Synch notebooks

Author: ArturoAmorQ

notebooks/dimred_components.ipynb

@@ -60,7 +60,7 @@
    "source": [
     "from skrub import TableReport\n",
     "\n",
-    "TableReport(X)"
+    "TableReport(X, verbose=0)"
    ]
   },
   {
@@ -171,7 +171,9 @@
    "source": [
     "pipe_90 = make_pipeline(StandardScaler(), PCA(n_components=0.90))\n",
     "pipe_90.fit(X)\n",
-    "print(f\"n_components_ for 90% threshold: {pipe_90.named_steps['pca'].n_components_}\")"
+    "print(\n",
+    "    f\"n_components_ for 90% threshold: {pipe_90.named_steps['pca'].n_components_}\"\n",
+    ")"
    ]
   },
   {
@@ -204,7 +206,9 @@
     "    X_split, _ = train_test_split(X, train_size=0.5, random_state=random_state)\n",
     "    pipe_split = make_pipeline(StandardScaler(), PCA())\n",
     "    pipe_split.fit(X_split)\n",
-    "    split_explained.append(pipe_split.named_steps[\"pca\"].explained_variance_ratio_)"
+    "    split_explained.append(\n",
+    "        pipe_split.named_steps[\"pca\"].explained_variance_ratio_\n",
+    "    )"
    ]
   },
   {
@@ -216,9 +220,13 @@
     "fig, ax = plt.subplots(figsize=(8, 4))\n",
     "\n",
     "for ev in split_explained:\n",
-    "    ax.plot(np.arange(1, len(ev) + 1), np.cumsum(ev), color=\"tab:blue\", alpha=0.2)\n",
+    "    ax.plot(\n",
+    "        np.arange(1, len(ev) + 1), np.cumsum(ev), color=\"tab:blue\", alpha=0.2\n",
+    "    )\n",
     "\n",
-    "ax.plot(components, cumulative, color=\"tab:blue\", linewidth=2, label=\"Full dataset\")\n",
+    "ax.plot(\n",
+    "    components, cumulative, color=\"tab:blue\", linewidth=2, label=\"Full dataset\"\n",
+    ")\n",
     "ax.axhline(0.90, color=\"tab:orange\", linestyle=\"--\", label=\"90%\")\n",
     "ax.axhline(0.95, color=\"tab:red\", linestyle=\"--\", label=\"95%\")\n",
     "ax.set_xlabel(\"Number of components\")\n",
@@ -318,7 +326,9 @@
     "for ev in split_explained:\n",
     "    ax.plot(np.arange(1, len(ev) + 1), ev, color=\"tab:blue\", alpha=0.2)\n",
     "\n",
-    "ax.plot(components, explained, color=\"tab:blue\", linewidth=2, label=\"Full dataset\")\n",
+    "ax.plot(\n",
+    "    components, explained, color=\"tab:blue\", linewidth=2, label=\"Full dataset\"\n",
+    ")\n",
     "ax.axhline(\n",
     "    kaiser_threshold,\n",
     "    color=\"tab:red\",\n",
@@ -424,15 +434,20 @@
     "for ax, n_components, label in zip(\n",
     "    axes,\n",
     "    [kaiser_n, threshold_90],\n",
-    "    [f\"Kaiser ({kaiser_n} components)\", f\"90% threshold ({threshold_90} components)\"],\n",
+    "    [\n",
+    "        f\"Kaiser ({kaiser_n} components)\",\n",
+    "        f\"90% threshold ({threshold_90} components)\",\n",
+    "    ],\n",
     "):\n",
     "    pipe_km = make_pipeline(\n",
     "        StandardScaler(),\n",
     "        PCA(n_components=n_components),\n",
     "        KMeans(random_state=0),\n",
     "    )\n",
     "    for random_state in range(1, 11):\n",
-    "        X_sub, _ = train_test_split(X, train_size=0.5, random_state=random_state)\n",
+    "        X_sub, _ = train_test_split(\n",
+    "            X, train_size=0.5, random_state=random_state\n",
+    "        )\n",
     "        scores = []\n",
     "        for k in n_clusters_range:\n",
     "            pipe_km[-1].set_params(n_clusters=k)\n",

