added complementary option to pw3

PW-3/ex3/ex3-review-questions-stud.ipynb

@@ -61,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "14aba0f7",
    "metadata": {},
    "outputs": [],
@@ -148,12 +148,108 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 10,
    "id": "4de72736",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training data shape:  (10000, 28, 28)\n",
+      "Training labels shape:  (10000,)\n",
+      "Test data shape:  (10000, 28, 28)\n",
+      "Test labels shape:  (10000,)\n",
+      "(10000, 784) (10000, 784)\n",
+      "Accuracy score : 0.5711\n"
+     ]
+    }
+   ],
    "source": [
-    "pass"
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "\n",
+    "\n",
+    "# This is a method to read the MNIST dataset from a ROOT directory\n",
+    "def load_MNIST(ROOT):\n",
+    "  '''load all of mnist\n",
+    "  training set first'''\n",
+    "  Xtr = []\n",
+    "  train = pd.read_csv(os.path.join(ROOT, 'mnist_train.csv'))\n",
+    "  X = np.array(train.drop('label', axis=1))\n",
+    "  Ytr = np.array(train['label'])\n",
+    "  # With this for-loop we give the data a shape of the acctual image (28x28)\n",
+    "  # instead of the shape in file (1x784)\n",
+    "  for row in X:\n",
+    "      Xtr.append(row.reshape(28,28))\n",
+    "  # load test set second\n",
+    "  Xte = []\n",
+    "  test = pd.read_csv(os.path.join(ROOT, 'mnist_test.csv'))\n",
+    "  X = np.array(test.drop('label', axis=1))\n",
+    "  Yte = np.array(test['label'])\n",
+    "  # same reshaping\n",
+    "  for row in X:\n",
+    "      Xte.append(row.reshape(28,28))\n",
+    "  \n",
+    "  return np.array(Xtr), np.array(Ytr), np.array(Xte), np.array(Yte)\n",
+    "\n",
+    "# Load the raw MNIST data.\n",
+    "mnist_dir = '' \n",
+    "X_train, y_train, X_test, y_test = load_MNIST(mnist_dir)\n",
+    "\n",
+    "# As a sanity check, we print out the size of the training and test data.\n",
+    "print('Training data shape: ', X_train.shape)\n",
+    "print('Training labels shape: ', y_train.shape)\n",
+    "print('Test data shape: ', X_test.shape)\n",
+    "print('Test labels shape: ', y_test.shape)\n",
+    "X_train = np.reshape(X_train, (X_train.shape[0], -1)) \n",
+    "X_test = np.reshape(X_test, (X_test.shape[0], -1))    \n",
+    "\n",
+    "print(X_train.shape, X_test.shape)\n",
+    "def predict_gaussian(X_test, mu, sigma2, priors):\n",
+    "    n_samples = X_test.shape[0]\n",
+    "    y_pred = np.zeros(n_samples)\n",
+    "\n",
+    "    K, n_pixels = mu.shape\n",
+    "    \n",
+    "    for idx in range(n_samples):\n",
+    "        x = X_test[idx]\n",
+    "        proba_classes = np.zeros(K)\n",
+    "\n",
+    "        for c in range(K):\n",
+    "            log_likelihood = -0.5 * np.log(2 * np.pi * sigma2[c]) - ((x - mu[c])**2) / (2 * sigma2[c])\n",
+    "            proba_classes[c] = np.log(priors[c]) + np.sum(log_likelihood)\n",
+    "  \n",
+    "        y_pred[idx] = np.argmax(proba_classes)\n",
+    "\n",
+    "    return y_pred\n",
+    "classes = np.unique(y_train)\n",
+    "priors = np.array([np.mean(y_train == c) for c in classes])\n",
+    "\n",
+    "n_pixels = X_train.shape[1]\n",
+    "\n",
+    "mu = np.zeros((len(classes), n_pixels))\n",
+    "sigma2 = np.zeros((len(classes), n_pixels))\n",
+    "\n",
+    "for c in classes:\n",
+    "    X_c = X_train[y_train == c]\n",
+    "    mu[c, :] = X_c.mean(axis=0)\n",
+    "    sigma2[c, :] = X_c.var(axis=0) + 1e-5\n",
+    "    \n",
+    "y_pred = predict_gaussian(X_test, mu, sigma2, priors)\n",
+    "accuracy = np.mean(y_pred == y_test)\n",
+    "\n",
+    "print(\"Accuracy score :\", accuracy)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "07cb7aee",
+   "metadata": {},
+   "source": [
+    "The .57 accuracy observed here might prove that the method is not the right one for this type of problems, because if each pixel is a feature, the number of dimensions become way to big. This might also be caused by the fact that pixels are not uncorrelated."
    ]
   },
   {
@@ -199,7 +295,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -213,7 +309,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.12.3"
   }
  },
  "nbformat": 4,