Our features are attributes that describe the flag, and some of them might not be in the right format. In this section, we will take a look at each feature and transform it if necessary.
In order to keep track of which features we have already processed, let's start defining an empty vector namesProcessed
, which contains the features that we have already processed. When we transform a feature, we add the feature name into namesProcessed
:
namesProcessed <- c()
Let's start with the numeric columns, such as red
, which have two possible outcomes: 0
, in case the flag contains red and 1
otherwise. The red
variable defines an attribute, so it should be categorical instead of numeric. Then, we can convert red
into a feature that is yes
if the color is red and no
otherwise.
If we take a look at the charts of each feature, we notice that some of them display only two values that are always 0
and 1
. In order to convert each of them into the yes
and no
format, we can use a for
...