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

0.6-4 submission (#1935)

Browse Source
This commit is contained in:
Tong He 2017-01-04 23:31:05 -08:00 committed by GitHub
parent 8b827425b2
commit ce84af7923
5 changed files with 40 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
R-package/DESCRIPTION
View File

@ -1,17 +1,18 @@
Package: xgboost Package: xgboost
Type: Package Type: Package
Title: Extreme Gradient Boosting Title: Extreme Gradient Boosting
Version: 0.6-3 Version: 0.6-4
Date: 2016-12-28 Date: 2017-01-04
Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>, Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>,
Michael Benesty <michael@benesty.fr>, Vadim Khotilovich <khotilovich@gmail.com>, Michael Benesty <michael@benesty.fr>, Vadim Khotilovich <khotilovich@gmail.com>,
Yuan Tang <terrytangyuan@gmail.com> Yuan Tang <terrytangyuan@gmail.com>
Maintainer: Tong He <hetong007@gmail.com> Maintainer: Tong He <hetong007@gmail.com>
Description: Extreme Gradient Boosting, which is an efficient implementation Description: Extreme Gradient Boosting, which is an efficient implementation
of gradient boosting framework. This package is its R interface. The package of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
includes efficient linear model solver and tree learning algorithms. The package This package is its R interface. The package includes efficient linear
can automatically do parallel computation on a single machine which could be model solver and tree learning algorithms. The package can automatically
more than 10 times faster than existing gradient boosting packages. It supports do parallel computation on a single machine which could be more than 10
times faster than existing gradient boosting packages. It supports
various objective functions, including regression, classification and ranking. various objective functions, including regression, classification and ranking.
The package is made to be extensible, so that users are also allowed to define The package is made to be extensible, so that users are also allowed to define
their own objectives easily. their own objectives easily.
@ -23,7 +24,7 @@ Suggests:
knitr, knitr,
rmarkdown, rmarkdown,
ggplot2 (>= 1.0.1), ggplot2 (>= 1.0.1),
DiagrammeR (>= 0.8.1), DiagrammeR (>= 0.9.0),
Ckmeans.1d.dp (>= 3.3.1), Ckmeans.1d.dp (>= 3.3.1),
vcd (>= 1.3), vcd (>= 1.3),
testthat, testthat,

9
R-package/R/xgb.plot.multi.trees.R
View File

@ -78,7 +78,7 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
nodes.dt <- tree.matrix[,.(Quality = sum(Quality)),by = .(abs.node.position, Feature)][,.(Text =paste0(Feature[1:min(length(Feature), features_keep)], " (", Quality[1:min(length(Quality), features_keep)], ")") %>% paste0(collapse = "\n")), by=abs.node.position] nodes.dt <- tree.matrix[,.(Quality = sum(Quality)),by = .(abs.node.position, Feature)][,.(Text =paste0(Feature[1:min(length(Feature), features_keep)], " (", Quality[1:min(length(Quality), features_keep)], ")") %>% paste0(collapse = "\n")), by=abs.node.position]
edges.dt <- tree.matrix[Feature != "Leaf",.(abs.node.position, Yes)] %>% list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>% rbindlist() %>% setnames(c("From", "To")) %>% .[,.N,.(From, To)] %>% .[,N:=NULL] edges.dt <- tree.matrix[Feature != "Leaf",.(abs.node.position, Yes)] %>% list(tree.matrix[Feature != "Leaf",.(abs.node.position, No)]) %>% rbindlist() %>% setnames(c("From", "To")) %>% .[,.N,.(From, To)] %>% .[,N:=NULL]
nodes <- DiagrammeR::create_nodes(nodes = nodes.dt[,abs.node.position], nodes <- DiagrammeR::create_node_df(n = nrow(nodes.dt),
label = nodes.dt[,Text], label = nodes.dt[,Text],
style = "filled", style = "filled",
color = "DimGray", color = "DimGray",
@ -87,8 +87,8 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
fontname = "Helvetica" fontname = "Helvetica"
) )
edges <- DiagrammeR::create_edges(from = edges.dt[,From], edges <- DiagrammeR::create_edge_df(from = match(edges.dt[,From], nodes.dt[,abs.node.position]),
to = edges.dt[,To], to = match(edges.dt[,To], nodes.dt[,abs.node.position]),
color = "DimGray", color = "DimGray",
arrowsize = "1.5", arrowsize = "1.5",
arrowhead = "vee", arrowhead = "vee",
@ -96,8 +96,7 @@ xgb.plot.multi.trees <- function(model, feature_names = NULL, features_keep = 5,
rel = "leading_to") rel = "leading_to")
graph <- DiagrammeR::create_graph(nodes_df = nodes, graph <- DiagrammeR::create_graph(nodes_df = nodes,
edges_df = edges, edges_df = edges)
graph_attrs = "rankdir = LR")
DiagrammeR::render_graph(graph, width = plot_width, height = plot_height) DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
} }

