Clustering & Anomaly Detection

Clustering

K-Means

cluster.KMeans([name, overwrite_model])

Creates an KMeans object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

KMeans.contour([nbins, chart])	Draws the model's contour plot.
KMeans.deploySQL([X])	Returns the SQL code needed to deploy the model.
KMeans.drop()	Drops the model from the VAST DataBase.
KMeans.export_models(name, path[, kind])	Exports machine learning models.
KMeans.fit(input_relation[, X, return_report])	Trains the model.
KMeans.get_attributes([attr_name])	Returns the model attributes.
KMeans.get_match_index(x, col_list[, str_check])	Returns the matching index.
KMeans.get_params()	Returns the parameters of the model.
KMeans.get_plotting_lib([class_name, chart, ...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
KMeans.import_models(path[, schema, kind])	Imports machine learning models.
KMeans.plot([max_nb_points, chart])	Draws the model.
KMeans.plot_voronoi([max_nb_points, ...])	Draws the Voronoi Graph of the model.
KMeans.predict(vdf[, X, name, inplace])	Makes predictions using the input relation.
KMeans.set_params([parameters])	Sets the parameters of the model.
KMeans.summarize()	Summarizes the model.
KMeans.to_binary(path)	Exports the model to the VAST Binary format.
KMeans.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
KMeans.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
KMeans.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

KMeans.object_type

Bisecting K-Means

cluster.BisectingKMeans([name, overwrite_model])

Creates a BisectingKMeans object using the VAST bisecting k-means algorithm.

Methods:

BisectingKMeans.contour([nbins, chart])	Draws the model's contour plot.
BisectingKMeans.deploySQL([X])	Returns the SQL code needed to deploy the model.
BisectingKMeans.drop()	Drops the model from the VAST DataBase.
BisectingKMeans.export_models(name, path[, kind])	Exports machine learning models.
BisectingKMeans.features_importance([...])	Computes the model's features importance.
BisectingKMeans.fit(input_relation[, X, ...])	Trains the model.
BisectingKMeans.get_attributes([attr_name])	Returns the model attributes.
BisectingKMeans.get_match_index(x, col_list)	Returns the matching index.
BisectingKMeans.get_params()	Returns the parameters of the model.
BisectingKMeans.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
BisectingKMeans.get_tree()	Returns a table containing information about the BK-tree.
BisectingKMeans.import_models(path[, ...])	Imports machine learning models.
BisectingKMeans.plot([max_nb_points, chart])	Draws the model.
BisectingKMeans.plot_tree([pic_path])	Draws the input tree.
BisectingKMeans.plot_voronoi([...])	Draws the Voronoi Graph of the model.
BisectingKMeans.predict(vdf[, X, name, inplace])	Makes predictions using the input relation.
BisectingKMeans.set_params([parameters])	Sets the parameters of the model.
BisectingKMeans.summarize()	Summarizes the model.
BisectingKMeans.to_binary(path)	Exports the model to the VAST Binary format.
BisectingKMeans.to_graphviz([round_score, ...])	Returns the code for a Graphviz tree.
BisectingKMeans.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
BisectingKMeans.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
BisectingKMeans.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

BisectingKMeans.object_type

DBSCAN (Beta)

cluster.DBSCAN([name, overwrite_model, eps, ...])

[Beta Version] Creates a DBSCAN object by using the DBSCAN algorithm as defined by Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu.

Methods:

DBSCAN.contour([nbins, chart])	Draws the model's contour plot.
DBSCAN.deploySQL([X])	Returns the SQL code needed to deploy the model.
DBSCAN.drop()	Drops the model from the VAST DataBase.
DBSCAN.export_models(name, path[, kind])	Exports machine learning models.
DBSCAN.fit(input_relation[, X, key_columns, ...])	Trains the model.
DBSCAN.get_attributes([attr_name])	Returns the model attributes.
DBSCAN.get_match_index(x, col_list[, str_check])	Returns the matching index.
DBSCAN.get_params()	Returns the parameters of the model.
DBSCAN.get_plotting_lib([class_name, chart, ...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
DBSCAN.import_models(path[, schema, kind])	Imports machine learning models.
DBSCAN.plot([max_nb_points, chart])	Draws the model.
DBSCAN.predict()	Creates a VastFrame of the model.
DBSCAN.set_params([parameters])	Sets the parameters of the model.
DBSCAN.summarize()	Summarizes the model.
DBSCAN.to_binary(path)	Exports the model to the VAST Binary format.
DBSCAN.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
DBSCAN.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

