c_[y_train_large, y_train_odd]\n",
+    "\n",
+    "knn_clf = KNeighborsClassifier()\n",
+    "\n",
+    "# Train on training set with labels of true for 7 or greater and another boolean that\n",
+    "# is true if the number is odd.\n",
+    "knn_clf.fit(X_train, y_multilabel)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 136,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[False,  True]])"
+      ]
+     },
+     "execution_count": 136,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "knn_clf.predict([some_digit])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 137,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.9764102655606048"
+      ]
+     },
+     "execution_count": 137,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train_knn_pred = cross_val_predict(knn_clf, X_train, y_multilabel, cv=3)\n",
+    "f1_score(y_multilabel, y_train_knn_pred, average=\"macro\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-9 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-9 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-9 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-9 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-9 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-9 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-9 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-9 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-9 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-9 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>ClassifierChain(base_estimator=SVC(), cv=3, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;ClassifierChain<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.multioutput.ClassifierChain.html\">?<span>Documentation for ClassifierChain</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>ClassifierChain(base_estimator=SVC(), cv=3, random_state=42)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">base_estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "ClassifierChain(base_estimator=SVC(), cv=3, random_state=42)"
+      ]
+     },
+     "execution_count": 139,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.multioutput import ClassifierChain\n",
+    "chain_clf = ClassifierChain(SVC(), cv=3, random_state=42)\n",
+    "chain_clf.fit(X_train[:2000], y_multilabel[:2000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0., 1.]])"
+      ]
+     },
+     "execution_count": 140,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain_clf.predict([some_digit])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 141,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "np.random.seed(42) # to make this code example reproducible\n",
+    "noise = np.random.randint(0, 100, (len(X_train), 784))\n",
+    "X_train_mod = X_train + noise\n",
+    "noise = np.random.randint(0, 100, (len(X_test), 784))\n",
+    "X_test_mod = X_test + noise\n",
+    "y_train_mod = X_train\n",
+    "y_test_mod = X_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot(X_test_mod[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 147,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "knn_clf = KNeighborsClassifier()\n",
+    "knn_clf.fit(X_train_mod, y_train_mod)\n",
+    "clean_digit = knn_clf.predict([X_test_mod[0]])\n",
+    "plot(clean_digit)\n",
+    "plt.show()"
+   ]
   }
  ],
  "metadata": {

	machinelearning Unnamed repository; edit this file 'description' to name the repository.
	Log \| Files \| Refs

A	gradientDescent/GradientDescentLinearRegression.ipynb	\|	79	+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
A	linearRegression/LinearRegressionClosedForm.ipynb	\|	160	+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
M	mnist/MNISTClassification.ipynb	\|	2573	+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--