BaseLiNGAM: LiNGAM class

In gkikuchi/rlingam: R Implementation of LiNGAM algorithms

Description

R implementation for LiNGAM models This class is a base class for LiNGAM.

This code is based on Python implementation:

(The LiNGAM Project: https://sites.google.com/site/sshimizu06/lingam)

Public fields

random_state

(integer) Random seed

causal_order

(numeric vector) Causal oreder of variables

adjacency_matrix

(numeric matrix) Estimated adjacency matrix

intercept

(numeric vector) Estimated intercept term

lasso_engine

(character) "lars" or "glmnet"

Methods

Public methods

• BaseLiNGAM$new()

• BaseLiNGAM$fit()

• BaseLiNGAM$estimate_adjacency_matrix()

• BaseLiNGAM$predict_adaptive_lasso()

• BaseLiNGAM$clone()

---

Method new()

create lingam object

Usage

BaseLiNGAM$new(random_state = NULL, lasso_engine = "glmnet")

Arguments

random_state

(integer) Random seed

lasso_engine

(character) "lars" or "glmnet"

---

Method fit()

subclasses should implement this method

Usage

BaseLiNGAM$fit(X)

Arguments

X

(numeric matrix or data.frame) data matrix

---

Method estimate_adjacency_matrix()

estimate adjacency matrix based on causal order

Usage

BaseLiNGAM$estimate_adjacency_matrix(X)

Arguments

X

(numeric matrix or data.frame) data matrix

---

Method predict_adaptive_lasso()

fit adaptice lasso

Usage

BaseLiNGAM$predict_adaptive_lasso(X, predictors, target, gamma = 1)

Arguments

X

(numeric matrix or data.frame) data matrix

predictors

(numeric vector) index of explanatory variables

target

(integer) index of target variable

gamma

(numeric) data x will be weighted like x^(gamma) for adaptive lasso

Returns

coef_ (numeric vector) estimated coefficients

---

Method clone()

The objects of this class are cloneable with this method.

Usage

BaseLiNGAM$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

gkikuchi/rlingam documentation built on Jan. 7, 2022, 11:10 p.m.