Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[R] replace uses of T and F with TRUE and FALSE (#5778)

Browse Source 
* [R-package] replace uses of T and F with TRUE and FALSE

* enable linting

* Remove skip

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>
This commit is contained in:
James Lamb 2020-06-11 11:08:02 +01:00 committed by GitHub
parent cb7f7e542c
commit c35be9dc40
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
15 changed files with 32 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
R-package/demo/basic_walkthrough.R
View File

@ -100,7 +100,7 @@ print(paste("test-error=", err))
# You can dump the tree you learned using xgb.dump into a text file
dump_path = file.path(tempdir(), 'dump.raw.txt')
xgb.dump(bst, dump_path, with_stats = T)
xgb.dump(bst, dump_path, with_stats = TRUE)
# Finally, you can check which features are the most important.
print("Most important features (look at column Gain):")

2
R-package/demo/caret_wrapper.R
View File

@ -9,7 +9,7 @@ require(e1071)
# Load Arthritis dataset in memory.
data(Arthritis)
# Create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
df <- data.table(Arthritis, keep.rownames = F)
df <- data.table(Arthritis, keep.rownames = FALSE)
# Let's add some new categorical features to see if it helps. Of course these feature are highly correlated to the Age feature. Usually it's not a good thing in ML, but Tree algorithms (including boosted trees) are able to select the best features, even in case of highly correlated features.
# For the first feature we create groups of age by rounding the real age. Note that we transform it to factor (categorical data) so the algorithm treat them as independant values.

2
R-package/demo/create_sparse_matrix.R
View File

@ -19,7 +19,7 @@ if (!require(vcd)) {
data(Arthritis)
# create a copy of the dataset with data.table package (data.table is 100% compliant with R dataframe but its syntax is a lot more consistent and its performance are really good).
df <- data.table(Arthritis, keep.rownames = F)
df <- data.table(Arthritis, keep.rownames = FALSE)
# Let's have a look to the data.table
cat("Print the dataset\n")

8
R-package/demo/interaction_constraints.R
View File

@ -19,18 +19,18 @@ treeInteractions <- function(input_tree, input_max_depth){
setorderv(parents_left, 'ID_merge')
setorderv(parents_right, 'ID_merge')
trees <- merge(trees, parents_left, by='ID_merge', all.x=T)
trees <- merge(trees, parents_left, by='ID_merge', all.x=TRUE)
trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
trees[, c('i.id','i.feature'):=NULL]
trees <- merge(trees, parents_right, by='ID_merge', all.x=T)
trees <- merge(trees, parents_right, by='ID_merge', all.x=TRUE)
trees[!is.na(i.id), c(paste0('parent_', i-1), paste0('parent_feat_', i-1)):=list(i.id, i.feature)]
trees[, c('i.id','i.feature'):=NULL]
}
# Extract nodes with interactions
interaction_trees <- trees[!is.na(Split) & !is.na(parent_1),
c('Feature',paste0('parent_feat_',1:(input_max_depth-1))), with=F]
c('Feature',paste0('parent_feat_',1:(input_max_depth-1))), with=FALSE]
interaction_trees_split <- split(interaction_trees, 1:nrow(interaction_trees))
interaction_list <- lapply(interaction_trees_split, as.character)
@ -96,7 +96,7 @@ x1 <- sort(unique(x[['V1']]))
for (i in 1:length(x1)){
testdata <- copy(x[, -c('V1')])
testdata[['V1']] <- x1[i]
testdata <- testdata[, paste0('V',1:10), with=F]
testdata <- testdata[, paste0('V',1:10), with=FALSE]
pred <- predict(bst3, as.matrix(testdata))
# Should not print out anything due to monotonic constraints

2
R-package/demo/tweedie_regression.R
View File

@ -13,7 +13,7 @@ exclude <- c('POLICYNO', 'PLCYDATE', 'CLM_FREQ5', 'CLM_AMT5', 'CLM_FLAG', 'IN_Y
# retains the missing values
# NOTE: this dataset is comes ready out of the box
options(na.action = 'na.pass')
x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = F])
x <- sparse.model.matrix(~ . - 1, data = dt[, -exclude, with = FALSE])
options(na.action = 'na.omit')
# response

