XGBoostClassifier¶

In [ ]:

XGBoostClassifier(name: str,
                  max_ntree: int = 10,
                  max_depth: int = 5,
                  nbins: int = 32,
                  split_proposal_method: str = "global",
                  tol: float = 0.001,
                  learning_rate: float = 0.1,
                  min_split_loss: float = 0.0,
                  weight_reg: float = 0.0,
                  sample: float = 1.0,
                  col_sample_by_tree: float = 1.0,
                  col_sample_by_node: float = 1.0,)

Creates an XGBoostClassifier object using the Vertica XGB_CLASSIFIER algorithm.

Parameters¶

Name	Type	Optional	Description
name	str	❌	Name of the model to be stored in the database.
max_ntree	int	✓	Maximum number of trees that will be created.
max_depth	int	✓	Maximum depth of each tree.
nbins	int	✓	Number of bins to use for finding splits in each column, more splits leads to longer runtime but more fine-grained and possibly better splits.
split_proposal_method	str	✓	approximate splitting strategy. Can be 'global' or 'local' (not yet supported).
tol	float	✓	approximation error of quantile summary structures used in the approximate split finding method.
learning_rate	float	✓	weight applied to each tree's prediction, reduces each tree's impact allowing for later trees to contribute, keeping earlier trees from 'hogging' all the improvements.
min_split_loss	float	✓	Each split must improve the objective function value of the model by at least this much in order to not be pruned. Value of 0 is the same as turning off this parameter (trees will still be pruned based on positive/negative objective function values).
weight_reg	float	✓	Regularization term that is applied to the weights of the leaves in the regression tree. The higher this value is, the more sparse/smooth the weights will be, which often helps prevent overfitting.
sample	float	✓	Fraction of rows to use in training per iteration.
col_sample_by_tree	float	✓	Float in the range (0,1] that specifies the fraction of columns (features), chosen at random, to use when building each tree.
col_sample_by_node	float	✓	Float in the range (0,1] that specifies the fraction of columns (features), chosen at random, to use when evaluating each split.

Attributes¶

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

Name	Type	Description
classes_	list	List of all the response classes.
input_relation	str	Training relation.
X	list	List of the predictors.
y	str	Response column.
test_relation	str	Relation to use to test the model. All model methods are abstractions that simplify the process. The testing relation will be used by the methods to evaluate the model. If empty, the training relation will be used instead. This attribute can be changed at any time.
prior_	float / list	The value(s) used to score the model. For binary classification, this is the average of the response column. Otherwise, this is the list of the probabilities of each class.

Methods¶

Name	Description
classification_report / report	Computes a classification report using multiple metrics to evaluate the model (AUC, accuracy, PRC AUC, F1...). In case of multiclass classification, it will consider each category as positive and switch to the next one during the computation.
confusion_matrix	Computes the model confusion matrix.
contour	Draws the model's contour plot.
cutoff_curve	Draws the model's Cutoff curve.
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 input tree information.
lift_chart	Draws the model Lift Chart.
plot_tree	Draws the input tree (requires the graphviz module).
prc_curve	Draws the model PRC curve.
predict	Predicts using the input relation.
predict_proba	Returns the model's probabilities using the input relation.
roc_curve	Draws the model ROC curve.
score	Computes the model score.
set_params	Sets the parameters of the model.
to_graphviz	Converts the input tree to a Graphviz tree.
to_json	Creates a Python XGBoost JSON file that can be imported into the Python XGBoost API.
to_memmodel	Converts a specified Vertica model to a memModel model.
to_python	Returns the Python code needed to deploy the model without using built-in Vertica functions.
to_sql	Returns the SQL code needed to deploy the model without using Vertica built-in functions.

Example¶

In [9]:

from verticapy.learn.ensemble import XGBoostClassifier
model = XGBoostClassifier(name = "public.xgb_titanic",
                          max_ntree = 20,
                          max_depth = 15,)
display(model)

<XGBoostClassifier>