Package 'mlsauce'

AdaOpt classifier

Description

AdaOpt classifier

Usage

AdaOpt(
  n_iterations = 50L,
  learning_rate = 0.3,
  reg_lambda = 0.1,
  reg_alpha = 0.5,
  eta = 0.01,
  gamma = 0.01,
  k = 3L,
  tolerance = 0,
  n_clusters = 0,
  batch_size = 100L,
  row_sample = 1,
  type_dist = "euclidean-f",
  cache = TRUE,
  n_clusters_input = 0,
  clustering_method = "kmeans",
  cluster_scaling = "standard",
  seed = 123L
)

Arguments

n_iterations	number of iterations of the optimizer at training time
learning_rate	controls the speed of the optimizer at training time
reg_lambda	L2 regularization parameter for successive errors in the optimizer (at training time)
reg_alpha	L1 regularization parameter for successive errors in the optimizer (at training time)
eta	controls the slope in gradient descent (at training time)
gamma	controls the step size in gradient descent (at training time)
k	number of nearest neighbors selected at test time for classification
tolerance	controls early stopping in gradient descent (at training time)
n_clusters	number of clusters, if MiniBatch k-means is used at test time (for faster prediction)
batch_size	size of the batch, if MiniBatch k-means is used at test time (for faster prediction)
row_sample	percentage of rows chosen from training set (by stratified subsampling, for faster prediction)
type_dist	distance used for finding the nearest neighbors; currently euclidean-f (euclidean distances calculated as whole), euclidean (euclidean distances calculated row by row), cosine (cosine distance)
cache	if the nearest neighbors are cached or not, for faster retrieval in subsequent calls
n_clusters_input	number of clusters a priori on inpu data
clustering_method	either "kmeans" or "gmm" (Gaussian mixture)
cluster_scaling	either 'standard', 'minmax', 'robust'
seed	reproducibility seed for initial weak learner and clustering

Value

An object of class AdaOpt

Examples

## Not run: 
library(datasets)

X <- as.matrix(iris[, 1:4])
y <- as.integer(iris[, 5]) - 1L

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(iris[train_index, 1:4])
y_train <- as.integer(iris[train_index, 5]) - 1L
X_test <- as.matrix(iris[test_index, 1:4])
y_test <- as.integer(iris[test_index, 5]) - 1L


obj <- mlsauce::AdaOpt()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

Download datasets

Description

Download datasets

Usage

download(
  pkgname = "MASS",
  dataset = "Boston",
  source = "https://cran.r-universe.dev/"
)

Arguments

pkgname	a string; R package name
dataset	a string; dataset name
source	a string; package location (address)

Value

A data frame

Examples

df <- mlsauce::download(pkgname="MASS", dataset="Boston", source="https://cran.r-universe.dev/")
print(df)

---

GenericBoosting classifier

Description

GenericBoosting classifier

Usage

GenericBoostingClassifier(
  base_model,
  n_estimators = 100L,
  learning_rate = 0.1,
  n_hidden_features = 5L,
  reg_lambda = 0.1,
  row_sample = 1,
  col_sample = 1,
  dropout = 0,
  tolerance = 1e-04,
  direct_link = 1L,
  verbose = 1L,
  seed = 123L,
  activation = "relu",
  n_clusters = 0,
  clustering_method = "kmeans",
  cluster_scaling = "standard",
  degree = 0,
  weights_distr = "uniform"
)

Arguments

n_estimators:	int, number of boosting iterations.
learning_rate:	float, controls the learning speed at training time.
n_hidden_features:	int
number	of nodes in successive hidden layers.
reg_lambda:	float, L2 regularization parameter for successive errors in the optimizer (at training time).
row_sample:	float, percentage of rows chosen from the training set.
col_sample:	float, percentage of columns chosen from the training set.
dropout:	float, percentage of nodes dropped from the training set.
tolerance:	float, controls early stopping in gradient descent (at training time).
direct_link:	bool, indicates whether the original features are included (True) in model's fitting or not (False).
verbose:	int, progress bar (yes = 1) or not (no = 0) (currently).
seed:	int, reproducibility seed for nodes_sim=='uniform', clustering and dropout.
activation:	str, activation function: currently 'relu', 'relu6', 'sigmoid', 'tanh'
n_clusters:	int, number of clusters for clustering.
clustering_method:	str, clustering method: currently 'kmeans', 'gmm' (Gaussian Mixture Model)
cluster_scaling:	str, scaling method for clustering: currently 'standard', 'minmax', 'robust'
degree:	int, degree of polynomial interactions features.
weights_distr:	str, distribution of weights for the hidden layer currently 'uniform', 'gaussian'

Value

An object of class GenericBoostingClassifier

Examples

library(datasets)

X <- as.matrix(iris[, 1:4])
y <- as.integer(iris[, 5]) - 1L

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.integer(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.integer(y[test_index])

