verticapy.machine_learning.vertica.preprocessing.StandardScaler.inverse_transform¶

StandardScaler.inverse_transform(vdf: Annotated[str | vDataFrame, ''], X: Annotated[str | list[str], 'STRING representing one column or a list of columns'] | None = None) → vDataFrame¶

Applies the Inverse Model on a vDataFrame.

Parameters¶

vdf: SQLRelation: Input vDataFrame. You can also specify a customized relation, but you must enclose it with an alias. For example: (SELECT 1) x is valid whereas (SELECT 1) and SELECT 1 are invalid.
X: SQLColumns, optional: list of the input vDataColumn.

Returns¶

vDataFrame: object result of the model transformation.

Examples¶

We import verticapy:

import verticapy as vp

For this example, we will use a dummy dataset.

data = vp.vDataFrame(
    {
        "values": [1, 1.01, 1.02, 1.05, 1.024],
    }
)

Let’s import the model:

from verticapy.machine_learning.vertica import Scaler

Then we can create the model:

model = Scaler(method = "zscore")

We can now fit the model:

model.fit(data)


=======
details
=======
column_name|  avg   |std_dev 
-----------+--------+--------
  values   | 1.02080| 0.01879

To get the scaled dataset, we can use the transform method. Let us transform the data:

model.transform(data)

	123 values Float(22)
1	-1.10675880944634
2	-0.57466322798175
3	-0.0425676465171623
4	1.5537190978766
5	0.170270586068673

Rows: 1-5 | Column: values | Type: Float(22)

Similarly, you can perform the inverse transform to get the original features using:

model.inverse_transform(data_transformed)

The variable data_transformed is the scaled dataset.

Important

For this example, a specific model is utilized, and it may not correspond exactly to the model you are working with. To see a comprehensive example specific to your class of interest, please refer to that particular class.