Christophe

.gitignore

@@ -105,3 +105,11 @@ ENV/
 *.cb2
 *.fdb_latexmk
 *.synctex.gz
+projects/project1/data/dataset/dataset/sample_submission.csv
+projects/project1/data/dataset/dataset/x_test.csv
+projects/project1/data/dataset/dataset/x_train.csv
+projects/project1/data/dataset/dataset/y_train.csv
+projects/project1/x_train_cleaned.csv
+projects/project1/data/dataset/dataset/x_train_clean.csv
+projects/project1/data/dataset/dataset/x_train_cleaned.csv
+projects/project1/latex-example-paper.zip

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "git.ignoreLimitWarning": true
+}

Untitled.ipynb

@@ -0,0 +1,33 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f00748fc-eb20-4a98-87ad-0f38fc307222",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:ada] *",
+   "language": "python",
+   "name": "conda-env-ada-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

labs/ex01/template/taskA.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -20,7 +20,6 @@
   },
   {
    "cell_type": "markdown",
-   "execution_count": null,
    "metadata": {},
    "source": [
     "Data Generation\n",
@@ -29,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -48,7 +47,6 @@
   },
   {
    "cell_type": "markdown",
-   "execution_count": null,
    "metadata": {},
    "source": [
     "Solution\n",
@@ -57,18 +55,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0.77132064 0.02075195 0.63364823 0.74880388 0.49850701]\n",
+      " [0.22479665 0.19806286 0.76053071 0.16911084 0.08833981]\n",
+      " [0.68535982 0.95339335 0.00394827 0.51219226 0.81262096]\n",
+      " [0.61252607 0.72175532 0.29187607 0.91777412 0.71457578]\n",
+      " [0.54254437 0.14217005 0.37334076 0.67413362 0.44183317]\n",
+      " [0.43401399 0.61776698 0.51313824 0.65039718 0.60103895]\n",
+      " [0.8052232  0.52164715 0.90864888 0.31923609 0.09045935]\n",
+      " [0.30070006 0.11398436 0.82868133 0.04689632 0.62628715]\n",
+      " [0.54758616 0.819287   0.19894754 0.8568503  0.35165264]\n",
+      " [0.75464769 0.29596171 0.88393648 0.32551164 0.1650159 ]]\n"
+     ]
+    }
+   ],
    "source": [
     "print(data)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ Your `standardize` passed 1 tests.\n"
+     ]
+    }
+   ],
    "source": [
     "def standardize(x):\n",
     "    \"\"\"Stadartize the input data x\n",
@@ -88,7 +111,8 @@
     "    # INSERT YOUR CODE HERE\n",
     "    # TODO: standartize input data x\n",
     "    # ***************************************************\n",
-    "    raise NotImplementedError\n",
+    "    #Here we use axis=0 because we are standardizing the data by dimension, and hence column\n",
+    "    std_data = (x - np.mean(x, axis = 0))/np.std(x, axis = 0)\n",
     "    return std_data\n",
     "\n",
     "\n",
@@ -97,9 +121,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[ 1.0775774  -1.34411605  0.31525355  0.80665878  0.24128662]\n",
+      " [-1.81711634 -0.77630186  0.74088404 -1.25592235 -1.42276759]\n",
+      " [ 0.62228127  1.64254169 -1.797091   -0.03521894  1.51565143]\n",
+      " [ 0.23651339  0.90075228 -0.83122987  1.40786459  1.11788073]\n",
+      " [-0.13414844 -0.95529104 -0.55795449  0.54097769  0.01136005]\n",
+      " [-0.70898541  0.56774371 -0.08900028  0.45652209  0.65726018]\n",
+      " [ 1.2571441   0.25993298  1.23775021 -0.72176808 -1.4141686 ]\n",
+      " [-1.41508984 -1.04555188  0.96949701 -1.69076861  0.75969247]\n",
+      " [-0.10744434  1.21308427 -1.14296098  1.19109415 -0.35450368]\n",
+      " [ 0.98926822 -0.46279408  1.15485183 -0.69943932 -1.11169162]] \n",
+      "\n",
+      " [-1.66533454e-16  4.99600361e-17 -2.22044605e-17  1.11022302e-17\n",
+      "  3.33066907e-16] \n",
+      "\n",
+      " [1. 1. 1. 1. 1.]\n"
+     ]
+    }
+   ],
    "source": [
     "std_data = standardize(data)\n",
     "print(std_data, \"\\n\\n\", np.mean(std_data, axis=0), \"\\n\\n\", np.std(std_data, axis=0))"
@@ -114,8 +160,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
   }
  },
  "nbformat": 4,