Let’s say a dataset contains categorical values in a column and there are some missing categorical values. So, we need to handle missing categorical values. There are two ways of handling missing categorical values using the pandas Python library. We can do mode imputation or “missing” value imputation. Let’s try to understand them in detail.

In the case of mode imputation, the missing values in a column are replaced with the most frequent non-null value appearing in the column. Let’s look at an example.

Let’s read the titanic dataset and see the missing values appearing in each column.

import pandas

df = pandas.read_csv("titanic.csv")
print(df.head())

The output is like the following:

  survived  pclass     sex   age  ...  deck  embark_town  alive  alone
0         0       3    male  22.0  ...   NaN  Southampton     no  False
1         1       1  female  38.0  ...     C    Cherbourg    yes  False
2         1       3  female  26.0  ...   NaN  Southampton    yes   True
3         1       1  female  35.0  ...     C  Southampton    yes  False
4         0       3    male  35.0  ...   NaN  Southampton     no   True

[5 rows x 15 columns]

So, the dataset has 15 columns. Out of them, we can see the embark_town column contains categorical values. So, let’s create …