[R-package] Improvements, readability, and bug fixes (#378)

* Define environment in examples (xgboost clash)

* Large R code changes

R-package/demo/early_stopping.R

 require(lightgbm)
 require(methods)
-# load in the agaricus dataset
-data(agaricus.train, package='lightgbm')
-data(agaricus.test, package='lightgbm')
+
+# Load in the agaricus dataset
+data(agaricus.train, package = "lightgbm")
+data(agaricus.test, package = "lightgbm")
+
 dtrain <- lgb.Dataset(agaricus.train$data, label = agaricus.train$label)
 dtest <- lgb.Dataset(agaricus.test$data, label = agaricus.test$label)
-# note: for customized objective function, we leave objective as default
-# note: what we are getting is margin value in prediction
-# you must know what you are doing
-param <- list(num_leaves=4, learning_rate=1)
+
+# Note: for customized objective function, we leave objective as default
+# Note: what we are getting is margin value in prediction
+# You must know what you are doing
+param <- list(num_leaves = 4,
+              learning_rate = 1)
 valids <- list(eval = dtest)
 num_round <- 20
-# user define objective function, given prediction, return gradient and second order gradient
-# this is loglikelihood loss
+
+# User define objective function, given prediction, return gradient and second order gradient
+# This is loglikelihood loss
 logregobj <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
+  preds <- 1 / (1 + exp(-preds))
   grad <- preds - labels
   hess <- preds * (1 - preds)
   return(list(grad = grad, hess = hess))
 }
-# user defined evaluation function, return a pair metric_name, result, higher_better
+
+# User defined evaluation function, return a pair metric_name, result, higher_better
 # NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
+# This may make buildin evalution metric not function properly
+# For example, we are doing logistic loss, the prediction is score before logistic transformation
+# The buildin evaluation error assumes input is after logistic transformation
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(name = "error", value = err, higher_better=FALSE))
+  err <- as.numeric(sum(labels != (preds > 0))) / length(labels)
+  return(list(name = "error", value = err, higher_better = FALSE))
 }
-print ('start training with early Stopping setting')
+print("Start training with early Stopping setting")
 
-bst <- lgb.train(param, dtrain, num_round, valids,
-                 objective = logregobj, eval = evalerror,
+bst <- lgb.train(param,
+                 dtrain,
+                 num_round,
+                 valids,
+                 objective = logregobj,
+                 eval = evalerror,
                  early_stopping_round = 3)

R-package/demo/multiclass.R

 require(lightgbm)
 
-# we load the default iris dataset shipped with R
+# We load the default iris dataset shipped with R
 data(iris)
 
-# we must convert factors to numeric
-# they must be starting from number 0 to use multiclass
-# for instance: 0, 1, 2, 3, 4, 5...
-iris$Species <- as.numeric(as.factor(iris$Species))-1
+# We must convert factors to numeric
+# They must be starting from number 0 to use multiclass
+# For instance: 0, 1, 2, 3, 4, 5...
+iris$Species <- as.numeric(as.factor(iris$Species)) - 1
 
-# we cut the data set into 80% train and 20% validation
-# the 10 last samples of each class are for validation
+# We cut the data set into 80% train and 20% validation
+# The 10 last samples of each class are for validation
 
 train <- as.matrix(iris[c(1:40, 51:90, 101:140), ])
 test <- as.matrix(iris[c(41:50, 91:100, 141:150), ])
-dtrain <- lgb.Dataset(data=train[, 1:4], label=train[, 5])
-dtest <- lgb.Dataset.create.valid(dtrain, data=test[, 1:4], label=test[, 5])
-valids <- list(test=dtest)
+dtrain <- lgb.Dataset(data = train[, 1:4], label = train[, 5])
+dtest <- lgb.Dataset.create.valid(dtrain, data = test[, 1:4], label = test[, 5])
+valids <- list(test = dtest)
 
-# method 1 of training
-params <- list(objective="multiclass", metric="multi_error", num_class=3)
-model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
+# Method 1 of training
+params <- list(objective = "multiclass", metric = "multi_error", num_class = 3)
+model <- lgb.train(params,
+                   dtrain,
+                   100,
+                   valids,
+                   min_data = 1,
+                   learning_rate = 1,
+                   early_stopping_rounds = 10)
 
-# we can predict on test data, outputs a 90-length vector
-# order: obs1 class1, obs1 class2, obs1 class3, obs2 class1, obs2 class2, obs2 class3...
+# We can predict on test data, outputs a 90-length vector
+# Order: obs1 class1, obs1 class2, obs1 class3, obs2 class1, obs2 class2, obs2 class3...
 my_preds <- predict(model, test[, 1:4])
 
-# method 2 of training, identical
-model <- lgb.train(list(), dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10, objective="multiclass", metric="multi_error", num_class=3)
+# Method 2 of training, identical
+model <- lgb.train(list(),
+                   dtrain,
+                   100,
+                   valids,
+                   min_data = 1,
+                   learning_rate = 1,
+                   early_stopping_rounds = 10,
+                   objective = "multiclass",
+                   metric = "multi_error",
+                   num_class = 3)
 
-# we can predict on test data, identical
+# We can predict on test data, identical
 my_preds <- predict(model, test[, 1:4])
 