notebooks/dimred_ex_01.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Solution for Exercise M8.01\n",
+    "# Exercise M8.01\n",
     "\n",
     "In the Chapter on Linear Models we saw that feature engineering using\n",
     "`PolynomialFeatures` can give a linear model the flexibility to capture\n",
@@ -111,10 +111,7 @@
    "metadata": {},
    "source": [
     "Build a `grid_search_results` DataFrame from the attribute `cv_results_`\n",
-    "keeping only the columns listed in `results_columns` below. Add a\n",
-    "`\"mean_test_error\"` column as the negative of `\"mean_test_score\"`, drop\n",
-    "`\"mean_test_score\"`, and rename `\"param_pca__n_components\"` to\n",
-    "`\"n_components\"`."
+    "keeping only the columns listed in `results_columns` below."
    ]
   },
   {
@@ -160,30 +157,53 @@
    "source": [
     "import plotly.express as px\n",
     "\n",
-    "labels = {\n",
-    "    \"mean_fit_time\": \"CV fit time (s)\",\n",
-    "    \"mean_test_error\": \"CV score (MAE)\",\n",
-    "}\n",
-    "grid_search_results[\"n_components\"] = grid_search_results[\"n_components\"].fillna(\"None\")\n",
-    "fig = px.scatter(\n",
-    "    grid_search_results,\n",
-    "    x=\"mean_fit_time\",\n",
-    "    y=\"mean_test_error\",\n",
-    "    error_x=\"std_fit_time\",\n",
-    "    error_y=\"std_test_score\",\n",
-    "    hover_data=grid_search_results.columns,\n",
-    "    labels=labels,\n",
-    ")\n",
-    "fig.update_layout(\n",
-    "    title={\n",
-    "        \"text\": \"Trade-off between fit time and mean test score\",\n",
-    "        \"y\": 0.95,\n",
-    "        \"x\": 0.5,\n",
-    "        \"xanchor\": \"center\",\n",
-    "        \"yanchor\": \"top\",\n",
+    "\n",
+    "def plot_grid_search_results(grid_search_results):\n",
+    "    grid_search_results[\"mean_test_error\"] = -grid_search_results[\n",
+    "        \"mean_test_score\"\n",
+    "    ]\n",
+    "    grid_search_results = (\n",
+    "        grid_search_results.drop(columns=[\"mean_test_score\"])\n",
+    "        .rename(columns={\"param_\" + param_name: \"n_components\"})\n",
+    "        .round(2)\n",
+    "    )\n",
+    "    grid_search_results.sort_values(\"mean_test_error\", ascending=False)\n",
+    "\n",
+    "    labels = {\n",
+    "        \"mean_fit_time\": \"CV fit time (s)\",\n",
+    "        \"mean_test_error\": \"CV score (RMSE)\",\n",
     "    }\n",
-    ")\n",
-    "fig.show(renderer=\"notebook\")"
+    "    grid_search_results[\"n_components\"] = grid_search_results[\n",
+    "        \"n_components\"\n",
+    "    ].fillna(\"None\")\n",
+    "    fig = px.scatter(\n",
+    "        grid_search_results,\n",
+    "        x=\"mean_fit_time\",\n",
+    "        y=\"mean_test_error\",\n",
+    "        error_x=\"std_fit_time\",\n",
+    "        error_y=\"std_test_score\",\n",
+    "        hover_data=grid_search_results.columns,\n",
+    "        labels=labels,\n",
+    "    )\n",
+    "    fig.update_layout(\n",
+    "        title={\n",
+    "            \"text\": \"Trade-off between fit time and mean test score\",\n",
+    "            \"y\": 0.95,\n",
+    "            \"x\": 0.5,\n",
+    "            \"xanchor\": \"center\",\n",
+    "            \"yanchor\": \"top\",\n",
+    "        }\n",
+    "    )\n",
+    "    fig.show(renderer=\"notebook\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Write your code here."
    ]
   },
   {
@@ -266,4 +286,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}