Scikit-Learn Decomposition Methods
The following Scikit-Learn module types are matrix factorization and dimensionality reduction methods.
Modules
- FactorAnalysis
- FastICA
- IncrementalPCA
- KernelPCA
- LatentDirichletAllocation
- MiniBatchNMF
- MiniBatchSparsePCA
- NMF
- PCA
- SparseCoder
- SparsePCA
- TruncatedSVD
FactorAnalysis
Scikit-Learn module documentation: FactorAnalysis
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of latent components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Convergence tolerance | --skl_tol | Float ≥ 0 | None | tol |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
FastICA
Scikit-Learn module documentation: FastICA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of independent components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Convergence tolerance | --skl_tol | Float ≥ 0 | None | tol |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
IncrementalPCA
Scikit-Learn module documentation: IncrementalPCA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of principal components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Number of samples per mini-batch | --skl_batch_size | Integer ≥ 1 | None | batch_size |
KernelPCA
Scikit-Learn module documentation: KernelPCA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of CPU cores to use | --cpus_per_task | Integer ≥ 1 | None | n_jobs |
| Number of principal components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Kernel function | --skl_kernel | linear | poly | rbf | sigmoid | cosine | precomputed | None | kernel |
| Kernel coefficient | --skl_gamma | scale | auto | numeric string | None | gamma |
| Degree of polynomial kernel | --skl_poly_degree | Integer ≥ 1 | None | degree |
| Independent term in kernel function | --skl_coef0 | Float | None | coef0 |
| Maximum number of iterations for eigenvalue solver | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
LatentDirichletAllocation
Scikit-Learn module documentation: LatentDirichletAllocation
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of CPU cores to use | --cpus_per_task | Integer ≥ 1 | None | n_jobs |
| Number of topics | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Number of documents per mini-batch | --skl_batch_size | Integer ≥ 1 | None | batch_size |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
MiniBatchNMF
Scikit-Learn module documentation: MiniBatchNMF
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Convergence tolerance | --skl_tol | Float ≥ 0 | None | tol |
| Number of samples per mini-batch | --skl_batch_size | Integer ≥ 1 | None | batch_size |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
MiniBatchSparsePCA
Scikit-Learn module documentation: MiniBatchSparsePCA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of CPU cores to use | --cpus_per_task | Integer ≥ 1 | None | n_jobs |
| Number of sparse components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Number of samples per mini-batch | --skl_batch_size | Integer ≥ 1 | None | batch_size |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
NMF
Scikit-Learn module documentation: NMF
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Convergence tolerance | --skl_tol | Float ≥ 0 | None | tol |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
PCA
Scikit-Learn module documentation: PCA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of principal components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
SparseCoder
Scikit-Learn module documentation: SparseCoder
Note: SparseCoder requires a dictionary array that must be provided externally and cannot be configured via CLI arguments.
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of CPU cores to use | --cpus_per_task | Integer ≥ 1 | None | n_jobs |
SparsePCA
Scikit-Learn module documentation: SparsePCA
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of CPU cores to use | --cpus_per_task | Integer ≥ 1 | None | n_jobs |
| Number of sparse components | --skl_n_components | Integer ≥ 1 | None | n_components |
| Maximum number of iterations | --skl_max_iter | Integer ≥ 1 | None | max_iter |
| Convergence tolerance | --skl_tol | Float ≥ 0 | None | tol |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |
TruncatedSVD
Scikit-Learn module documentation: TruncatedSVD
Arguments
| Description | Zero2Neuro Argument | Possible Values | Default Value | Scikit-Learn Parameter |
|---|---|---|---|---|
| Number of singular values to compute | --skl_n_components | Integer ≥ 1 | None | n_components |
| Random seed for reproducibility | --skl_random_state | Integer | None | random_state |