diff --git a/predict-credit-churn/CreditChurn.ipynb b/predict-credit-churn/CreditChurn.ipynb
index 121b21c..eeb399e 100644
--- a/predict-credit-churn/CreditChurn.ipynb
+++ b/predict-credit-churn/CreditChurn.ipynb
@@ -94,18 +94,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "First let's use some built in functions from EvalML to convert the data to a woodwork data structure and then cast its dtypes to something we'd rather work with. Then we're going to take a look at some of the unqiue, non-numeric values in the features. Sure enough, `Education_Level`, `Marital_Status`, and `Income_Category` have `Unknown` as a value. This is something we'll have to remember before we get to the model training, since `Unknown` isn't an acceptable value for any of the features."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from evalml.utils.gen_utils import _convert_to_woodwork_structure, _convert_woodwork_types_wrapper\n",
-    "data = _convert_to_woodwork_structure(data)\n",
-    "data = _convert_woodwork_types_wrapper(data.to_dataframe())"
+    "We're going to take a look at some of the unqiue, non-numeric values in the features. Sure enough, `Education_Level`, `Marital_Status`, and `Income_Category` have `Unknown` as a value. This is something we'll have to remember before we get to the model training, since `Unknown` isn't an acceptable value for any of the features."
    ]
   },
   {
@@ -183,7 +172,7 @@
    "outputs": [],
    "source": [
     "X = data.copy()\n",
-    "data = data.drop(['Credit_Limit'], axis=1)\n",
+    "X = X.drop(['Credit_Limit'], axis=1)\n",
     "y = X.pop('Attrition_Flag')\n",
     "\n",
     "X['Income_Category'] = X['Income_Category'].replace({'Less than $40K':0,\n",
@@ -230,6 +219,25 @@
     "X = preprocessing(X, y)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Using `infer_feature_types`, we can convert our dataset into a [Woodwork](https://github.com/alteryx/woodwork) data structure, and even [specify what types](https://evalml.alteryx.com/en/stable/user_guide/automl.html) certain features should be. For example, we want to cast `Income_Category` as a categorical type, rather than natural language which is what it was inferred as."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from evalml.utils.gen_utils import infer_feature_types\n",
+    "X = infer_feature_types(X, feature_types={'Income_Category': 'categorical',\n",
+    "                                          'Education_Level': 'categorical'})\n",
+    "X"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},