diff --git a/ml2/3_3_Data_Munging_with_Pandas.ipynb b/ml2/3_3_Data_Munging_with_Pandas.ipynb
index 1ecd01d..99347bc 100644
--- a/ml2/3_3_Data_Munging_with_Pandas.ipynb
+++ b/ml2/3_3_Data_Munging_with_Pandas.ipynb
@@ -451,7 +451,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Pivot tables are an intuitive way to analyze data, and alternative to group columns."
+    "Pivot tables are an intuitive way to analyze data, and an alternative to group columns.\n",
+    "\n",
+    "This command makes a table with rows Sex and columns Pclass, and\n",
+    "averages the result of the column Survived, thereby giving the percentage of survivors in each grouping."
    ]
   },
   {
@@ -460,7 +463,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pd.pivot_table(df, index='Sex')"
+    "pd.pivot_table(df, index='Sex', columns='Pclass', values=['Survived'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we want to analyze multi-index, the percentage of survivoers, given sex and age, and distributed by Pclass."
    ]
   },
   {
@@ -469,7 +479,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pd.pivot_table(df, index=['Sex', 'Pclass'])"
+    "pd.pivot_table(df, index=['Sex', 'Age'], columns=['Pclass'], values=['Survived'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Nevertheless, this is not very useful since we have a row per age. Thus, we define a partition."
    ]
   },
   {
@@ -478,7 +495,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pd.pivot_table(df, index=['Sex', 'Pclass'], values=['Age', 'SibSp'])"
+    "# Partition each of the passengers into 3 categories based on their age\n",
+    "age = pd.cut(df['Age'], [0,12,18,80])"
    ]
   },
   {
@@ -487,7 +505,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pd.pivot_table(df, index=['Sex', 'Pclass'], values=['Age', 'SibSp'], aggfunc=np.mean)"
+    "pd.pivot_table(df, index=['Sex', age], columns=['Pclass'], values=['Survived'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can change the function used for aggregating each group."
    ]
   },
   {
@@ -496,8 +521,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Try np.sum, np.size, len\n",
-    "pd.pivot_table(df, index=['Sex', 'Pclass'], values=['Age', 'SibSp'], aggfunc=[np.mean, np.sum])"
+    "# default\n",
+    "pd.pivot_table(df, index=['Sex', age], columns=['Pclass'], values=['Survived'], aggfunc=np.mean)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Two agg functions\n",
+    "pd.pivot_table(df, index=['Sex', age], columns=['Pclass'], values=['Survived'], aggfunc=[np.mean, np.sum])"
    ]
   },
   {
@@ -972,7 +1007,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.11.5"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,