NormalizationBinParametersMixin

Name of the numeric field used to normalize values during binning. The normalization field must be specified when the normalizationType is set to field. Only non-zero values from the normalizationField are used during binning.

The maximum value used to normalize the data during binning. It ensures that all data points are scaled relative to this maximum value.

The minimum value used to normalize the data during binning. It ensures that all data points are scaled relative to this minimum value.

The total value used when the normalizationType is percent-of-total. Percent of total takes each data value, divides it by the normalizationTotal of all values, and then multiplies by 100 to turn it into a percentage.

Normalization type used to normalize data during binning. Some analytical methods require that data be normally distributed. When the data is skewed (the distribution is lopsided) you can transform the data to make it normal.

The following normalization types are supported:

Value	Description
natural-log	Natural logarithmic transformation can be used when the data has a positively skewed distribution and there are a few large values. If these large values are located in the dataset, the log transformation will help make the variances more constant and normalize the data.
log	The logarithmic transformation (base 10) is similar to the natural logarithmic transformation. It is used to reduce skewness, particularly in datasets with large values.
square-root	Square root transformation is similar to a logarithmic transformation in that it reduces right skewness of a dataset. Unlike logarithmic transformations, square root transformations can be applied to zero.
percent-of-total	Percent of total takes each data value, divides it by the normalizationTotal of all values, and then multiplies by 100 to turn it into a percentage. If you don’t provide a normalizationTotal, it will be calculated automatically.
field	Divides the data value by the value from the specified field. You must provide the normalizationField, and values of 0 are filtered out.