Apply the fitted train-only scale to the train rows.

highlighted = computed this step

Scale row A with the train fit

Row A scales to 0 because it equals the train-only minimum.

0010=0{0 - 0\over10}=0
Train Only Preprocessing ExactlyExact min-max fit with train rows and full-data contrast.role tablerowrolexAtrain0Btrain10Ctest20fit parametersfitminmaxtrain-only A,B010full-data A,B,C contrast020train-only min-max fit and full-data contrastrowxtrain-only scaledfull-data scaledA000B1011/2C2021test row C changes the full-data fit; contrast onlyfit preprocessing on train rows only; full-data is contrasttest row changes numbers when it enters the fitdoes not claim: NOT leakage guarantee; NOT future performanceNOT accuracy; NOT generalization; NOT calibrated; NOT safeNOT best preprocessing; NOT probability truth

Scale row B with the train fit

Row B scales to 1 because it equals the train-only maximum.

10010=1{10 - 0\over10}=1
Train Only Preprocessing ExactlyExact min-max fit with train rows and full-data contrast.role tablerowrolexAtrain0Btrain10Ctest20fit parametersfitminmaxtrain-only A,B010full-data A,B,C contrast020train-only min-max fit and full-data contrastrowxtrain-only scaledfull-data scaledA000B1011/2C2021test row C changes the full-data fit; contrast onlyfit preprocessing on train rows only; full-data is contrasttest row changes numbers when it enters the fitdoes not claim: NOT leakage guarantee; NOT future performanceNOT accuracy; NOT generalization; NOT calibrated; NOT safeNOT best preprocessing; NOT probability truth

The train rows define the scale

The train-only fit maps A to 0 and B to 1.

A0,B1A\mapsto0,\quad B\mapsto1
Train Only Preprocessing ExactlyExact min-max fit with train rows and full-data contrast.role tablerowrolexAtrain0Btrain10Ctest20fit parametersfitminmaxtrain-only A,B010full-data A,B,C contrast020train-only min-max fit and full-data contrastrowxtrain-only scaledfull-data scaledA000B1011/2C2021test row C changes the full-data fit; contrast onlyfit preprocessing on train rows only; full-data is contrasttest row changes numbers when it enters the fitdoes not claim: NOT leakage guarantee; NOT future performanceNOT accuracy; NOT generalization; NOT calibrated; NOT safeNOT best preprocessing; NOT probability truth