diff --git a/0-pilot-project/MNIST-kNN.ipynb b/0-pilot-project/MNIST-kNN.ipynb
index 75d1754..1499438 100644
--- a/0-pilot-project/MNIST-kNN.ipynb
+++ b/0-pilot-project/MNIST-kNN.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "5125f820",
+   "id": "0b4fc5df",
    "metadata": {},
    "source": [
     "### Load MNIST dataset"
@@ -11,7 +11,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "4dbfbcbd",
+   "id": "12f0d563",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -23,7 +23,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "bb0fae7c",
+   "id": "00907c8a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "06585ea4",
+   "id": "75bfecec",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -46,7 +46,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "8d92fea0",
+   "id": "a46d690d",
    "metadata": {},
    "outputs": [
     {
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "288e3ba7",
+   "id": "91ca9e00",
    "metadata": {},
    "source": [
     "Bunch objects are sometimes used as an output for functions and methods. They extend dictionaries by enabling values to be accessed by key, bunch[\"value_key\"], or by an attribute, bunch.value_key.\\\n",
@@ -83,7 +83,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "b171490e",
+   "id": "73f99731",
    "metadata": {},
    "outputs": [
     {
@@ -106,7 +106,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "d45b18b4",
+   "id": "4e9d2111",
    "metadata": {},
    "outputs": [
     {
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "07ebfb03",
+   "id": "a265f8c6",
    "metadata": {},
    "source": [
     "Datasets loaded by Scikit-Learn generally have a similar dictionary structure, including the following:\\\n",
@@ -139,7 +139,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "11f18ea2",
+   "id": "6adfe3a8",
    "metadata": {},
    "outputs": [
     {
@@ -159,7 +159,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a7cf6de3",
+   "id": "d7fb839a",
    "metadata": {},
    "source": [
     "### Prepare the MNIST dataset"
@@ -167,7 +167,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cf0d7b65",
+   "id": "74c92079",
    "metadata": {},
    "source": [
     "$f(X) = y$\n",
@@ -181,7 +181,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "1e953940",
+   "id": "0b84ef9b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -191,7 +191,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "12769332",
+   "id": "3f87bfe5",
    "metadata": {},
    "outputs": [
     {
@@ -212,7 +212,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "4b7766d9",
+   "id": "df5d43d6",
    "metadata": {},
    "outputs": [
     {
@@ -233,7 +233,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "385c1ec8",
+   "id": "6ac9bcc4",
    "metadata": {},
    "outputs": [
     {
@@ -253,7 +253,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cdea3089",
+   "id": "4112ff94",
    "metadata": {},
    "source": [
     "### Plot data"
@@ -262,7 +262,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "dc896a25",
+   "id": "79eee1c1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -274,7 +274,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "daa4382b",
+   "id": "880e45dd",
    "metadata": {},
    "outputs": [
     {
@@ -297,7 +297,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "42938e91",
+   "id": "70a234b6",
    "metadata": {},
    "outputs": [
     {
@@ -317,7 +317,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "8c9ebb6b",
+   "id": "cd746b72",
    "metadata": {},
    "outputs": [
     {
@@ -343,7 +343,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "id": "1560264d",
+   "id": "51633961",
    "metadata": {},
    "outputs": [
     {
@@ -364,7 +364,7 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "id": "2755e361",
+   "id": "34e6d15c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -375,7 +375,7 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "id": "d4fa3259",
+   "id": "1b8d8b53",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -389,7 +389,7 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "id": "96bdd01c",
+   "id": "cd36c702",
    "metadata": {},
    "outputs": [
     {
@@ -413,7 +413,7 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "id": "92321904",
+   "id": "9400192f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +429,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "id": "f55b9f28",
+   "id": "929a8060",
    "metadata": {},
    "outputs": [
     {
@@ -454,7 +454,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "16a7efd4",
+   "id": "02209b9d",
    "metadata": {},
    "source": [
     "### Prepare data for machine learning"
@@ -463,7 +463,7 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "id": "729e023e",
+   "id": "512aa5ff",
    "metadata": {},
    "outputs": [
     {
@@ -484,7 +484,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "71fc6692",
+   "id": "6f9cd32d",
    "metadata": {},
    "source": [
     "### Train classifier"
@@ -492,29 +492,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
-   "id": "09db3699",
+   "execution_count": 23,
+   "id": "0212798c",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "train_sz=66652, k= 1, accuracy=98.7157%\n",
-      "train_sz=66652, k= 3, accuracy=98.7754%\n",
-      "train_sz=66652, k= 5, accuracy=98.7157%\n",
-      "train_sz=66652, k= 7, accuracy=98.6260%\n",
-      "train_sz=66652, k= 9, accuracy=98.5066%\n",
-      "train_sz=66652, k=11, accuracy=98.5663%\n",
-      "train_sz=66652, k=13, accuracy=98.5066%\n",
-      "train_sz=66652, k=15, accuracy=98.5066%\n",
-      "train_sz=66652, k=17, accuracy=98.3572%\n",
-      "train_sz=66652, k=19, accuracy=98.3871%\n",
-      "train_sz=66652, k=21, accuracy=98.3274%\n",
-      "train_sz=66652, k=23, accuracy=98.3572%\n",
-      "train_sz=66652, k=25, accuracy=98.4170%\n",
-      "train_sz=66652, k=27, accuracy=98.4170%\n",
-      "train_sz=66652, k=29, accuracy=98.3274%\n"
+      "train_sz=66652, k= 3, accuracy=98.7754%\n"
      ]
     }
    ],
@@ -531,6 +517,9 @@
     "accuracies = []\n",
     "classifier = KNeighborsClassifier()\n",