DBSCAN.object_type

---

Anomaly Detection

Isolation Forest

ensemble.IsolationForest([name, overwrite_model])

Creates an IsolationForest object using scikit-learn for training and the scalability of VAST DataBase for the inferences.

Methods:

IsolationForest.contour([nbins, chart])	Draws the model's contour plot.
IsolationForest.decision_function(vdf[, X, ...])	Returns the anomaly score using the input relation.
IsolationForest.deploySQL([X, cutoff, ...])	Returns the SQL code needed to deploy the model.
IsolationForest.drop()	Drops the model from the VAST DataBase.
IsolationForest.export_models(name, path[, kind])	Exports machine learning models.
IsolationForest.features_importance([...])	Computes the model's features importance.
IsolationForest.fit(input_relation[, X, ...])	Trains the model.
IsolationForest.get_attributes([attr_name])	Returns the model attributes.
IsolationForest.get_match_index(x, col_list)	Returns the matching index.
IsolationForest.get_params()	Returns the parameters of the model.
IsolationForest.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
IsolationForest.get_tree([tree_id])	Returns a table with all the input tree information.
IsolationForest.import_models(path[, ...])	Imports machine learning models.
IsolationForest.plot([max_nb_points, chart])	Draws the model.
IsolationForest.plot_tree([tree_id, pic_path])	Draws the input tree.
IsolationForest.predict(vdf[, X, name, ...])	Predicts using the input relation.
IsolationForest.set_params([parameters])	Sets the parameters of the model.
IsolationForest.summarize()	Summarizes the model.
IsolationForest.to_binary(path)	Exports the model to the VAST Binary format.
IsolationForest.to_graphviz([tree_id, ...])	Returns the code for a Graphviz tree.
IsolationForest.to_memmodel()	Converts the model to an InMemory object that can be used for different types of predictions.
IsolationForest.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
IsolationForest.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

IsolationForest.object_type

Local Outlier Factor (Beta)

neighbors.LocalOutlierFactor([name, ...])

[Beta Version] Creates a LocalOutlierFactor object by using the Local Outlier Factor algorithm.

Methods:

LocalOutlierFactor.contour([nbins, chart])	Draws the model's contour plot.
LocalOutlierFactor.deploySQL([X])	Returns the SQL code needed to deploy the model.
LocalOutlierFactor.drop()	Drops the model (clears stored SQL).
LocalOutlierFactor.export_models(name, path)	Exports machine learning models.
LocalOutlierFactor.fit(input_relation[, X, ...])	Trains the model by generating and storing the LOF SQL query.
LocalOutlierFactor.get_attributes([attr_name])	Returns the model attributes.
LocalOutlierFactor.get_match_index(x, col_list)	Returns the matching index.
LocalOutlierFactor.get_params()	Returns the parameters of the model.
LocalOutlierFactor.get_plotting_lib([...])	Returns the first available library (Plotly, Matplotlib) to draw a specific graphic.
LocalOutlierFactor.import_models(path[, ...])	Imports machine learning models.
LocalOutlierFactor.predict()	Returns a VastFrame with the LOF scores.
LocalOutlierFactor.set_params([parameters])	Sets the parameters of the model.
LocalOutlierFactor.summarize()	Summarizes the model.
LocalOutlierFactor.to_binary(path)	Exports the model to the VAST Binary format.
LocalOutlierFactor.to_python([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in VAST functions.
LocalOutlierFactor.to_sql([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in VAST functions.

Attributes:

LocalOutlierFactor.object_type