Automated Machine Learning#

AutoML#

automl.AutoML([name, overwrite_model, ...])

Tests multiple models to find those that maximize the input score.

Methods:

`AutoML.contour`([nbins, chart])	Draws the model's contour plot.
`AutoML.deploySQL`([X])	Returns the SQL code needed to deploy the model.
`AutoML.does_model_exists`(name[, ...])	Checks whether the model is stored in the Vertica database.
`AutoML.drop`()	Drops the model from the Vertica database.
`AutoML.export_models`(name, path[, kind])	Exports machine learning models.
`AutoML.features_importance`([chart])	Computes the model's features importance.
`AutoML.fit`(input_relation[, X, y, return_report])	Trains the model.
`AutoML.get_attributes`([attr_name])	Returns the model attributes.
`AutoML.get_match_index`(x, col_list[, str_check])	Returns the matching index.
`AutoML.get_params`()	Returns the parameters of the model.
`AutoML.get_plotting_lib`([class_name, chart, ...])	Returns the first available library (Plotly, Matplotlib, or Highcharts) to draw a specific graphic.
`AutoML.get_vertica_attributes`([attr_name])	Returns the model attribute.
`AutoML.import_models`(path[, schema, kind])	Imports machine learning models.
`AutoML.plot`([mltype, chart])	Draws the AutoML plot.
`AutoML.register`(registered_name[, raise_error])	Registers the model and adds it to in-DB Model versioning environment with a status of 'under_review'.
`AutoML.set_params`([parameters])	Sets the parameters of the model.
`AutoML.summarize`()	Summarizes the model.
`AutoML.to_binary`(path)	Exports the model to the Vertica Binary format.
`AutoML.to_memmodel`()	Converts the model to an InMemory object that can be used for different types of predictions.
`AutoML.to_pmml`(path)	Exports the model to PMML.
`AutoML.to_python`([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in Vertica functions.
`AutoML.to_sql`([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in Vertica functions.
`AutoML.to_tf`(path)	Exports the model to the Frozen Graph format (TensorFlow).

Attributes:

AutoML.object_type

AutoClustering#

automl.AutoClustering([name, ...])

Automatically creates k different groups with which to generalize the data.

Methods:

`AutoClustering.contour`([nbins, chart])	Draws the model's contour plot.
`AutoClustering.deploySQL`([X])	Returns the SQL code needed to deploy the model.
`AutoClustering.does_model_exists`(name[, ...])	Checks whether the model is stored in the Vertica database.
`AutoClustering.drop`()	Drops the model from the Vertica database.
`AutoClustering.export_models`(name, path[, kind])	Exports machine learning models.
`AutoClustering.fit`(input_relation[, X, ...])	Trains the model.
`AutoClustering.get_attributes`([attr_name])	Returns the model attributes.
`AutoClustering.get_match_index`(x, col_list)	Returns the matching index.
`AutoClustering.get_params`()	Returns the parameters of the model.
`AutoClustering.get_plotting_lib`([...])	Returns the first available library (Plotly, Matplotlib, or Highcharts) to draw a specific graphic.
`AutoClustering.get_vertica_attributes`([...])	Returns the model Vertica attributes.
`AutoClustering.import_models`(path[, schema, ...])	Imports machine learning models.
`AutoClustering.register`(registered_name[, ...])	Registers the model and adds it to in-DB Model versioning environment with a status of 'under_review'.
`AutoClustering.set_params`([parameters])	Sets the parameters of the model.
`AutoClustering.summarize`()	Summarizes the model.
`AutoClustering.to_binary`(path)	Exports the model to the Vertica Binary format.
`AutoClustering.to_pmml`(path)	Exports the model to PMML.
`AutoClustering.to_python`([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in Vertica functions.
`AutoClustering.to_sql`([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in Vertica functions.
`AutoClustering.to_tf`(path)	Exports the model to the Frozen Graph format (TensorFlow).

Attributes:

AutoDataPrep.object_type

AutoDataPrep#

automl.AutoDataPrep([name, overwrite_model, ...])

Automatically find relations between the different features to preprocess the data according to each column type.

Methods:

`AutoDataPrep.contour`([nbins, chart])	Draws the model's contour plot.
`AutoDataPrep.deploySQL`([X])	Returns the SQL code needed to deploy the model.
`AutoDataPrep.does_model_exists`(name[, ...])	Checks whether the model is stored in the Vertica database.
`AutoDataPrep.drop`()	Drops the model from the Vertica database.
`AutoDataPrep.export_models`(name, path[, kind])	Exports machine learning models.
`AutoDataPrep.fit`(input_relation[, X, ts, ...])	Trains the model.
`AutoDataPrep.get_attributes`([attr_name])	Returns the model attributes.
`AutoDataPrep.get_match_index`(x, col_list[, ...])	Returns the matching index.
`AutoDataPrep.get_params`()	Returns the parameters of the model.
`AutoDataPrep.get_plotting_lib`([class_name, ...])	Returns the first available library (Plotly, Matplotlib, or Highcharts) to draw a specific graphic.
`AutoDataPrep.get_vertica_attributes`([attr_name])	Returns the model Vertica attributes.
`AutoDataPrep.import_models`(path[, schema, kind])	Imports machine learning models.
`AutoDataPrep.register`(registered_name[, ...])	Registers the model and adds it to in-DB Model versioning environment with a status of 'under_review'.
`AutoDataPrep.set_params`([parameters])	Sets the parameters of the model.
`AutoDataPrep.summarize`()	Summarizes the model.
`AutoDataPrep.to_binary`(path)	Exports the model to the Vertica Binary format.
`AutoDataPrep.to_pmml`(path)	Exports the model to PMML.
`AutoDataPrep.to_python`([return_proba, ...])	Returns the Python function needed for in-memory scoring without using built-in Vertica functions.
`AutoDataPrep.to_sql`([X, return_proba, ...])	Returns the SQL code needed to deploy the model without using built-in Vertica functions.
`AutoDataPrep.to_tf`(path)	Exports the model to the Frozen Graph format (TensorFlow).

Attributes:

AutoDataPrep.object_type