One-Hot Encoding

Encode the Shown Table

The same pinned category order encodes every displayed known-category row.

highlighted = computed this step

Encode all shown rows

Rows A, B, and C use the known colors red, blue, and green. Each row gets an integer indicator pattern.

A,B,C→indicator rowsA,B,C\rightarrow\text{indicator rows}
Categorical Features ExactlyExact one-hot columns from a pinned category list.one-hot columns from pinned category orderrowcolorredbluegreenotherAred1000Bblue0100Cgreen0010category order: red, blue, green; other reservedpreprocessing rewrites category tokens into indicator columnsunknown category uses the pinned other-column policyNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth

Row B turns on blue

Row B has color blue, so blue is 1 while red, green, and other are 0.

Bblue=(0,1,0,0)B_{\text{blue}}=(0,1,0,0)
Categorical Features ExactlyExact one-hot columns from a pinned category list.one-hot columns from pinned category orderrowcolorredbluegreenotherAred1000Bblue0100Cgreen0010category order: red, blue, green; other reservedpreprocessing rewrites category tokens into indicator columnsunknown category uses the pinned other-column policyNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth

Row C turns on green

Row C has color green, so the green column is 1 and the other shown columns are 0.

Cgreen=(0,0,1,0)C_{\text{green}}=(0,0,1,0)
Categorical Features ExactlyExact one-hot columns from a pinned category list.one-hot columns from pinned category orderrowcolorredbluegreenotherAred1000Bblue0100Cgreen0010category order: red, blue, green; other reservedpreprocessing rewrites category tokens into indicator columnsunknown category uses the pinned other-column policyNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth