IsolationForest

In [ ]:
IsolationForest(name: str,
                n_estimators: int = 100,
                max_depth: int = 10,
                nbins: int = 32,
                sample: float = 0.632,
                col_sample_by_tree: float = 1.0)

Creates an IsolationForest object using the Vertica IFOREST algorithm.

Parameters

Name Type Optional Description
name
str
❌
 Name of the model to be stored in the database.
n_estimators
int
✓
 The number of trees in the forest, an integer in the range [1, 1000].
max_depth
int
✓
 Maximum depth of each tree, an integer in the range [1, 100].
nbins
int
✓
 Number of bins used for finding splits in each column, an integer in the range [2, 1000]. A greater value for nbins results in more precise splits, but a longer runtime.
sample
float
✓
 The random sample of the input dataset for training each tree, a float in the range [0.0, 1.0].
col_sample_by_tree
float
✓
 The fraction of randomly chosen columns (features) used to build each tree, a float in the range (0,1].

Attributes

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

Name Type Description
input_relation
str
 Training relation.
X
list
 List of the predictors.
y
str
 Response column.

Methods

Name Description
contour Draws the model's contour plot.
decision_function Returns the anomaly score using the input relation.
deploySQL Returns the SQL code to deploy the model.
drop Drops the model from the Vertica database.
fit Trains the model.
get_attr Returns model attributes.
get_params Returns model parameters.
get_tree Returns a tablesample with information about the input tree.
plot_tree Draws the input tree (requires the graphviz module).
predict Predicts using the input relation.
set_params Sets the parameters of the model.
to_graphviz Converts the input tree to a Graphviz tree.
to_memmodel Converts a specified Vertica model to a memModel model.
to_python Returns the Python code to deploy the model without using built-in Vertica functions.
to_sql Returns the SQL code to deploy the model without using Vertica built-in functions.

Example

In [29]:
from verticapy.learn.ensemble import IsolationForest
model = IsolationForest(name = "public.iforest_model",
                               n_estimators = 20,
                               max_depth = 3,
                               nbins = 32)
display(model)

<IsolationForest>