-# a (30x3) matrix with the predictions, use parameter reshape
+# A (30x3) matrix with the predictions, use parameter reshape
 # class1 class2 class3
 #   obs1   obs1   obs1
 #   obs2   obs2   obs2
 #   ....   ....   ....
-my_preds <- predict(model, test[, 1:4], reshape=TRUE)
+my_preds <- predict(model, test[, 1:4], reshape = TRUE)
 
-# we can also get the predicted scores before the Sigmoid/Softmax application
-my_preds <- predict(model, test[, 1:4], rawscore=TRUE)
+# We can also get the predicted scores before the Sigmoid/Softmax application
+my_preds <- predict(model, test[, 1:4], rawscore = TRUE)
 
-# raw score predictions as matrix instead of vector
-my_preds <- predict(model, test[, 1:4], rawscore=TRUE, reshape=TRUE)
+# Raw score predictions as matrix instead of vector
+my_preds <- predict(model, test[, 1:4], rawscore = TRUE, reshape = TRUE)
 
-# we can also get the leaf index
-my_preds <- predict(model, test[, 1:4], predleaf=TRUE)
+# We can also get the leaf index
+my_preds <- predict(model, test[, 1:4], predleaf = TRUE)
 
-# preddict leaf index as matrix instead of vector
-my_preds <- predict(model, test[, 1:4], predleaf=TRUE, reshape=TRUE)
+# Predict leaf index as matrix instead of vector
+my_preds <- predict(model, test[, 1:4], predleaf = TRUE, reshape = TRUE)

R-package/man/dim.Rd

@@ -22,14 +22,16 @@ Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
 be directly used with an \code{lgb.Dataset} object.
 }
 \examples{
-dontrun{
-  data(agaricus.train, package='lightgbm')
-  train <- agaricus.train
-  dtrain <- lgb.Dataset(train$data, label=train$label)
+\dontrun{
+library(lightgbm)
+data(agaricus.train, package = "lightgbm")
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
 
-  stopifnot(nrow(dtrain) == nrow(train$data))
-  stopifnot(ncol(dtrain) == ncol(train$data))
-  stopifnot(all(dim(dtrain) == dim(train$data)))
+stopifnot(nrow(dtrain) == nrow(train$data))
+stopifnot(ncol(dtrain) == ncol(train$data))
+stopifnot(all(dim(dtrain) == dim(train$data)))
 }
+
 }
 

R-package/man/dimnames.lgb.Dataset.Rd

@@ -24,15 +24,17 @@ Generic \code{dimnames} methods are used by \code{colnames}.
 Since row names are irrelevant, it is recommended to use \code{colnames} directly.
 }
 \examples{
-dontrun{
-  data(agaricus.train, package='lightgbm')
-  train <- agaricus.train
-  dtrain <- lgb.Dataset(train$data, label=train$label)
-  lgb.Dataset.construct(dtrain)
-  dimnames(dtrain)
-  colnames(dtrain)
-  colnames(dtrain) <- make.names(1:ncol(train$data))
-  print(dtrain, verbose=TRUE)
+\dontrun{
+library(lightgbm)
+data(agaricus.train, package = "lightgbm")
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+lgb.Dataset.construct(dtrain)
+dimnames(dtrain)
+colnames(dtrain)
+colnames(dtrain) <- make.names(1:ncol(train$data))
+print(dtrain, verbose = TRUE)
 }
+
 }
 

R-package/man/getinfo.Rd

@@ -34,15 +34,18 @@ The \code{name} field can be one of the following:
 }
 \examples{
 \dontrun{
-  data(agaricus.train, package='lightgbm')
-  train <- agaricus.train
-  dtrain <- lgb.Dataset(train$data, label=train$label)
-  lgb.Dataset.construct(dtrain)
-  labels <- getinfo(dtrain, 'label')
-  setinfo(dtrain, 'label', 1-labels)
+library(lightgbm)
+data(agaricus.train, package = "lightgbm")
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+lgb.Dataset.construct(dtrain)
 
-  labels2 <- getinfo(dtrain, 'label')
-  stopifnot(all(labels2 == 1-labels))
+labels <- lightgbm::getinfo(dtrain, "label")
+lightgbm::setinfo(dtrain, "label", 1 - labels)
+
+labels2 <- lightgbm::getinfo(dtrain, "label")
+stopifnot(all(labels2 == 1 - labels))
 }
+
 }
 

R-package/man/lgb.Dataset.Rd

@@ -33,12 +33,14 @@ or local file (that was created previously by saving an \code{lgb.Dataset}).
 }
 \examples{
 \dontrun{
-  data(agaricus.train, package='lightgbm')
-  train <- agaricus.train
-  dtrain <- lgb.Dataset(train$data, label=train$label)
-  lgb.Dataset.save(dtrain, 'lgb.Dataset.data')
-  dtrain <- lgb.Dataset('lgb.Dataset.data')
-  lgb.Dataset.construct(dtrain)
+library(lightgbm)
+data(agaricus.train, package = "lightgbm")
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+lgb.Dataset.save(dtrain, "lgb.Dataset.data")
+dtrain <- lgb.Dataset("lgb.Dataset.data")
+lgb.Dataset.construct(dtrain)
 }
+
 }