deepmol.scalers package

Submodules

deepmol.scalers.base_scaler module

class BaseScaler(scaler, columns: list | None = None)

Bases: ABC, Transformer

Abstract class for all scalers. It is used to define the interface for all scalers.

load(file_path: str) → BaseScaler

Loads the scaler object from a file.

file_path: str

The path to the file where the scaler object is saved.

Returns:

The scaler object.

Return type:

object

save(file_path: str) → None

Saves the scaler object to a file.

file_path: str

The path to the file where the scaler object will be saved.

scale(other_object, inplace=False, **kwargs)

Method that modifies an input object inplace or on a copy.

Parameters:

• self (object) – The class instance object.

• other_object (object) – The object to apply the method to.

• inplace (bool) – Whether to apply the method in place.

• kwargs (dict) – Keyword arguments to pass to the method.

Returns:

new_object – The new object.

Return type:

object

property scaler_object

Returns the scaler object.

Returns:

The scaler object.

Return type:

object

deepmol.scalers.sklearn_scalers module

class Binarizer(threshold: float = 0.0, copy: bool = True, columns: list | None = None)

Bases: BaseScaler

Binarize data (set feature values to 0 or 1) according to a threshold.

class KernelCenterer(columns: list | None = None)

Bases: BaseScaler

Center a kernel matrix.

class MaxAbsScaler(copy: bool = True, columns: list | None = None)

Bases: BaseScaler

Scale each feature by its maximum absolute value.

class MinMaxScaler(feature_range: Tuple[int, int] = (0, 1), copy: bool = True, clip: bool = False, columns: list | None = None)

Bases: BaseScaler

Transform features by scaling each feature to a given range.

class Normalizer(norm: str = 'l2', copy: bool = True, columns: list | None = None)

Bases: BaseScaler

Normalize samples individually to unit norm.

class PolynomialFeatures(degree: int = 2, interaction_only: bool = False, include_bias: bool = True, order: str = 'C', columns: list | None = None)

Bases: BaseScaler

Generate polynomial and interaction features.

class PowerTransformer(method: str = 'yeo-johnson', standardize: bool = True, copy: bool = True, columns: list | None = None)

Bases: BaseScaler

Apply a power transform featurewise to make data more Gaussian-like.

class QuantileTransformer(n_quantiles: int = 1000, output_distribution: str = 'uniform', ignore_implicit_zeros: bool = False, subsample: int = 100000, random_state: int | None = None, copy: bool = True, columns: list | None = None)

Bases: BaseScaler

Transform features using quantiles information.

class RobustScaler(with_centering: bool = True, with_scaling: bool = True, quantile_range: Tuple[float, float] = (25.0, 75.0), copy: bool = True, unit_variance: bool = False, columns: list | None = None)

Bases: BaseScaler

Scale features using statistics that are robust to outliers.

class StandardScaler(copy: bool = True, with_mean: bool = True, with_std: bool = True, columns: list | None = None)

Bases: BaseScaler

Standardize features by removing the mean and scaling to unit variance.

Module contents