How to Scale Data With Outliers

Question 1

WHAT’S ROBUST SCALING FORMULA? P248

Answer 1

value = (value – median) / (p75 − p25)

Question 2

WHAT IS THE MEAN AND STD OF INPUT VARIABLES AFTER ROBUST SCALING? P248

Answer 2

The resulting variable has a near-zero mean and zero median and a standard deviation of nearly 1. (based on Listing 18.7 on P252)

Question 3

WHAT ARE THE PARAMETERS OF ROBUSTSCALER IN SCIKIT-LEARN? WHAT’S THEIR DEFAULT VALUE? P249

Answer 3

with_centering argument (default:True) controls whether the value is centered to zero (median is subtracted)
with_scaling argument (default: True): scale the data to interquartile range
The quantile_range, It takes a tuple of two integers between 0 and 100 and defaults to the percentile values of the IQR, specifically (25, 75).
unit_variance, (default:False): If True, scale data so that normally distributed features have a variance of 1.