Clarify missing height correlation example

1-Introduction/04-stats-and-probability/notebook.ipynb

@@ -487,18 +487,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "np.corrcoef(df['Height'].ffill(),df['Weight'])"
+    "np.corrcoef(df['Height'], df['Weight'])"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Unfortunately, we did not get any results - only some strange `nan` values. This is due to the fact that some of the values in our series are undefined, represented as `nan`, which causes the result of the operation to be undefined as well. By looking at the matrix we can see that `Weight` is the problematic column, because self-correlation between `Height` values has been computed.\n",
+    "Unfortunately, we did not get a correlation result—only `nan` values involving `Height`. This happens because `Height` contains a missing value, represented as `nan`, so calculations that use that column are also undefined. The `1` in the bottom-right of the matrix is the self-correlation of `Weight`, which has no missing values.\n",
     "\n",
     "> This example shows the importance of **data preparation** and **cleaning**. Without proper data we cannot compute anything.\n",
     "\n",
-    "Let's use `fillna` method to fill the missing values, and compute the correlation: "
+    "For this example, let's use `ffill` to replace the missing `Height` with the previous valid height, and then compute the correlation:"
    ]
   },
   {