KernelDensity (Beta)¶

In [ ]:

KernelDensity(name: str, 
              bandwidth: float = 1,
              kernel: str = "gaussian",
              p: int = 2,
              max_leaf_nodes: int = 1e9,
              max_depth: int = 5,
              min_samples_leaf: int = 1,
              nbins: int = 5,
              xlim: list = [])

Creates a KernelDensity object. This object uses pure SQL to compute the final score.

Parameters¶

Name	Type	Optional	Description
name	str	❌	Name of the model to be stored in the database.
bandwidth	float	✓	The bandwidth of the kernel.
kernel	str	✓	The method used for the plot. gaussian : Gaussian Kernel. logistic : Logistic Kernel. sigmoid : Sigmoid Kernel. silverman : Silverman Kernel.
p	int	✓	The p corresponding to the one of the p-distance (distance metric used during the model computation).
max_leaf_nodes	int	✓	The maximum number of leaf nodes, an integer between 1 and 1e9, inclusive.
max_depth	int	✓	The maximum tree depth, an integer between 1 and 100, inclusive.
min_samples_leaf	int	✓	The minimum number of samples each branch must have after splitting a node, an integer between 1 and 1e6, inclusive. A split that causes fewer remaining samples is discarded.
nbins	int	✓	The number of bins to use to discretize the input features.
xlim	list	✓	List of tuples to use to compute the kernel window.

Attributes¶

After the object creation, all the parameters become attributes. The model will also create extra attributes when fitting the model:

Name	Type	Description
input_relation	str	Training relation.
X	list	List of the predictors.
map	str	Name of the Mapping Relation.
tree_name	str	Name of the Tree.

Methods¶

Name	Description
deploySQL	Returns the SQL code needed to deploy the model.
drop	Drops the model from the Vertica DB.
features_importance	Computes the model features importance using the Gini Index.
fit	Trains the model.
get_attr	Returns the model attribute.
get_params	Returns the model Parameters.
get_tree	Returns a tablesample with all the KernelDensity tree information.
plot	Draws the Model.
plot_tree	Draws the KernelDensity tree (requires the graphviz module).
predict	Computes the KernelDensity score.
regression_report / report	Computes a regression report using multiple metrics to evaluate the density estimation (r2, mse, max error...).
score	Computes the density estimation score.
set_params	Sets the parameters of the model.
to_graphviz	Converts the KernelDensity tree to a Graphviz tree.

Example¶

In [16]:

from verticapy.learn.neighbors import KernelDensity
model = KernelDensity(name = "KDE_test",
                      bandwidth = 1,
                      kernel = "gaussian",
                      p = 2,
                      max_leaf_nodes = 1e9,
                      max_depth = 5,
                      min_samples_leaf = 1,
                      nbins = 5,
                      xlim = [])
display(model)

<KernelDensity>