Let's begin with a code that will help to select the top 10 features with the most predictive power to find the best class for an observation in our forest DataFrame:

vectorAssembler = feat.VectorAssembler(
    inputCols=forest.columns[0:-1]
    , outputCol='features'
)

selector = feat.ChiSqSelector(
    labelCol='CoverType'
    , numTopFeatures=10
    , outputCol='selected')

pipeline_sel = Pipeline(stages=[vectorAssembler, selector])