henchman.plotting.histogram(col, y=None, n_bins=10, col_max=None, col_min=None, normalized=False, figargs=None)[source]

Creates a histogram. This function takes a single input and creates a histogram from it. There is an optional second column input for labels, if you would like to see how a label is distributed relative to your numeric variable.

  • col (pd.Series) – The column from which to make a histogram.
  • y (pd.Series, optional) – A binary label that you would like to track.
  • n_bins (int) – The number of bins of the histogram. Default is 10.
  • col_max (float) – Maximum value to include in histogram.
  • col_min (float) – Minimum value to include in histogram.
  • normalized (bool) – Whether or not to normalize the columns. Default is False.


If the dataframe X has a column named amount and a label y, you can compare them with

>>> import henchman.plotting as hplot
>>> plot1 = hplot.histogram(X['amount'], y, normalized=False)
>>> hplot.show(plot1)

If you wanted a single variable histogram instead, omit y:

>>> plot2 = hplot.histogram(X['amount'], col_max=200, n_bins=20)
>>> hplot.show(plot2)