Contents

This Page

  1. Docs
  2. actableai.clustering.models package

actableai.clustering.models package

Submodules

actableai.clustering.models.affinity_propagation module

class actableai.clustering.models.affinity_propagation.AffinityPropagation(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapper

Class to handle Affinity Propagation.

Parameters
models (Base class for all clustering) –
static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.

actableai.clustering.models.agglomerative_clustering module

class actableai.clustering.models.agglomerative_clustering.AgglomerativeClustering(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapperNoFit

Class to handle Agglomerative Clustering.

Parameters
models (Base class for all clustering) –
static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.

actableai.clustering.models.base module

class actableai.clustering.models.base.BaseClusteringModel(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.models.base.AAIParametersModel[numpy.ndarray, numpy.ndarray], abc.ABC

TODO write documentation

abstract static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.
handle_categorical = False
has_fit: bool = True
has_predict: bool = True
project(data: numpy.ndarray) → numpy.ndarray
class actableai.clustering.models.base.ClusteringModelWrapper(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.BaseClusteringModel, abc.ABC

initialize_model()
class actableai.clustering.models.base.ClusteringModelWrapperNoFit(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapper, abc.ABC

class actableai.clustering.models.base.Model(value)

Bases: str, enum.Enum

Enum representing the different model available.

affinity_propagation = 'affinity_propagation'
agglomerative_clustering = 'agglomerative_clustering'
dbscan = 'dbscan'
dec = 'dec'
kmeans = 'kmeans'
spectral_clustering = 'spectral_clustering'

actableai.clustering.models.dbscan module

class actableai.clustering.models.dbscan.DBSCAN(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapperNoFit

Class to handle DBSCAN.

Parameters
models (Base class for all clustering) –
static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.

actableai.clustering.models.dec module

class actableai.clustering.models.dec.ClusteringLayer(*args, **kwargs)

Bases: keras.engine.base_layer.Layer

Clustering layer converts input sample (feature) to soft label, i.e. a vector that represents the probability of the sample belonging to each cluster. The probability is calculated with student’s t-distribution.

Example

model.add(ClusteringLayer(n_clusters=10))

Input shape:
2D tensor with shape: (n_samples, n_features).
Output shape:
2D tensor with shape: (n_samples, n_clusters).
build(input_shape)

Creates the variables of the layer (optional, for subclass implementers).

This is a method that implementers of subclasses of Layer or Model can override if they need a state-creation step in-between layer instantiation and layer call. It is invoked automatically before the first execution of call().

This is typically used to create the weights of Layer subclasses (at the discretion of the subclass implementer).

Parameters
input_shape – Instance of TensorShape, or list of instances of TensorShape if the layer expects a list of inputs (one instance per input).
call(inputs, **kwargs)
student t-distribution, as same as used in t-SNE algorithm.
q_ij = 1/(1+dist(x_i, u_j)^2), then normalize it.
Parameters
inputs – the variable containing data, shape=(n_samples, n_features)
Returns
student’s t-distribution, or soft labels for each sample. shape=(n_samples, n_clusters)
Return type
q
compute_output_shape(input_shape)

Computes the output shape of the layer.

This method will cause the layer’s state to be built, if that has not happened before. This requires that the layer will later be used with inputs that match the input shape provided here.

Parameters
input_shape – Shape tuple (tuple of integers) or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns
An input shape tuple.
classmethod from_config(config)

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Parameters
config – A Python dictionary, typically the output of get_config.
Returns
A layer instance.
get_config()

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Note that get_config() does not guarantee to return a fresh copy of dict every time it is called. The callers should make a copy of the returned dict if they want to modify it.

Returns
Python dictionary.
class actableai.clustering.models.dec.DEC(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: bool = 1)

Bases: actableai.clustering.models.base.BaseClusteringModel

TODO write documentation

static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.
handle_categorical = True
has_explanations: bool = True

actableai.clustering.models.kmeans module

class actableai.clustering.models.kmeans.KMeans(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapper

Class to handle K-Means clustering.

Parameters
models (Base class for all clustering) –
classmethod KMeans_pick_k(scaled_data, alpha_k, k_range, *KMeans_args, **KMeans_kwargs) → sklearn.cluster._kmeans.KMeans
Find best k for KMeans based on scaled inertia method.
https://towardsdatascience.com/an-approach-for-choosing-number-of-clusters-for-k-means-c28e614ecb2c
Parameters
  • scaled_data – matrix scaled data. rows are samples and columns are features for clustering.
  • alpha_k – manually tuned factor that gives penalty to the number of clusters.
  • k_range – range of k values to test.
Returns

The value of the best k.

Return type

best_k

static KMeans_pick_k_sil(X, k_range, *KMeans_args, **KMeans_kwargs)
Find best k for KMeans based on silhouette score.
https://newbedev.com/scikit-learn-k-means-elbow-criterion
Parameters
  • X – matrix of data. rows are samples and columns are features for clustering.
  • k_range – range of k values to test.
Returns

The value of the best k.

Return type

best_k

static KMeans_scaled_inertia(scaled_data: numpy.ndarray, k: int, alpha_k: float, *KMeans_args, **KMeans_kwargs)

KMeans with scaled inertia.

Parameters
  • scaled_data – matrix scaled data. rows are samples and columns are features for clustering.
  • k – current k for applying KMeans.
  • alpha_k – manually tuned factor that gives penalty to the number of clusters.
Returns

scaled inertia value for current k

Return type

float

classmethod find_num_clusters(data: numpy.ndarray, k_select_method: str, auto_num_clusters_min: int, auto_num_clusters_max: int, alpha_k: float = 0.01) → int
static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.

actableai.clustering.models.spectral_clustering module

class actableai.clustering.models.spectral_clustering.SpectralClustering(input_size: int, num_clusters: int, df_training: pandas.core.frame.DataFrame, parameters: Optional[Dict[str, Any]] = None, process_parameters: bool = True, verbosity: int = 1)

Bases: actableai.clustering.models.base.ClusteringModelWrapperNoFit

Class to handle Spectral Clustering.

Parameters
models (Base class for all clustering) –
static get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.

Module contents

class actableai.clustering.models.ClusteringModel(parameters: Optional[Dict[str, Any]] = None)

Bases: actableai.models.base.AAIParametersModel[pandas.core.frame.DataFrame, pandas.core.frame.DataFrame], abc.ABC

get_parameters() → actableai.parameters.parameters.Parameters

Returns the parameters of the model.

Returns
The parameters.
has_fit: bool = True
has_predict: bool = True
project(data: Union[numpy.ndarray, pandas.core.frame.DataFrame]) → numpy.ndarray
class actableai.clustering.models.ClusteringModelInference(model: actableai.models.inference.ModelType)

Bases: actableai.models.inference.AAIBaseModelInference[actableai.clustering.models.ClusteringModel, actableai.clustering.models.ClusteringModelMetadata]

class actableai.clustering.models.ClusteringModelMetadata(*, features: List[str], feature_parameters: Dict[str, Any], prediction_target: str)

Bases: actableai.models.inference.AAIBaseModelMetadata

feature_parameters: Dict[str, Any]
features: List[str]
prediction_target: str
© Copyright 2022, ActableAI Team. Created using Sphinx.