Merge pull request #2316 from jperk224:patch-1

PiperOrigin-RevId: 684927870

site/en/tutorials/keras/regression.ipynb

@@ -252,6 +252,8 @@
       "source": [
         "The `\"Origin\"` column is categorical, not numeric. So the next step is to one-hot encode the values in the column with [pd.get_dummies](https://pandas.pydata.org/docs/reference/api/pandas.get_dummies.html).\n",
         "\n",
+        "Neglecting to specify a data type by way of a `dtype` argument will leave you with boolean values, causing errors during normalization when instantiating the Tensor object if the feature values are not cast to a uniform type when passing the array into `tf.keras.layers.Normalization.adapt()`.  [Tensor objects](https://www.tensorflow.org/guide/tensor) must house uniform data types.\n",
+        "\n",
         "Note: You can set up the `tf.keras.Model` to do this kind of transformation for you but that's beyond the scope of this tutorial. Check out the [Classify structured data using Keras preprocessing layers](../structured_data/preprocessing_layers.ipynb) or [Load CSV data](../load_data/csv.ipynb) tutorials for examples."
       ]
     },
@@ -274,7 +276,7 @@
       },
       "outputs": [],
       "source": [
-        "dataset = pd.get_dummies(dataset, columns=['Origin'], prefix='', prefix_sep='')\n",
+        "dataset = pd.get_dummies(dataset, columns=['Origin'], prefix='', prefix_sep='', dtype=float)\n",
         "dataset.tail()"
       ]
     },