BPt.Dataset.k_bin

Dataset.k_bin(scope, n_bins=5, strategy='uniform', inplace=False)

This method is used to apply k binning to a column, or columns. On the backend this function used the scikit-learn KBinsDiscretizer.

Parameters

scopeScope

A BPt style Scope used to select a subset of column(s) in which to apply the current function to. See Scope for more information on how this can be applied.

n_binsint, optional

The number of bins to discretize the passed columns to. This same value is applied for all columns within scope.

default = 5

strategy‘uniform’, ‘quantile’ or ‘kmeans’, optional

The strategy in which the binning should be adhere to. Options are:

• ‘uniform’

  All bins in each feature have identical widths.

• ‘quantile’

  All bins in each feature have the same number of points.

• ‘kmeans’

  Values in each bin have the same nearest center of a 1D k-means cluster.

default = 'uniform'

inplacebool, optional

If True, perform the current function inplace and return None.

default = False

Examples

import BPt as bp
data = bp.Dataset([.1, .2, .3, .4, .5, .6, .7, .8, .9],
                  columns=['feat'])

# Apply k_bin, not in place, then plot
data.k_bin('feat', n_bins=3, strategy='uniform').plot('feat')

# Apply with dif params
data.k_bin('feat', n_bins=5, strategy='quantile').plot('feat')