Genetic encoders
This file contains the class definition for all the genetic encoders. All the genetic encoder classes inherit the Scikit learn BaseEstimator and TransformerMixin classes to follow the Scikit learn paradigm.
DominantEncoder
¶
Bases: BaseEstimator
, TransformerMixin
This class contains the function definition for encoding the input features as a Dominant genetic model. The encoding used is AA(0)->1, Aa(1)->1, aa(2)->0.
Source code in tpot2/builtin_modules/genetic_encoders.py
fit(X, y=None)
¶
Do nothing and return the estimator unchanged. Dummy function to fit in with the sklearn API and hence work in pipelines.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
array - like
|
|
required |
transform(X, y=None)
¶
Transform the data by applying the Dominant encoding.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
numpy ndarray, {n_samples, n_components}
|
New data, where n_samples is the number of samples (number of individuals) and n_components is the number of components (number of features). |
required |
y |
None
|
Unused |
None
|
Returns:
Name | Type | Description |
---|---|---|
X_transformed |
numpy ndarray, {n_samples, n_components}
|
The encoded feature set |
Source code in tpot2/builtin_modules/genetic_encoders.py
HeterosisEncoder
¶
Bases: BaseEstimator
, TransformerMixin
This class contains the function definition for encoding the input features as a Heterozygote Advantage genetic model. The encoding used is AA(0)->0, Aa(1)->1, aa(2)->0.
Source code in tpot2/builtin_modules/genetic_encoders.py
fit(X, y=None)
¶
Do nothing and return the estimator unchanged. Dummy function to fit in with the sklearn API and hence work in pipelines.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
array - like
|
|
required |
transform(X, y=None)
¶
Transform the data by applying the Heterosis encoding.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
numpy ndarray, {n_samples, n_components}
|
New data, where n_samples is the number of samples (number of individuals) and n_components is the number of components (number of features). |
required |
y |
None
|
Unused |
None
|
Returns:
Name | Type | Description |
---|---|---|
X_transformed |
numpy ndarray, {n_samples, n_components}
|
The encoded feature set |
Source code in tpot2/builtin_modules/genetic_encoders.py
OverDominanceEncoder
¶
Bases: BaseEstimator
, TransformerMixin
This class contains the function definition for encoding the input features as a Over Dominance genetic model. The encoding used is AA(0)->1, Aa(1)->2, aa(2)->0.
Source code in tpot2/builtin_modules/genetic_encoders.py
fit(X, y=None)
¶
Do nothing and return the estimator unchanged. Dummy function to fit in with the sklearn API and hence work in pipelines.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
array - like
|
|
required |
transform(X, y=None)
¶
Transform the data by applying the Heterosis encoding.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
numpy ndarray, {n_samples, n_components}
|
New data, where n_samples is the number of samples (number of individuals) and n_components is the number of components (number of features). |
required |
y |
None
|
Unused |
None
|
Returns:
Name | Type | Description |
---|---|---|
X_transformed |
numpy ndarray, {n_samples, n_components}
|
The encoded feature set |
Source code in tpot2/builtin_modules/genetic_encoders.py
RecessiveEncoder
¶
Bases: BaseEstimator
, TransformerMixin
This class contains the function definition for encoding the input features as a Recessive genetic model. The encoding used is AA(0)->0, Aa(1)->1, aa(2)->1.
Source code in tpot2/builtin_modules/genetic_encoders.py
fit(X, y=None)
¶
Do nothing and return the estimator unchanged. Dummy function to fit in with the sklearn API and hence work in pipelines.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
array - like
|
|
required |
transform(X, y=None)
¶
Transform the data by applying the Recessive encoding.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
numpy ndarray, {n_samples, n_components}
|
New data, where n_samples is the number of samples (number of individuals) and n_components is the number of components (number of features). |
required |
y |
None
|
Unused |
None
|
Returns:
Name | Type | Description |
---|---|---|
X_transformed |
numpy ndarray, {n_samples, n_components}
|
The encoded feature set |
Source code in tpot2/builtin_modules/genetic_encoders.py
UnderDominanceEncoder
¶
Bases: BaseEstimator
, TransformerMixin
This class contains the function definition for encoding the input features as a Under Dominance genetic model. The encoding used is AA(0)->2, Aa(1)->0, aa(2)->1.
Source code in tpot2/builtin_modules/genetic_encoders.py
fit(X, y=None)
¶
Do nothing and return the estimator unchanged. Dummy function to fit in with the sklearn API and hence work in pipelines.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
array - like
|
|
required |
transform(X, y=None)
¶
Transform the data by applying the Heterosis encoding.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
X |
numpy ndarray, {n_samples, n_components}
|
New data, where n_samples is the number of samples (number of individuals) and n_components is the number of components (number of features). |
required |
y |
None
|
Unused |
None
|
Returns:
Name | Type | Description |
---|---|---|
X_transformed |
numpy ndarray, {n_samples, n_components}
|
The encoded feature set |