Notice: This page requires JavaScript to function properly.
Please enable JavaScript in your browser settings or update your browser.
What Will We Do With the NaN Values? | Preprocessing Data
Advanced Techniques in pandas

Course Content

Advanced Techniques in pandas

# What Will We Do With the NaN Values?

In the previous chapter, you received the result:

 PassengerId 0 Survived 0 Pclass 0 Name 0 Sex 0 Age 86 SibSp 0 Parch 0 Ticket 0 Fare 1 Cabin 327 Embarked 0

The dataset has 418 rows. Look at the column `Cabin`, where we have `327` missing values. There is no sense filling them in because we have minimal information here. So, in this case, the best solution is to delete the column that is senseless to us. One of the reasons is that we can delete only the rows that contain missing values, but we can't delete 327 rows out of 418. So, let's figure out how to do this.

To delete a column, you must apply the function `.drop()` to the data set. The syntax is the following:

Explanation:

• `.drop()` - a function that deletes columns;
• `columns = 'column_name'` or `columns = ['column_1', 'column_2']` - argument of the function, where you specify the name or names of columns that you want to delete;
• `inplace = True` - useful argument of pandas that allows us to save all changes. You can use it in other functions too; we will learn some of them later on.

Your task is to delete the column with the greatest number of NaN values. Follow the algorithm:

1. Drop the column `'Cabin'` using the `inplace = True` argument.
2. Output the random `5` rows of the data set.

Everything was clear?

Section 5. Chapter 3

# What Will We Do With the NaN Values?

In the previous chapter, you received the result:

 PassengerId 0 Survived 0 Pclass 0 Name 0 Sex 0 Age 86 SibSp 0 Parch 0 Ticket 0 Fare 1 Cabin 327 Embarked 0

The dataset has 418 rows. Look at the column `Cabin`, where we have `327` missing values. There is no sense filling them in because we have minimal information here. So, in this case, the best solution is to delete the column that is senseless to us. One of the reasons is that we can delete only the rows that contain missing values, but we can't delete 327 rows out of 418. So, let's figure out how to do this.

To delete a column, you must apply the function `.drop()` to the data set. The syntax is the following:

Explanation:

• `.drop()` - a function that deletes columns;
• `columns = 'column_name'` or `columns = ['column_1', 'column_2']` - argument of the function, where you specify the name or names of columns that you want to delete;
• `inplace = True` - useful argument of pandas that allows us to save all changes. You can use it in other functions too; we will learn some of them later on.

1. Drop the column `'Cabin'` using the `inplace = True` argument.
2. Output the random `5` rows of the data set.