LinearSVC

In [ ]:
LinearSVC(name: str,
          cursor = None,
          tol: float = 1e-4, 
          C: float = 1.0, 
          fit_intercept: bool = True,
          intercept_scaling: float = 1.0,
          intercept_mode: str = "regularized",
          class_weight: list = [1, 1],
          max_iter: int = 100)

Creates a LinearSVC object using the Vertica SVM (Support Vector Machine) algorithm. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples to each category, making it a non-probabilistic binary linear classifier.

Parameters

Name Type Optional Description
name
str
❌
 Name of the model to be stored in the DB.
cursor
DBcursor
✓
 Vertica DB cursor.
tol
float
✓
 to use to control accuracy.
C
float
✓
 The weight for misclassification cost. The algorithm minimizes the regularization cost and the misclassification cost.
fit_intercept
bool
✓
 Whether to calculate the intercept for the model.
intercept_scaling
float
✓
 A float value, serves as the value of a dummy feature whose coefficient Vertica uses to calculate the model intercept. Because the dummy feature is not in the training data, its values are set to a constant, by default set to 1.
intercept_mode
str
✓
 Specify how to treat the intercept.
  • regularized : Fits the intercept and applies a regularization on it.
  • unregularized : Fits the intercept but does not include it in regularization.
class_weight
list
✓
 Specifies how to determine weights of the two classes. It can be a list of 2 elements or one of the following method:
  • auto : Weights each class according to the number of samples.
  • none : No weights are used.
max_iter
int
✓
 The maximum number of iterations that the algorithm performs.

Attributes

After the object is created, all parameters become attributes. Additional attributes will be created when fitting the model:

Name Type Description
coef_
tablesample
 Coefficients and their mathematical information (pvalue, std, value...)
input_relation
str
 Training relation.
X
list
 List of the predictors.
y
str
 Response column.
test_relation
float
 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.

Methods

Name Description
classification_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's confusion matrix.
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 by normalizing the LinearSVC hyperplan coefficients.
fit Trains the model.
get_attr Returns the model attribute.
get_params Returns the model Parameters.
lift_chart Draws the model Lift Chart.
plot Draws the LinearSVC if the number of predictors is less than 3.
prc_curve Draws the model precision-recall curve.
predict Predicts using the input relation.
roc_curve Draws the model ROC curve.
score Computes the model score.
set_cursor Sets a new database cursor.
set_params Sets the parameters of the model.
shapExplainer Creates a shapExplainer for the model.
to_sklearn Converts this Vertica model to an sklearn model.

Example

In [8]:
from verticapy.learn.svm import LinearSVC
model = LinearSVC(name = "iris_svm",
                  tol = 1e-4, 
                  C = 1.0, 
                  fit_intercept = True,
                  intercept_scaling = 1.0,
                  intercept_mode = "regularized",
                  class_weight = [1, 1],
                  max_iter = 100)
display(model)

<LinearSVC>