## Not run: 
regr <- sklearn$linear_model$Ridge()
obj <- mlsauce::GenericBoostingClassifier(regr)

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

GenericBoosting Regressor

Description

GenericBoosting Regressor

Usage

GenericBoostingRegressor(
  base_model,
  n_estimators = 100L,
  learning_rate = 0.1,
  n_hidden_features = 5L,
  reg_lambda = 0.1,
  row_sample = 1,
  col_sample = 1,
  dropout = 0,
  tolerance = 1e-04,
  direct_link = 1L,
  verbose = 1L,
  seed = 123L,
  activation = "relu",
  n_clusters = 0,
  clustering_method = "kmeans",
  cluster_scaling = "standard",
  degree = 0,
  weights_distr = "uniform"
)

Arguments

n_estimators:	int, number of boosting iterations.
learning_rate:	float, controls the learning speed at training time.
n_hidden_features:	int
number	of nodes in successive hidden layers.
reg_lambda:	float, L2 regularization parameter for successive errors in the optimizer (at training time).
row_sample:	float, percentage of rows chosen from the training set.
col_sample:	float, percentage of columns chosen from the training set.
dropout:	float, percentage of nodes dropped from the training set.
tolerance:	float, controls early stopping in gradient descent (at training time).
direct_link:	bool, indicates whether the original features are included (True) in model's fitting or not (False).
verbose:	int, progress bar (yes = 1) or not (no = 0) (currently).
seed:	int, reproducibility seed for nodes_sim=='uniform', clustering and dropout.
activation:	str, activation function: currently 'relu', 'relu6', 'sigmoid', 'tanh'
n_clusters:	int, number of clusters for clustering.
clustering_method:	str, clustering method: currently 'kmeans', 'gmm' (Gaussian Mixture Model)
cluster_scaling:	str, scaling method for clustering: currently 'standard', 'minmax', 'robust'
degree:	int, degree of polynomial interactions features.
weights_distr:	str, distribution of weights for the hidden layer currently 'uniform', 'gaussian'

Value

An object of class GenericBoostingRegressor

Examples

## Not run: 
library(datasets)

X <- as.matrix(datasets::mtcars[, -1])
y <- as.integer(datasets::mtcars[, 1])

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.double(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.double(y[test_index])

regr <- sklearn$linear_model$Ridge()
obj <- mlsauce::GenericBoostingRegressor(regr)

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

Lasso regressor

Description

Lasso regressor

Usage

LassoRegressor(reg_lambda = 0.1, max_iter = 10L, tol = 0.001)

Arguments

reg_lambda	L1 regularization parameter
max_iter	number of iterations of lasso shooting algorithm.
tol	tolerance for convergence of lasso shooting algorithm.

Value

An object of class Lasso

Examples

## Not run: 
library(datasets)

X <- as.matrix(datasets::mtcars[, -1])
y <- as.integer(datasets::mtcars[, 1])

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.double(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.double(y[test_index])

obj <- mlsauce::LassoRegressor()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

LSBoost classifier

Description

LSBoost classifier

Usage

LSBoostClassifier(
  n_estimators = 100L,
  learning_rate = 0.1,
  n_hidden_features = 5L,
  reg_lambda = 0.1,
  row_sample = 1,
  col_sample = 1,
  dropout = 0,
  tolerance = 1e-04,
  direct_link = 1L,
  verbose = 1L,
  seed = 123L,
  solver = c("ridge", "lasso"),
  activation = "relu",
  n_clusters = 0,
  clustering_method = "kmeans",
  cluster_scaling = "standard",
  degree = 0,
  weights_distr = "uniform"
)

Arguments

n_estimators:	int, number of boosting iterations.
learning_rate:	float, controls the learning speed at training time.
n_hidden_features:	int
number	of nodes in successive hidden layers.
reg_lambda:	float, L2 regularization parameter for successive errors in the optimizer (at training time).
row_sample:	float, percentage of rows chosen from the training set.
col_sample:	float, percentage of columns chosen from the training set.
dropout:	float, percentage of nodes dropped from the training set.
tolerance:	float, controls early stopping in gradient descent (at training time).
direct_link:	bool, indicates whether the original features are included (True) in model's fitting or not (False).
verbose:	int, progress bar (yes = 1) or not (no = 0) (currently).
seed:	int, reproducibility seed for nodes_sim=='uniform', clustering and dropout.
solver:	str, type of 'weak' learner; currently in ('ridge', 'lasso')
activation:	str, activation function: currently 'relu', 'relu6', 'sigmoid', 'tanh'
n_clusters:	int, number of clusters for clustering.
clustering_method:	str, clustering method: currently 'kmeans', 'gmm' (Gaussian Mixture Model)
cluster_scaling:	str, scaling method for clustering: currently 'standard', 'minmax', 'robust'
degree:	int, degree of polynomial interactions features.
weights_distr:	str, distribution of weights for the hidden layer currently 'uniform', 'gaussian'