10
R-package/tests/testthat/test_helpers.R
View File

@ -12,7 +12,7 @@ flag_32bit = .Machine$sizeof.pointer != 8
set.seed(1982)
data(Arthritis)
df <- data.table(Arthritis, keep.rownames = F)
df <- data.table(Arthritis, keep.rownames = FALSE)
df[,AgeDiscret := as.factor(round(Age / 10,0))]
df[,AgeCat := as.factor(ifelse(Age > 30, "Old", "Young"))]
df[,ID := NULL]
@ -47,7 +47,7 @@ test_that("xgb.dump works", {
if (!flag_32bit)
expect_length(xgb.dump(bst.Tree), 200)
dump_file = file.path(tempdir(), 'xgb.model.dump')
expect_true(xgb.dump(bst.Tree, dump_file, with_stats = T))
expect_true(xgb.dump(bst.Tree, dump_file, with_stats = TRUE))
expect_true(file.exists(dump_file))
expect_gt(file.size(dump_file), 8000)
@ -160,7 +160,7 @@ test_that("SHAPs sum to predictions, with or without DART", {
objective = "reg:squarederror",
eval_metric = "rmse"),
if (booster == "dart")
list(rate_drop = .01, one_drop = T)),
list(rate_drop = .01, one_drop = TRUE)),
data = d,
label = y,
nrounds = nrounds)
@ -168,8 +168,8 @@ test_that("SHAPs sum to predictions, with or without DART", {
pr <- function(...)
predict(fit, newdata = d, ...)
pred <- pr()
shap <- pr(predcontrib = T)
shapi <- pr(predinteraction = T)
shap <- pr(predcontrib = TRUE)
shapi <- pr(predinteraction = TRUE)
tol = 1e-5
expect_equal(rowSums(shap), pred, tol = tol)

2
R-package/tests/testthat/test_interactions.R
View File

@ -107,7 +107,7 @@ test_that("SHAP contribution values are not NAN", {
shaps <- as.data.frame(predict(fit,
newdata = as.matrix(subset(d, fold == 1)[, ivs]),
predcontrib = T))
predcontrib = TRUE))
result <- cbind(shaps, sum = rowSums(shaps), pred = predict(fit,
newdata = as.matrix(subset(d, fold == 1)[, ivs])))

7
R-package/tests/testthat/test_lint.R
View File

@ -1,8 +1,6 @@
context("Code is of high quality and lint free")
test_that("Code Lint", {
skip_on_cran()
skip_on_travis()
skip_if_not_installed("lintr")
my_linters <- list(
absolute_paths_linter=lintr::absolute_paths_linter,
assignment_linter=lintr::assignment_linter,
@ -21,7 +19,8 @@ test_that("Code Lint", {
spaces_inside_linter=lintr::spaces_inside_linter,
spaces_left_parentheses_linter=lintr::spaces_left_parentheses_linter,
trailing_blank_lines_linter=lintr::trailing_blank_lines_linter,
trailing_whitespace_linter=lintr::trailing_whitespace_linter
trailing_whitespace_linter=lintr::trailing_whitespace_linter,
true_false=lintr::T_and_F_symbol_linter
)
# lintr::expect_lint_free(linters=my_linters) # uncomment this if you want to check code quality
lintr::expect_lint_free(linters=my_linters) # uncomment this if you want to check code quality
})

2
R-package/vignettes/discoverYourData.Rmd
View File

@ -63,7 +63,7 @@ The first step is to load `Arthritis` dataset in memory and wrap it with `data.t
```{r, results='hide'}
data(Arthritis)
df <- data.table(Arthritis, keep.rownames = F)
df <- data.table(Arthritis, keep.rownames = FALSE)
```
> `data.table` is 100% compliant with **R** `data.frame` but its syntax is more consistent and its performance for large dataset is [best in class](http://stackoverflow.com/questions/21435339/data-table-vs-dplyr-can-one-do-something-well-the-other-cant-or-does-poorly) (`dplyr` from **R** and `Pandas` from **Python** [included](https://github.com/Rdatatable/data.table/wiki/Benchmarks-%3A-Grouping)). Some parts of **Xgboost** **R** package use `data.table`.

