Extracting features from dates with pandas
datetime
variables can take dates, time, or dates and time as values. They are not used in their raw format to build machine learning algorithms. Instead, we create additional features from them, and we can enrich the dataset dramatically by extracting information from the date and time.
The pandas
Python library contains a lot of capabilities for working with dates and time. pandas dt
is the accessor
object to the datetime
properties of a pandas Series. To access the pandas dt
functionality, the variables should be cast in a data type that supports these operations, such as datetime
or timedelta
.
Tip
Often, the datetime
variables are cast as objects, particularly when the data is loaded from a CSV file. Therefore, to extract the date and time features that we will discuss throughout this chapter, it is necessary to recast the variables as datetime
.
In this recipe, we will learn how to extract features from dates by utilizing pandas...