Work with teradatamlspk StandardScaler Function - Work with teradatamlspk StandardScaler Function - Teradata VantageCloud Lake

>>> from teradatamlspk.ml.feature import StandardScaler

>>> from teradatamlspk.sql.functions import monotonically_increasing_id

>>> df = df.select(monotonically_increasing_id().alias('id'), "feature1", "feature2", "feature3")
>>> df.show()
+--+--------+--------+--------+
|id|feature1|feature2|feature3|
+--+--------+--------+--------+
| 3|     3.0|    10.1|     3.0|
| 2|     2.0|     1.1|     1.0|
| 1|     1.0|     0.1|    -1.0|
+--+--------+--------+--------+

>>> scaler = StandardScaler(inputCol=["feature2", "feature3"], withMean=True)

>>> scaled_df = scaler.fit(df).transform(df)

+--+--------+------------------+--------+
|id|feature1|          feature2|feature3|
+--+--------+------------------+--------+
| 3|     3.0| 6.333333333333332|     2.0|
| 2|     2.0|-2.666666666666667|     0.0|
| 1|     1.0|-3.666666666666667|    -2.0|
+--+--------+------------------+--------+