9
R-package/R/xgb.plot.tree.R
View File

@ -49,7 +49,7 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, n_first_tree = NUL
allTrees[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"] allTrees[, filledcolor:= "Beige"][Feature == "Leaf", filledcolor:= "Khaki"]
# rev is used to put the first tree on top. # rev is used to put the first tree on top.
nodes <- DiagrammeR::create_nodes(nodes = allTrees[,ID] %>% rev, nodes <- DiagrammeR::create_node_df(n = length(allTrees[,ID] %>% rev),
label = allTrees[,label] %>% rev, label = allTrees[,label] %>% rev,
style = "filled", style = "filled",
color = "DimGray", color = "DimGray",
@ -59,8 +59,8 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, n_first_tree = NUL
fontname = "Helvetica" fontname = "Helvetica"
) )
edges <- DiagrammeR::create_edges(from = allTrees[Feature != "Leaf", c(ID)] %>% rep(2), edges <- DiagrammeR::create_edge_df(from = match(allTrees[Feature != "Leaf", c(ID)] %>% rep(2), allTrees[,ID] %>% rev),
to = allTrees[Feature != "Leaf", c(Yes, No)], to = match(allTrees[Feature != "Leaf", c(Yes, No)],allTrees[,ID] %>% rev),
label = allTrees[Feature != "Leaf", paste("<",Split)] %>% c(rep("",nrow(allTrees[Feature != "Leaf"]))), label = allTrees[Feature != "Leaf", paste("<",Split)] %>% c(rep("",nrow(allTrees[Feature != "Leaf"]))),
color = "DimGray", color = "DimGray",
arrowsize = "1.5", arrowsize = "1.5",
@ -69,8 +69,7 @@ xgb.plot.tree <- function(feature_names = NULL, model = NULL, n_first_tree = NUL
rel = "leading_to") rel = "leading_to")
graph <- DiagrammeR::create_graph(nodes_df = nodes, graph <- DiagrammeR::create_graph(nodes_df = nodes,
edges_df = edges, edges_df = edges)
graph_attrs = "rankdir = LR")
DiagrammeR::render_graph(graph, width = plot_width, height = plot_height) DiagrammeR::render_graph(graph, width = plot_width, height = plot_height)
} }

11
R-package/tests/testthat/test_basic.R
View File

@ -8,6 +8,8 @@ train <- agaricus.train
test <- agaricus.test test <- agaricus.test
set.seed(1994) set.seed(1994)
windows_flag = grepl('Windows', Sys.info()[['sysname']])
test_that("train and predict binary classification", { test_that("train and predict binary classification", {
nrounds = 2 nrounds = 2
expect_output( expect_output(
@ -148,18 +150,21 @@ test_that("training continuation works", {
bst1 <- xgb.train(param, dtrain, nrounds = 2, watchlist) bst1 <- xgb.train(param, dtrain, nrounds = 2, watchlist)
# continue for two more: # continue for two more:
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1) bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1)
expect_equal(bst$raw, bst2$raw) if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_false(is.null(bst2$evaluation_log)) expect_false(is.null(bst2$evaluation_log))
expect_equal(dim(bst2$evaluation_log), c(4, 2)) expect_equal(dim(bst2$evaluation_log), c(4, 2))
expect_equal(bst2$evaluation_log, bst$evaluation_log) expect_equal(bst2$evaluation_log, bst$evaluation_log)
# test continuing from raw model data # test continuing from raw model data
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1$raw) bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = bst1$raw)
expect_equal(bst$raw, bst2$raw) if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_equal(dim(bst2$evaluation_log), c(2, 2)) expect_equal(dim(bst2$evaluation_log), c(2, 2))
# test continuing from a model in file # test continuing from a model in file
xgb.save(bst1, "xgboost.model") xgb.save(bst1, "xgboost.model")
bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = "xgboost.model") bst2 <- xgb.train(param, dtrain, nrounds = 2, watchlist, xgb_model = "xgboost.model")
expect_equal(bst$raw, bst2$raw) if (!windows_flag)
expect_equal(bst$raw, bst2$raw)
expect_equal(dim(bst2$evaluation_log), c(2, 2)) expect_equal(dim(bst2$evaluation_log), c(2, 2))
}) })

30
R-package/tests/testthat/test_helpers.R
View File

@ -83,20 +83,22 @@ test_that("xgb-attribute functionality", {
expect_null(xgb.attributes(bst)) expect_null(xgb.attributes(bst))
}) })
test_that("xgb-attribute numeric precision", { if (grepl('Windows', Sys.info()[['sysname']]) || grepl('Linux', Sys.info()[['sysname']]) || grepl('Darwin', Sys.info()[['sysname']])) {
# check that lossless conversion works with 17 digits test_that("xgb-attribute numeric precision", {
# numeric -> character -> numeric # check that lossless conversion works with 17 digits
X <- 10^runif(100, -20, 20) # numeric -> character -> numeric
X2X <- as.numeric(format(X, digits = 17)) X <- 10^runif(100, -20, 20)
expect_identical(X, X2X) X2X <- as.numeric(format(X, digits = 17))
# retrieved attributes to be the same as written expect_identical(X, X2X)
for (x in X) { # retrieved attributes to be the same as written
xgb.attr(bst.Tree, "x") <- x for (x in X) {
expect_identical(as.numeric(xgb.attr(bst.Tree, "x")), x) xgb.attr(bst.Tree, "x") <- x
xgb.attributes(bst.Tree) <- list(a = "A", b = x) expect_identical(as.numeric(xgb.attr(bst.Tree, "x")), x)
expect_identical(as.numeric(xgb.attr(bst.Tree, "b")), x) xgb.attributes(bst.Tree) <- list(a = "A", b = x)
} expect_identical(as.numeric(xgb.attr(bst.Tree, "b")), x)
}) }
})
}
test_that("xgb.model.dt.tree works with and without feature names", { test_that("xgb.model.dt.tree works with and without feature names", {
names.dt.trees <- c("Tree", "Node", "ID", "Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover") names.dt.trees <- c("Tree", "Node", "ID", "Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")