pydbm.clustering package

Submodules

pydbm.clustering.deep_embedded_clustering module

class pydbm.clustering.deep_embedded_clustering.DeepEmbeddedClustering

Bases: object

The Deep Embedded Clustering(DEC).

References

  • Aljalbout, E., Golkov, V., Siddiqui, Y., Strobel, M., & Cremers, D. (2018). Clustering with deep learning: Taxonomy and new methods. arXiv preprint arXiv:1801.07648.
  • Guo, X., Gao, L., Liu, X., & Yin, J. (2017, June). Improved Deep Embedded Clustering with Local Structure Preservation. In IJCAI (pp. 1753-1759).
  • Ren, Y., Hu, K., Dai, X., Pan, L., Hoi, S. C., & Xu, Z. (2019). Semi-supervised deep embedded clustering. Neurocomputing, 325, 121-130.
  • Xie, J., Girshick, R., & Farhadi, A. (2016, June). Unsupervised deep embedding for clustering analysis. In International conference on machine learning (pp. 478-487).
  • Zhao, J., Mathieu, M., & LeCun, Y. (2016). Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126.
  • Wagstaff, K., Cardie, C., Rogers, S., & Schrödl, S. (2001, June). Constrained k-means clustering with background knowledge. In Icml (Vol. 1, pp. 577-584).
auto_encodable

getter

back_propagation

Back propagation.

Returns:np.ndarray of delta.
clustering

Clustering.

Parameters:observed_arr – Array like or sparse matrix as the observed data points.
Returns:np.ndarray of labels.
compute_loss

Compute loss.

Parameters:
  • p_arr – np.ndarray of result of soft assignment.
  • q_arr – np.ndarray of target distribution.
  • target_arr – np.ndarray of labeled data.
Returns:

(loss, np.ndarray of delta)
compute_pairwise_constraint
compute_target_distribution

Compute target distribution.

Parameters:q_arr – np.ndarray of result of soft assignment.
Returns:np.ndarray of target distribution.
forward_propagation

Embed and extract feature points and do soft assignment.

Parameters:observed_arr – np.ndarray of observed data points.
Returns:np.ndarray of result of soft assignment.
get_auto_encodable

getter

get_loss_arr

getter

get_mu_arr

getter for learned centroids.

get_opt_params

getter

inference

Inference the feature points to reconstruct the time-series.

Override.

Parameters:observed_arr – Array like or sparse matrix as the observed data points.
Returns:Predicted array like or sparse matrix.
learn

Learn.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • target_arr – np.ndarray of noised observed data points.
loss_arr

getter

mu_arr

getter for learned centroids.

opt_params

getter

optimize

Optimize.

Parameters:
  • learning_rate – Learning rate.
  • epoch – Now epoch.
set_auto_encodable

setter

set_loss_arr

setter

set_mu_arr

setter for learned centroids.

set_opt_params

setter

pydbm.clustering.reconstruction_classification_networks module

class pydbm.clustering.reconstruction_classification_networks.ReconstructionClassificationNetworks

Bases: object

The Deep Reconstruction-Classification Networks.

References

  • Ghifary, M., Kleijn, W. B., Zhang, M., Balduzzi, D., & Li, W. (2016, October). Deep reconstruction-classification networks for unsupervised domain adaptation. In European Conference on Computer Vision (pp. 597-613). Springer, Cham.
auto_encodable

getter

back_propagation

Back propagation.

Returns:np.ndarray of delta.
clf_loss_arr

getter

compute_loss

Compute loss.

Parameters:
  • inferneced_arr – np.ndarray of result of softmax output layer.
  • target_arr – np.ndarray of labeled data.
Returns:

(loss, np.ndarray of delta)
forward_propagation

Embed and extract feature points and do soft assignment.

Parameters:observed_arr – np.ndarray of observed data points.
Returns:np.ndarray of result of soft assignment.
get_auto_encodable

getter

get_clf_loss_arr

getter

get_loss_arr

getter

get_nn

getter

get_rec_loss_arr

getter

inference

Inference the feature points to reconstruct the time-series.

Override.

Parameters:observed_arr – Array like or sparse matrix as the observed data points.
Returns:Predicted array like or sparse matrix.
learn

Learn.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • target_arr – np.ndarray of noised observed data points.
loss_arr

getter

nn

getter

optimize

Optimize.

Parameters:
  • learning_rate – Learning rate.
  • epoch – Now epoch.
rec_loss_arr

getter

set_auto_encodable

setter

set_clf_loss_arr

setter

set_loss_arr

setter

set_nn

setter

set_rec_loss_arr

setter

pydbm.clustering.sklearn_kmeans module

class pydbm.clustering.sklearn_kmeans.SklearnKMeans

Bases: pydbm.clustering.interface.extractable_centroids.ExtractableCentroids

K-Means method.

The function of this class is only to get information on centroids to be mentioned as initial parameters in framework of the Deep Embedded Clustering(DEC).

References

extract_centroids

Clustering and extract centroids.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • k – The number of clusters.
Returns:

np.ndarray of centroids.

Module contents