tests/testthat/test-num-classes-field.r

In gbm-developers/gbm3: Generalized Boosted Regression Models

##############
# Author: James Hickey
# 
# Series of tests to check compatibility with 1.6 objects is
# present.
#
##############

context("Testing num.classes compatibility")
test_that("num.classes field passed to output - gbm_more", {
  # Given a fit with num.classes set
  ## test Gaussian distribution gbm model
  set.seed(1)
  
  # create some data
  N <- 100
  X1 <- runif(N)
  X2 <- 2*runif(N)
  X3 <- factor(sample(letters[1:4],N,replace=T))
  X4 <- ordered(sample(letters[1:6],N,replace=T))
  X5 <- factor(sample(letters[1:3],N,replace=T))
  X6 <- 3*runif(N)
  mu <- c(-1,0,1,2)[as.numeric(X3)]
  
  SNR <- 10 # signal-to-noise ratio
  Y <- X1**1.5 + 2 * (X2**.5) + mu
  sigma <- sqrt(var(Y)/SNR)
  Y <- Y + rnorm(N,0,sigma)
  
  # create a bunch of missing values
  X1[sample(1:N,size=25)] <- NA
  X3[sample(1:N,size=25)] <- NA
  
  w <- rep(1,N)
  offset <- rep(0, N)
  data <- data.frame(Y=Y,X1=X1,X2=X2,X3=X3,X4=X4,X5=X5,X6=X6)
  
  
  # Set up for new API
  params <- training_params(num_trees=20, interaction_depth=3, min_num_obs_in_node=10, 
                            shrinkage=0.005, bag_fraction=0.5, id=seq(nrow(data)), num_train=N/2, num_features=6)
  dist <- gbm_dist("Gaussian")
  
  fit <- gbmt(Y~X1+X2+X3+X4+X5+X6, data=data, distribution=dist, weights=w, offset=offset,
              train_params=params, var_monotone=c(0, 0, 0, 0, 0, 0), keep_gbm_data=TRUE, cv_folds=10, is_verbose=FALSE)
  fit$num.classes <- 2
  
  # When gbm_more called
  fit_more <- gbm_more(fit)
  
  # Then new object has same num.classes
  expect_equal(fit$num.classes, fit_more$num.classes)
  
})
test_that("num.classes field passed to output - to_old_gbm", {
  # Given a fit with num.classes set
  ## test Gaussian distribution gbm model
  set.seed(1)
  
  # create some data
  N <- 100
  X1 <- runif(N)
  X2 <- 2*runif(N)
  X3 <- factor(sample(letters[1:4],N,replace=T))
  X4 <- ordered(sample(letters[1:6],N,replace=T))
  X5 <- factor(sample(letters[1:3],N,replace=T))
  X6 <- 3*runif(N)
  mu <- c(-1,0,1,2)[as.numeric(X3)]
  
  SNR <- 10 # signal-to-noise ratio
  Y <- X1**1.5 + 2 * (X2**.5) + mu
  sigma <- sqrt(var(Y)/SNR)
  Y <- Y + rnorm(N,0,sigma)
  
  # create a bunch of missing values
  X1[sample(1:N,size=25)] <- NA
  X3[sample(1:N,size=25)] <- NA
  
  w <- rep(1,N)
  offset <- rep(0, N)
  data <- data.frame(Y=Y,X1=X1,X2=X2,X3=X3,X4=X4,X5=X5,X6=X6)
  
  
  # Set up for new API
  params <- training_params(num_trees=20, interaction_depth=3, min_num_obs_in_node=10, 
                            shrinkage=0.005, bag_fraction=0.5, id=seq(nrow(data)), num_train=N/2, num_features=6)
  dist <- gbm_dist("Gaussian")
  
  fit <- gbmt(Y~X1+X2+X3+X4+X5+X6, data=data, distribution=dist, weights=w, offset=offset,
              train_params=params, var_monotone=c(0, 0, 0, 0, 0, 0), keep_gbm_data=TRUE, cv_folds=10, is_verbose=FALSE)
  fit$num.classes <- 2
  
  # When to_old_gbm api
  fit_old <- to_old_gbm(fit)
  
  # Then old gbm object to have num.classes
  expect_equal(fit$num.classes, fit_old$num.classes)
})
test_that("if num.classes > 1 then output of predict is a matrix", {
  # Given a fit with num.classes set
  ## test Gaussian distribution gbm model
  set.seed(1)
  
  # create some data
  N <- 100
  X1 <- runif(N)
  X2 <- 2*runif(N)
  X3 <- factor(sample(letters[1:4],N,replace=T))
  X4 <- ordered(sample(letters[1:6],N,replace=T))
  X5 <- factor(sample(letters[1:3],N,replace=T))
  X6 <- 3*runif(N)
  mu <- c(-1,0,1,2)[as.numeric(X3)]
  
  SNR <- 10 # signal-to-noise ratio
  Y <- X1**1.5 + 2 * (X2**.5) + mu
  sigma <- sqrt(var(Y)/SNR)
  Y <- Y + rnorm(N,0,sigma)
  
  # create a bunch of missing values
  X1[sample(1:N,size=25)] <- NA
  X3[sample(1:N,size=25)] <- NA
  
  w <- rep(1,N)
  offset <- rep(0, N)
  data <- data.frame(Y=Y,X1=X1,X2=X2,X3=X3,X4=X4,X5=X5,X6=X6)
  
  
  # Set up for new API
  params <- training_params(num_trees=20, interaction_depth=3, min_num_obs_in_node=10, 
                            shrinkage=0.005, bag_fraction=0.5, id=seq(nrow(data)), num_train=N/2, num_features=6)
  dist <- gbm_dist("Gaussian")
  
  fit <- gbmt(Y~X1+X2+X3+X4+X5+X6, data=data, distribution=dist, weights=w, offset=offset,
              train_params=params, var_monotone=c(0, 0, 0, 0, 0, 0), keep_gbm_data=TRUE, cv_folds=10, is_verbose=FALSE)
  fit$num.classes <- 2
  
  # When predict called
  # Then predictions will be a matrix
  expect_true(is.matrix(predict(fit, data, 10)))
})