     "\n",
+    "train_sz = 66652\n",
+    "k = 3\n",
+    "\n",
     "X_train, X_test, y_train, y_test = X[:train_sz], X[train_sz:], y[:train_sz], y[train_sz:]\n",
     "classifier = KNeighborsClassifier(n_neighbors=k)\n",
     "classifier.fit(X_train, y_train)\n",
@@ -557,23 +546,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
-   "id": "cee98962",
+   "execution_count": 24,
+   "id": "157dbaa6",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 1440x1440 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# import matplotlib.pyplot as plt\n",
     "\n",
@@ -601,29 +577,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
-   "id": "659bae0d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.9877538829151732"
-      ]
-     },
-     "execution_count": 70,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "max(accuracies)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 82,
-   "id": "d37de857",
+   "execution_count": 26,
+   "id": "d5babb27",
    "metadata": {},
    "outputs": [
     {
@@ -647,8 +602,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
-   "id": "9f6804c8",
+   "execution_count": 27,
+   "id": "40267938",
    "metadata": {},
    "outputs": [
     {
@@ -666,8 +621,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
-   "id": "9c3ef940",
+   "execution_count": 28,
+   "id": "6a53fad1",
    "metadata": {},
    "outputs": [
     {
@@ -685,8 +640,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
-   "id": "8221555f",
+   "execution_count": 29,
+   "id": "832b7b62",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -696,8 +651,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
-   "id": "3d36bc28",
+   "execution_count": 30,
+   "id": "444ed55f",
    "metadata": {},
    "outputs": [
     {
@@ -706,7 +661,7 @@
        "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=uint8)"
       ]
      },
-     "execution_count": 86,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -718,7 +673,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ee904ff4",
+   "id": "c96b451a",
    "metadata": {},
    "source": [
     "### Evaluation"
@@ -726,8 +681,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 88,
-   "id": "cf17fb24",
+   "execution_count": 31,
+   "id": "964f3493",
    "metadata": {},
    "outputs": [
     {
@@ -747,8 +702,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
-   "id": "70034cf7",
+   "execution_count": 32,
+   "id": "c04ca966",
    "metadata": {},
    "outputs": [
     {
@@ -768,7 +723,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3975899b",
+   "id": "d6bcbe4b",
    "metadata": {},
    "source": [
     "Accuracy is strongly influenced by the distribution of the classes in the test data."
@@ -776,7 +731,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bd89f794",
+   "id": "62200820",
    "metadata": {},
    "source": [
     "#### Cross Validation\n",
@@ -785,8 +740,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
-   "id": "9be7442c",
+   "execution_count": 33,
+   "id": "485d7fb2",
    "metadata": {},
    "outputs": [
     {
@@ -806,8 +761,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
-   "id": "5c0317f5",
+   "execution_count": 34,
+   "id": "48cd1f2e",
    "metadata": {},
    "outputs": [
     {
@@ -828,7 +783,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "06da2cde",
+   "id": "61adca5b",
    "metadata": {},
    "source": [
     "#### Precision"
@@ -836,8 +791,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
-   "id": "473e073d",
+   "execution_count": 35,
+   "id": "dc6137f4",
    "metadata": {},
    "outputs": [
     {
@@ -846,7 +801,7 @@
        "0.9679281746772196"
       ]
      },
-     "execution_count": 92,
+     "execution_count": 35,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -859,7 +814,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3e0c1a22",
+   "id": "6e71a45e",
    "metadata": {},
    "source": [
     "#### Recall"
@@ -867,8 +822,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 93,
-   "id": "6763d555",
+   "execution_count": 36,
+   "id": "5651a2f9",
    "metadata": {},
    "outputs": [
     {
@@ -877,7 +832,7 @@
        "0.9677579067394827"
       ]
      },
-     "execution_count": 93,
+     "execution_count": 36,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -890,7 +845,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b7acbde2",
+   "id": "d1ad054a",
    "metadata": {},
    "source": [
     "#### F1 Score"
@@ -898,8 +853,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
-   "id": "9a3e7b6e",
+   "execution_count": 37,
+   "id": "d9091409",
    "metadata": {},
    "outputs": [
     {
@@ -908,7 +863,7 @@
        "0.9676787940700043"
       ]
      },
-     "execution_count": 94,
+     "execution_count": 37,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -921,7 +876,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "18beba4a",
+   "id": "e46c2f46",
    "metadata": {},
    "source": [
     "#### Confusion Matrix"
@@ -929,8 +884,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 95,
-   "id": "ae3cad3f",
+   "execution_count": 38,
+   "id": "c7d6cb70",
    "metadata": {},
    "outputs": [
     {
@@ -959,8 +914,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 96,
-   "id": "6bff7f05",
+   "execution_count": 39,
+   "id": "5435b8a1",
    "metadata": {},
    "outputs": [
     {
@@ -1007,8 +962,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
-   "id": "0d655587",
+   "execution_count": 40,
+   "id": "4d36c617",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1018,8 +973,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
-   "id": "1c951c80",
+   "execution_count": 41,
+   "id": "6ac6f602",
    "metadata": {},
    "outputs": [
     {
@@ -1048,7 +1003,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "789dc78c",
+   "id": "e437a491",
    "metadata": {},
    "source": [
     "## Train kNN Classifer\n",
@@ -1058,7 +1013,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4a7bc22f",
+   "id": "c41b6913",
    "metadata": {},
    "outputs": [],
    "source": []