SARIMAX (Beta)

In [ ]:
SARIMAX(name: str,
        p: int = 0,
        d: int = 0,
        q: int = 0,
        P: int = 0,
        D: int = 0,
        Q: int = 0,
        s: int = 0,
        tol: float = 1e-4,
        max_iter: int = 1000,
        solver: str = "Newton",
        max_pik: int = 100,
        papprox_ma: int = 200)

Creates an SARIMAX object using the Vertica linear regression function.

Parameters

Name Type Optional Description
name
str
❌
 Name of the model to be stored in the database.
p
int
✓
 Order of the AR (Auto-Regressive) part.
d
int
✓
 Order of the I (Integrated) part.
q
int
✓
 Order of the MA (Moving-Average) part.
P
int
✓
 Order of the seasonal AR (Auto-Regressive) part.
D
int
✓
 Order of the seasonal I (Integrated) part.
Q
int
✓
 Order of the seasonal MA (Moving-Average) part.
s
int
✓
 Span of the seasonality.
tol
float
✓
 Determines whether the algorithm has reached the specified accuracy result.
max_iter
int
✓
 Determines the maximum number of iterations the algorithm performs before achieving the specified accuracy result.
solver
str
✓
 The optimizer method to use to train the model.
  • Newton : Newton Method
  • BFGS : Broyden Fletcher Goldfarb Shanno
max_pik
int
✓
 Number of inverse MA coefficient used to approximate the MA.
papprox_ma
int
✓
 the p of the AR(p) used to approximate the MA coefficients.

Attributes

When this object is created, all of its parameters become attributes. When fitting the model, the model will create additional attributes.:

Name Type Description
coef_
tablesample
 Coefficients and their mathematical information (pvalue, std, value...)
ma_piq_
tablesample
 Moving Average Coefficients.
ma_avg_
float
 Moving Average Intercept.
deploy_predict_
str
 SQL code used to deploy the model.
input_relation
str
 Training relation.
ts
str
 vcolumn used to order the data.
exogenous
str
 exogenous columns.
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.
transform_relation
str
 Relation used to deploy the model.

Methods

Name Description
deploySQL Returns the SQL code needed to deploy the model.
drop Drops the model from the Vertica DB.
fit Trains the model.
get_attr Returns the model attribute.
get_params Returns the model Parameters.
plot Draws the SARIMAX model.
predict Predicts using the input relation.
regression_report / report Computes a regression report using multiple metrics to evaluate the model (r2, mse, max error...).
score Computes the model score.
set_params Sets the parameters of the model.

Example

In [2]:
from verticapy.learn.tsa import SARIMAX
model = SARIMAX(name = "SARIMAX_cases",
                tol = 1e-4,
                max_iter = 100, 
                solver = 'BFGS',
                p = 10,
                max_pik = 100)
display(model)

<SARIMAX>