binning.py

import pandas as pd


class Binning:
    def __init__(self, data):
        self.rank_data = data.rank(method='first')

    # todo (small reminder) in the original ipd it is NOT equal binning
    # Series of binned points (with dropDuplicates produces not equally frequent bins)
    def equal_frequency_binning(self, dim, bins_count):
        return pd.qcut(self.rank_data.sort_values(by=dim)[dim], bins_count)

    def equal_frequency_binning2(self, dim, bins_count):
        qcut = pd.qcut(self.rank_data.sort_values(by=dim)[dim], bins_count)
        return qcut.cat.rename_categories([i for i in range(bins_count)]).reindex(qcut.index)

    def get_rank_data(self):
        return self.rank_data