Value

An object of class LSBoostClassifier

Examples

library(datasets)

X <- as.matrix(iris[, 1:4])
y <- as.integer(iris[, 5]) - 1L

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.integer(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.integer(y[test_index])

## Not run: 
obj <- mlsauce::LSBoostClassifier()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

LSBoost Regressor

Description

LSBoost Regressor

Usage

LSBoostRegressor(
  n_estimators = 100L,
  learning_rate = 0.1,
  n_hidden_features = 5L,
  reg_lambda = 0.1,
  row_sample = 1,
  col_sample = 1,
  dropout = 0,
  tolerance = 1e-04,
  direct_link = 1L,
  verbose = 1L,
  seed = 123L,
  solver = c("ridge", "lasso"),
  activation = "relu",
  n_clusters = 0,
  clustering_method = "kmeans",
  cluster_scaling = "standard",
  degree = 0,
  weights_distr = "uniform"
)

Arguments

n_estimators:	int, number of boosting iterations.
learning_rate:	float, controls the learning speed at training time.
n_hidden_features:	int
number	of nodes in successive hidden layers.
reg_lambda:	float, L2 regularization parameter for successive errors in the optimizer (at training time).
row_sample:	float, percentage of rows chosen from the training set.
col_sample:	float, percentage of columns chosen from the training set.
dropout:	float, percentage of nodes dropped from the training set.
tolerance:	float, controls early stopping in gradient descent (at training time).
direct_link:	bool, indicates whether the original features are included (True) in model's fitting or not (False).
verbose:	int, progress bar (yes = 1) or not (no = 0) (currently).
seed:	int, reproducibility seed for nodes_sim=='uniform', clustering and dropout.
solver:	str, type of 'weak' learner; currently in ('ridge', 'lasso')
activation:	str, activation function: currently 'relu', 'relu6', 'sigmoid', 'tanh'
n_clusters:	int, number of clusters for clustering.
clustering_method:	str, clustering method: currently 'kmeans', 'gmm' (Gaussian Mixture Model)
cluster_scaling:	str, scaling method for clustering: currently 'standard', 'minmax', 'robust'
degree:	int, degree of polynomial interactions features.
weights_distr:	str, distribution of weights for the hidden layer currently 'uniform', 'gaussian'

Value

An object of class LSBoostRegressor

Examples

## Not run: 
library(datasets)

X <- as.matrix(datasets::mtcars[, -1])
y <- as.integer(datasets::mtcars[, 1])

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.double(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.double(y[test_index])

obj <- mlsauce::LSBoostRegressor()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

Python module mlsauce

Description

This is the Python mlsauce module imported using reticulate.

Usage

ms

Format

An object of class python.builtin.module (inherits from python.builtin.object) of length 0.

---

Python module numpy

Description

This is the Python numpy module imported using reticulate.

Usage

numpy

Format

An object of class python.builtin.module (inherits from python.builtin.object) of length 0.

---

Python module pandas

Description

This is the Python pandas module imported using reticulate.

Usage

pandas

Format

An object of class python.builtin.module (inherits from python.builtin.object) of length 0.

---

Ridge regressor

Description

Ridge regressor

Usage

RidgeRegressor(reg_lambda = 0.1)

Arguments

reg_lambda

L2 regularization parameter

Value

An object of class Ridge

Examples

## Not run: 
library(datasets)

X <- as.matrix(datasets::mtcars[, -1])
y <- as.integer(datasets::mtcars[, 1])

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(X[train_index, ])
y_train <- as.double(y[train_index])
X_test <- as.matrix(X[test_index, ])
y_test <- as.double(y[test_index])


obj <- mlsauce::RidgeRegressor()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---

Python module sklearn

Description

This is the Python sklearn module imported using reticulate.

Usage

sklearn

Format

An object of class python.builtin.module (inherits from python.builtin.object) of length 0.

---

Stump classifier

Description

Stump classifier

Usage

StumpClassifier(bins = "auto")

Arguments

bins:

int, number of histogram bins.

Value

An object of class StumpClassifier

Examples

## Not run: 
library(datasets)

X <- as.matrix(iris[, 1:4])
y <- as.integer(iris[, 5]) - 1L

n <- dim(X)[1]
p <- dim(X)[2]
set.seed(21341)
train_index <- sample(x = 1:n, size = floor(0.8*n), replace = TRUE)
test_index <- -train_index
X_train <- as.matrix(iris[train_index, 1:4])
y_train <- as.integer(iris[train_index, 5]) - 1L
X_test <- as.matrix(iris[test_index, 1:4])
y_test <- as.integer(iris[test_index, 5]) - 1L


obj <- mlsauce::StumpClassifier()

print(obj$get_params())

obj$fit(X_train, y_train)

print(obj$score(X_test, y_test))
## End(Not run)

---