Replace y_gen_faces with y_bad, and other little fixes (thanks Ian!)

09_unsupervised_learning.ipynb

@@ -1660,7 +1660,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "log_reg.score(X_test, y_test)"
+    "log_reg_score = log_reg.score(X_test, y_test)\n",
+    "log_reg_score"
    ]
   },
   {
@@ -1698,7 +1699,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pipeline.score(X_test, y_test)"
+    "pipeline_score = pipeline.score(X_test, y_test)\n",
+    "pipeline_score"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "How much did the error rate drop?"
    ]
   },
   {
@@ -1707,14 +1716,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "1 - (1 - 0.977777) / (1 - 0.968888)"
+    "1 - (1 - pipeline_score) / (1 - log_reg_score)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "How about that? We reduced the error rate by over 28%! But we chose the number of clusters $k$ completely arbitrarily, we can surely do better. Since K-Means is just a preprocessing step in a classification pipeline, finding a good value for $k$ is much simpler than earlier: there's no need to perform silhouette analysis or minimize the inertia, the best value of $k$ is simply the one that results in the best classification performance."
+    "How about that? We reduced the error rate by over 35%! But we chose the number of clusters $k$ completely arbitrarily, we can surely do better. Since K-Means is just a preprocessing step in a classification pipeline, finding a good value for $k$ is much simpler than earlier: there's no need to perform silhouette analysis or minimize the inertia, the best value of $k$ is simply the one that results in the best classification performance."
    ]
   },
   {
@@ -3473,11 +3482,12 @@
    "outputs": [],
    "source": [
     "def plot_faces(faces, labels, n_cols=5):\n",
+    "    faces = faces.reshape(-1, 64, 64)\n",
     "    n_rows = (len(faces) - 1) // n_cols + 1\n",
     "    plt.figure(figsize=(n_cols, n_rows * 1.1))\n",
     "    for index, (face, label) in enumerate(zip(faces, labels)):\n",
     "        plt.subplot(n_rows, n_cols, index + 1)\n",
-    "        plt.imshow(face.reshape(64, 64), cmap=\"gray\")\n",
+    "        plt.imshow(face, cmap=\"gray\")\n",
     "        plt.axis(\"off\")\n",
     "        plt.title(label)\n",
     "    plt.show()\n",
@@ -3485,7 +3495,7 @@
     "for cluster_id in np.unique(best_model.labels_):\n",
     "    print(\"Cluster\", cluster_id)\n",
     "    in_cluster = best_model.labels_==cluster_id\n",
-    "    faces = X_train[in_cluster].reshape(-1, 64, 64)\n",
+    "    faces = X_train[in_cluster]\n",
     "    labels = y_train[in_cluster]\n",
     "    plot_faces(faces, labels)"
    ]
@@ -3709,7 +3719,6 @@
     "n_darkened = 3\n",
     "darkened = X_train[:n_darkened].copy()\n",
     "darkened[:, 1:-1] *= 0.3\n",
-    "darkened = darkened.reshape(-1, 64*64)\n",
     "y_darkened = y_train[:n_darkened]\n",
     "\n",
     "X_bad_faces = np.r_[rotated, flipped, darkened]\n",
@@ -3819,7 +3828,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "plot_faces(X_bad_faces, y_gen_faces)"
+    "plot_faces(X_bad_faces, y_bad)"
    ]
   },
   {
@@ -3829,7 +3838,7 @@
    "outputs": [],
    "source": [
     "X_bad_faces_reconstructed = pca.inverse_transform(X_bad_faces_pca)\n",
-    "plot_faces(X_bad_faces_reconstructed, y_gen_faces)"
+    "plot_faces(X_bad_faces_reconstructed, y_bad)"
    ]
   },
   {