Rename sparse to sparse_output in OneHotEncoder, set numeric_only=True in corr(), set n_init=10 in KMeans

02_end_to_end_machine_learning_project.ipynb

@@ -1199,13 +1199,20 @@
     "## Looking for Correlations"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note: since Pandas 2.0.0, the `numeric_only` argument defaults to `False`, so we need to set it explicitly to True to avoid an error."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
-    "corr_matrix = housing.corr()"
+    "corr_matrix = housing.corr(numeric_only=True)"
    ]
   },
   {
@@ -1337,7 +1344,7 @@
     }
    ],
    "source": [
-    "corr_matrix = housing.corr()\n",
+    "corr_matrix = housing.corr(numeric_only=True)\n",
     "corr_matrix[\"median_house_value\"].sort_values(ascending=False)"
    ]
   },
@@ -2551,7 +2558,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Alternatively, you can set `sparse=False` when creating the `OneHotEncoder`:"
+    "Alternatively, you can set `sparse_output=False` when creating the `OneHotEncoder` (note: the `sparse` hyperparameter was renamned to `sparse_output` in Scikit-Learn 1.2):"
    ]
   },
   {
@@ -2577,7 +2584,7 @@
     }
    ],
    "source": [
-    "cat_encoder = OneHotEncoder(sparse=False)\n",
+    "cat_encoder = OneHotEncoder(sparse_output=False)\n",
     "housing_cat_1hot = cat_encoder.fit_transform(housing_cat)\n",
     "housing_cat_1hot"
    ]
@@ -3299,7 +3306,8 @@
     "        self.random_state = random_state\n",
     "\n",
     "    def fit(self, X, y=None, sample_weight=None):\n",
-    "        self.kmeans_ = KMeans(self.n_clusters, random_state=self.random_state)\n",
+    "        self.kmeans_ = KMeans(self.n_clusters, n_init=10,\n",
+    "                              random_state=self.random_state)\n",
     "        self.kmeans_.fit(X, sample_weight=sample_weight)\n",
     "        return self  # always return self!\n",
     "\n",
@@ -3310,6 +3318,13 @@
     "        return [f\"Cluster {i} similarity\" for i in range(self.n_clusters)]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note: The default value for the `n_init` hyperparameter above will change from 10 to `\"auto\"` in Scikit-Learn 1.4, so I'm setting it explicitly to 10 to keep this notebook stable."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 97,
@@ -6238,7 +6253,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -6252,7 +6267,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.13"
   },
   "nav_menu": {
    "height": "279px",