Reduce Dimension

class reduce_dimension.AutoencoderReducer(encoding_dim: int = 10, epochs: int = 50, batch_size: int = 32, optimizer: str = 'adam', loss: str = 'mse', **kwargs: Any)[source]

Dimensionality reduction using Autoencoders.

fit(X: DataFrame, y: Series | None = None) → AutoencoderReducer[source]

Fits the Autoencoder model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the Autoencoder model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the trained Autoencoder.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.FactorAnalysisReducer(n_components: int = 2, **kwargs: Any)[source]

Dimensionality reduction using Factor Analysis.

fit(X: DataFrame, y: Series | None = None) → FactorAnalysisReducer[source]

Fits the Factor Analysis model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the Factor Analysis model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted Factor Analysis model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.IsomapReducer(n_components: int = 2, n_neighbors: int = 5, **kwargs: Any)[source]

Dimensionality reduction using Isomap.

fit(X: DataFrame, y: Series | None = None) → IsomapReducer[source]

Fits the Isomap model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the Isomap model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted Isomap model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.LDAReducer(n_components: int = 2, **kwargs: Any)[source]

Dimensionality reduction using Linear Discriminant Analysis (LDA).

fit(X: DataFrame, y: Series) → LDAReducer[source]

Fits the LDA model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series) – Target variable.

Returns:

self

fit_transform(X: DataFrame, y: Series) → DataFrame[source]

Fits the LDA model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series) – Target variable.

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted LDA model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.PCAReducer(n_components: int = 2, **kwargs: Any)[source]

Dimensionality reduction using Principal Component Analysis (PCA).

fit(X: DataFrame, y: Series | None = None) → PCAReducer[source]

Fits the PCA model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the PCA model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted PCA model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.SVDReducer(n_components: int = 2, **kwargs: Any)[source]

Dimensionality reduction using Truncated Singular Value Decomposition (SVD).

fit(X: DataFrame, y: Series | None = None) → SVDReducer[source]

Fits the SVD model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the SVD model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted SVD model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.TSNEReducer(n_components: int = 2, perplexity: float = 30.0, **kwargs: Any)[source]

Dimensionality reduction using t-Distributed Stochastic Neighbor Embedding (t-SNE).

fit(X: DataFrame, y: Series | None = None) → TSNEReducer[source]

Fits the t-SNE model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the t-SNE model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable (not used).

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted t-SNE model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame

class reduce_dimension.UMAPReducer(n_components: int = 2, **kwargs: Any)[source]

Dimensionality reduction using Uniform Manifold Approximation and Projection (UMAP).

fit(X: DataFrame, y: Series | None = None) → UMAPReducer[source]

Fits the UMAP model to the data.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable.

Returns:

self

fit_transform(X: DataFrame, y: Series | None = None) → DataFrame[source]

Fits the UMAP model and transforms the input DataFrame.

Parameters:

X (pd.DataFrame) – Input DataFrame.
y (pd.Series, optional) – Target variable.

Returns:

Transformed DataFrame.

Return type:

pd.DataFrame

transform(X: DataFrame) → DataFrame[source]

Transforms the input DataFrame using the fitted UMAP model.

Parameters:: X (pd.DataFrame) – Input DataFrame.
Returns:: Transformed DataFrame.
Return type:: pd.DataFrame