1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
|
# install xgboost package, see R-package in root folder
require(xgboost)
require(gbm)
require(methods)
testsize <- 550000
dtrain <- read.csv("data/training.csv", header=TRUE, nrows=350001)
dtrain$Label = as.numeric(dtrain$Label=='s')
# gbm.time = system.time({
# gbm.model <- gbm(Label ~ ., data = dtrain[, -c(1,32)], n.trees = 120,
# interaction.depth = 6, shrinkage = 0.1, bag.fraction = 1,
# verbose = TRUE)
# })
# print(gbm.time)
# Test result: 761.48 secs
# dtrain[33] <- dtrain[33] == "s"
# label <- as.numeric(dtrain[[33]])
data <- as.matrix(dtrain[2:31])
weight <- as.numeric(dtrain[[32]]) * testsize / length(label)
sumwpos <- sum(weight * (label==1.0))
sumwneg <- sum(weight * (label==0.0))
print(paste("weight statistics: wpos=", sumwpos, "wneg=", sumwneg, "ratio=", sumwneg / sumwpos))
xgboost.time = list()
threads = c(1,2,4,8,16)
for (i in 1:length(threads)){
thread = threads[i]
xgboost.time[[i]] = system.time({
xgmat <- xgb.DMatrix(data, label = label, weight = weight, missing = -999.0)
param <- list("objective" = "binary:logitraw",
"scale_pos_weight" = sumwneg / sumwpos,
"bst:eta" = 0.1,
"bst:max_depth" = 6,
"eval_metric" = "auc",
"eval_metric" = "ams@0.15",
"nthread" = thread)
watchlist <- list("train" = xgmat)
nrounds = 120
print ("loading data end, start to boost trees")
bst = xgb.train(param, xgmat, nrounds, watchlist );
# save out model
xgb.save(bst, "higgs.model")
print ('finish training')
})
}
xgboost.time
# [[1]]
# user system elapsed
# 99.015 0.051 98.982
#
# [[2]]
# user system elapsed
# 100.268 0.317 55.473
#
# [[3]]
# user system elapsed
# 111.682 0.777 35.963
#
# [[4]]
# user system elapsed
# 149.396 1.851 32.661
#
# [[5]]
# user system elapsed
# 157.390 5.988 40.949
|
