corelay.processor.clustering

Clustering Processors

Classes

AgglomerativeClustering	Agglomerative clustering
Clustering	Clustering Processor
DBSCAN	DBSCAN clustering
Dendrogram	Dendrogram.
HDBSCAN	HDBSCAN clustering
KMeans	KMeans Clustering

class corelay.processor.clustering.AgglomerativeClustering(*args, **kwargs)

Bases: Clustering

Agglomerative clustering

Parameters:

• n_clusters (int) – Default: 5

• metric (str) – Options: “euclidean”, “l1”, “l2”, “manhattan”, “cosine”, or ‘precomputed’. Default: “euclidean”

• linkage (str) – Options: “ward”, “complete”, “average”, “single”. Default: “ward”

• kwargs (dict) – See also: sklearn.cluster.AgglomerativeClustering

See also

sklearn.cluster.AgglomerativeClustering

function(data)

Abstract function this Processor should apply on input

Parameters:

data (object) – Input data to this Processor.

Raises:

NotImplementedError – Always, since this is an abstract function.

class corelay.processor.clustering.Clustering(*args, **kwargs)

Bases: Processor

Clustering Processor

class corelay.processor.clustering.DBSCAN(*args, **kwargs)

Bases: Clustering

DBSCAN clustering

Parameters:

• metric (str) – Default: euclidean

• eps (float) – Default: 0.5

• min_samples (int) – Default: 5

• kwargs (dict) – See also: sklearn.cluster.DBSCAN

See also

sklearn.cluster.DBSCAN

function(data)

Abstract function this Processor should apply on input

Parameters:

data (object) – Input data to this Processor.

Raises:

NotImplementedError – Always, since this is an abstract function.

class corelay.processor.clustering.Dendrogram(*args, **kwargs)

Bases: Clustering

Dendrogram.

Parameters:

• output_path (str) – Path to where the dendrogram is saved,

• metric (str) – Options: “euclidean”, “l1”, “l2”, “manhattan”, “cosine”, or ‘precomputed’. Default: “euclidean”

• linkage (str) – Options: “ward”, “complete”, “average”, “single”. Default: “ward”

function(data)

Saves Dendrogram by default to /tmp/dendrogram.png and returns the input data.

class corelay.processor.clustering.HDBSCAN(*args, **kwargs)

Bases: Clustering

HDBSCAN clustering

Parameters:

• n_clusters (int) – Default: 2

• metric (str) – Default: euclidean

• kwargs (dict) – See also: hdbscan.HDBSCAN

See also

hdbscan.HDBSCAN

Notes

https://github.com/scikit-learn-contrib/hdbscan

function(data)

Abstract function this Processor should apply on input

Parameters:

data (object) – Input data to this Processor.

Raises:

NotImplementedError – Always, since this is an abstract function.

class corelay.processor.clustering.KMeans(*args, **kwargs)

Bases: Clustering

KMeans Clustering

Parameters:

• n_clusters (int) – Default: 2

• index (tuple) – Default: empty slice

• kwargs (dict) – See also: sklearn.cluster.KMeans

See also

sklearn.cluster.KMeans

function(data)

Abstract function this Processor should apply on input

Parameters:

data (object) – Input data to this Processor.

Raises:

NotImplementedError – Always, since this is an abstract function.