Table of Contents

Topic: Dealing with Missing Data in Python

Recall:

  1. How do you detect missing values? **
  2. How do you replace missing values? *
  3. Which package can you use to visualise missingness? ***
  4. How do you remove missing values? ***
  5. How do you impute missing values?
  6. What are the common imputation methods? ***
  7. How do you fill missing data in time series? **
  8. How do you impute categorical values?
  9. What are one-hot encoding and ordinal encoding? *

Notes:

1. Null value operations

While working with missing data, you'll have to store these missing values as an empty type. This way, you will easily be able to identify them, replace them or play with them! This is why we have the None and numpy.nan types. You need to be able to differentiate clearly between the two types.

None is of type NoneType while np.nan is of float. This allows np.nan to have both arithmetic and logical operations