MGScanning_pred: Multi-Grained Scanning Predictor implementation in R
In Laurae2/Laurae: Advanced High Performance Data Science Toolbox for R

Description Usage Arguments Details Value Examples

This function attempts to predict from Multi-Grained Scanning using xgboost.

1 2	MGScanning_pred(model, data, folds = NULL, dimensions = NULL, multi_class = NULL, data_start = NULL)

`model`	Type: list. A model trained by `MGScanning`.
`data`	Type: data.table. A data to predict on. If passing training data, it will predict as if it was out of fold and you will overfit (so, use the list `preds` instead please).
`folds`	Type: list. The folds as list for cross-validation if using the training data. Otherwise, leave `NULL`. Defaults to `NULL`.
`dimensions`	Type: numeric. The dimensions of the data. Only supported is `1` for matrix format, and `2` for list of matrices. Defaults to `NULL`.
`multi_class`	Type: numeric. How many classes you got. Set to 2 for binary classification, or regression cases. Set to `NULL` to let it try guessing by reading the `model`. Defaults to `NULL`.
`data_start`	Type: vector of numeric. The initial prediction labels. Set to `NULL` if you do not know what you are doing. Defaults to `NULL`.

For implementation details of Cascade Forest / Complete-Random Tree Forest / Multi-Grained Scanning / Deep Forest, check this: https://github.com/Microsoft/LightGBM/issues/331#issuecomment-283942390 by Laurae.

A data.table or a list based on data predicted using model.

## Not run: 
# Load libraries
library(data.table)
library(Matrix)
library(xgboost)

# Create data
data(agaricus.train, package = "lightgbm")
data(agaricus.test, package = "lightgbm")
agaricus_data_train <- data.table(as.matrix(agaricus.train$data))
agaricus_data_test <- data.table(as.matrix(agaricus.test$data))
agaricus_label_train <- agaricus.train$label
agaricus_label_test <- agaricus.test$label
folds <- Laurae::kfold(agaricus_label_train, 5)

# Train a model (binary classification) - FAST VERSION
model <- MGScanning(data = agaricus_data_train, # Training data
                    labels = agaricus_label_train, # Training labels
                    folds = folds, # Folds for cross-validation
                    dimensions = 1, # Change this for 2 dimensions if needed
                    depth = 10, # Change this to change the sliding window size
                    stride = 20, # Change this to change the sliding window speed
                    nthread = 1, # Change this to use more threads
                    lr = 1, # Do not touch this unless you are expert
                    training_start = NULL, # Do not touch this unless you are expert
                    validation_start = NULL, # Do not touch this unless you are expert
                    n_forest = 2, # Number of forest models
                    n_trees = 30, # Number of trees per forest
                    random_forest = 1, # We want only 2 random forest
                    seed = 0,
                    objective = "binary:logistic",
                    eval_metric = Laurae::df_logloss,
                    multi_class = 2, # Modify this for multiclass problems)
                    verbose = TRUE)

# Train a model (binary classification) - SLOW
model <- MGScanning(data = agaricus_data_train, # Training data
                    labels = agaricus_label_train, # Training labels
                    folds = folds, # Folds for cross-validation
                    dimensions = 1, # Change this for 2 dimensions if needed
                    depth = 10, # Change this to change the sliding window size
                    stride = 1, # Change this to change the sliding window speed
                    nthread = 1, # Change this to use more threads
                    lr = 1, # Do not touch this unless you are expert
                    training_start = NULL, # Do not touch this unless you are expert
                    validation_start = NULL, # Do not touch this unless you are expert
                    n_forest = 2, # Number of forest models
                    n_trees = 30, # Number of trees per forest
                    random_forest = 1, # We want only 2 random forest
                    seed = 0,
                    objective = "binary:logistic",
                    eval_metric = Laurae::df_logloss,
                    multi_class = 2, # Modify this for multiclass problems)
                    verbose = TRUE)

# Create predictions
data_predictions <- model$preds

# Make real predictions
new_preds <- MGScanning_pred(model, data = agaricus_data_test)

# We can check whether we have equal predictions, it's all TRUE!
all.equal(model$preds, MGScanning_pred(model,
                                       agaricus_data_train,
                                       folds = folds))

# Example on fake pictures (matrices) and multiclass problem

# Generate fake images
new_data <- list(matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20))

# Generate fake labels
new_labels <- c(2, 1, 0, 2, 1, 0, 2, 1, 0, 0)

# Train a model (multiclass problem)
model <- MGScanning(data = new_data, # Training data
                    labels = new_labels, # Training labels
                    folds = list(1:3, 3:6, 7:10), # Folds for cross-validation
                    dimensions = 2,
                    depth = 10,
                    stride = 1,
                    nthread = 1, # Change this to use more threads
                    lr = 1, # Do not touch this unless you are expert
                    training_start = NULL, # Do not touch this unless you are expert
                    validation_start = NULL, # Do not touch this unless you are expert
                    n_forest = 2, # Number of forest models
                    n_trees = 10, # Number of trees per forest
                    random_forest = 1, # We want only 2 random forest
                    seed = 0,
                    objective = "multi:softprob",
                    eval_metric = Laurae::df_logloss,
                    multi_class = 3, # Modify this for multiclass problems)
                    verbose = TRUE)

# Matrix output is 10x600
dim(model$preds)

# We can check whether we have equal predictions, it's all TRUE!
all.equal(model$preds, MGScanning_pred(model,
                                       new_data,
                                       folds = list(1:3, 3:6, 7:10)))

# Real predictions on new data
new_data <- list(matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20),
                 matrix(rnorm(n = 400), ncol = 20, nrow = 20))
new_preds <- MGScanning_pred(model, data = new_data)

## End(Not run)