2
R-package/vignettes/xgboostPresentation.Rmd
View File

@ -363,7 +363,7 @@ xgb.plot.importance(importance_matrix = importance_matrix)
You can dump the tree you learned using `xgb.dump` into a text file.
```{r dump, message=T, warning=F}
xgb.dump(bst, with_stats = T)
xgb.dump(bst, with_stats = TRUE)
```
You can plot the trees from your model using ```xgb.plot.tree``

2
demo/data/gen_autoclaims.R
View File

@ -14,5 +14,5 @@ data$STATE = as.factor(data$STATE)
data$CLASS = as.factor(data$CLASS)
data$GENDER = as.factor(data$GENDER)
data.dummy <- dummy.data.frame(data, dummy.class='factor', omit.constants=T);
data.dummy <- dummy.data.frame(data, dummy.class='factor', omit.constants=TRUE);
write.table(data.dummy, 'autoclaims.csv', sep=',', row.names=F, col.names=F, quote=F)

4
demo/kaggle-otto/otto_train_pred.R
View File

@ -1,8 +1,8 @@
require(xgboost)
require(methods)
train = read.csv('data/train.csv',header=TRUE,stringsAsFactors = F)
test = read.csv('data/test.csv',header=TRUE,stringsAsFactors = F)
train = read.csv('data/train.csv',header=TRUE,stringsAsFactors = FALSE)
test = read.csv('data/test.csv',header=TRUE,stringsAsFactors = FALSE)
train = train[,-1]
test = test[,-1]

16
demo/kaggle-otto/understandingXGBoostModel.Rmd
View File

@ -30,8 +30,8 @@ require(xgboost)
require(methods)
require(data.table)
require(magrittr)
train <- fread('data/train.csv', header = T, stringsAsFactors = F)
test <- fread('data/test.csv', header=TRUE, stringsAsFactors = F)
train <- fread('data/train.csv', header = T, stringsAsFactors = FALSE)
test <- fread('data/test.csv', header=TRUE, stringsAsFactors = FALSE)
```
> `magrittr` and `data.table` are here to make the code cleaner and much more rapid.
@ -42,13 +42,13 @@ Let's explore the dataset.
dim(train)
# Training content
train[1:6,1:5, with =F]
train[1:6,1:5, with =FALSE]
# Test dataset dimensions
dim(test)
# Test content
test[1:6,1:5, with =F]
test[1:6,1:5, with =FALSE]
```
> We only display the 6 first rows and 5 first columns for convenience
@ -70,7 +70,7 @@ According to its description, the **Otto** challenge is a multi class classifica
```{r searchLabel}
# Check the content of the last column
train[1:6, ncol(train), with = F]
train[1:6, ncol(train), with = FALSE]
# Save the name of the last column
nameLastCol <- names(train)[ncol(train)]
```
@ -86,7 +86,7 @@ For that purpose, we will:
```{r classToIntegers}
# Convert from classes to numbers
y <- train[, nameLastCol, with = F][[1]] %>% gsub('Class_','',.) %>% {as.integer(.) -1}
y <- train[, nameLastCol, with = FALSE][[1]] %>% gsub('Class_','',.) %>% {as.integer(.) -1}
# Display the first 5 levels
y[1:5]
@ -95,7 +95,7 @@ y[1:5]
We remove label column from training dataset, otherwise **XGBoost** would use it to guess the labels!
```{r deleteCols, results='hide'}
train[, nameLastCol:=NULL, with = F]
train[, nameLastCol:=NULL, with = FALSE]
```
`data.table` is an awesome implementation of data.frame, unfortunately it is not a format supported natively by **XGBoost**. We need to convert both datasets (training and test) in `numeric` Matrix format.
@ -163,7 +163,7 @@ Each *split* is done on one feature only at one value.
Let's see what the model looks like.
```{r modelDump}
model <- xgb.dump(bst, with.stats = T)
model <- xgb.dump(bst, with.stats = TRUE)
model[1:10]
```
> For convenience, we are displaying the first 10 lines of the model only.

2
doc/R-package/discoverYourData.md
View File

@ -52,7 +52,7 @@ The first step is to load `Arthritis` dataset in memory and wrap it with `data.t
```r
data(Arthritis)
df <- data.table(Arthritis, keep.rownames = F)
df <- data.table(Arthritis, keep.rownames = FALSE)
```
> `data.table` is 100% compliant with **R** `data.frame` but its syntax is more consistent and its performance for large dataset is [best in class](http://stackoverflow.com/questions/21435339/data-table-vs-dplyr-can-one-do-something-well-the-other-cant-or-does-poorly) (`dplyr` from **R** and `Pandas` from **Python** [included](https://github.com/Rdatatable/data.table/wiki/Benchmarks-%3A-Grouping)). Some parts of **Xgboost** **R** package use `data.table`.

2
doc/R-package/xgboostPresentation.md
View File

@ -489,7 +489,7 @@ You can dump the tree you learned using `xgb.dump` into a text file.
```r
xgb.dump(bst, with_stats = T)
xgb.dump(bst, with_stats = TRUE)
```
```