we saw that it is possible to replace or impute missing data based on simple population statistics such as the mean, median or mode of the targeted feature. When a friend of yours hears that you are imputing the Age column by simply taking the mean or median of the non-missing data, she decides to show-off the following code which produces two telling plots plt.figure(figsize-(15,5)) plt.subplot (1, 2, 1) sns.boxenplot(train_df['Pclass'], train_df['Age'], hue-train_df[ 'Survived']) plt.subplot (1, 2, 2) sns.boxenplot (train_df [ 'Sex'], train_df[ 'Age'], hue-train_df[ 'Survived']) plt.show() 80 60 Survived 0 1 80 60 40 WWW Survived 0 1