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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
|
#' @export
makeRLearner.classif.xgboost = function() {
makeRLearnerClassif(
cl = "classif.xgboost",
package = "xgboost",
par.set = makeParamSet(
# we pass all of what goes in 'params' directly to ... of xgboost
# makeUntypedLearnerParam(id = "params", default = list()),
makeDiscreteLearnerParam(id = "booster", default = "gbtree", values = c("gbtree", "gblinear", "dart")),
makeUntypedLearnerParam(id = "watchlist", default = NULL, tunable = FALSE),
makeNumericLearnerParam(id = "eta", default = 0.3, lower = 0, upper = 1),
makeNumericLearnerParam(id = "gamma", default = 0, lower = 0),
makeIntegerLearnerParam(id = "max_depth", default = 6L, lower = 1L),
makeNumericLearnerParam(id = "min_child_weight", default = 1, lower = 0),
makeNumericLearnerParam(id = "subsample", default = 1, lower = 0, upper = 1),
makeNumericLearnerParam(id = "colsample_bytree", default = 1, lower = 0, upper = 1),
makeNumericLearnerParam(id = "colsample_bylevel", default = 1, lower = 0, upper = 1),
makeIntegerLearnerParam(id = "num_parallel_tree", default = 1L, lower = 1L),
makeNumericLearnerParam(id = "lambda", default = 1, lower = 0),
makeNumericLearnerParam(id = "lambda_bias", default = 0, lower = 0),
makeNumericLearnerParam(id = "alpha", default = 0, lower = 0),
makeUntypedLearnerParam(id = "objective", default = "binary:logistic", tunable = FALSE),
makeUntypedLearnerParam(id = "eval_metric", default = "error", tunable = FALSE),
makeNumericLearnerParam(id = "base_score", default = 0.5, tunable = FALSE),
makeNumericLearnerParam(id = "max_delta_step", lower = 0, default = 0),
makeNumericLearnerParam(id = "missing", default = NA, tunable = FALSE, when = "both",
special.vals = list(NA, NA_real_, NULL)),
makeIntegerVectorLearnerParam(id = "monotone_constraints", default = 0, lower = -1, upper = 1),
makeNumericLearnerParam(id = "tweedie_variance_power", lower = 1, upper = 2, default = 1.5, requires = quote(objective == "reg:tweedie")),
makeIntegerLearnerParam(id = "nthread", lower = 1L, tunable = FALSE),
makeIntegerLearnerParam(id = "nrounds", default = 1L, lower = 1L),
# FIXME nrounds seems to have no default in xgboost(), if it has 1, par.vals is redundant
makeUntypedLearnerParam(id = "feval", default = NULL, tunable = FALSE),
makeIntegerLearnerParam(id = "verbose", default = 1L, lower = 0L, upper = 2L, tunable = FALSE),
makeIntegerLearnerParam(id = "print_every_n", default = 1L, lower = 1L, tunable = FALSE,
requires = quote(verbose == 1L)),
makeIntegerLearnerParam(id = "early_stopping_rounds", default = NULL, lower = 1L, special.vals = list(NULL), tunable = FALSE),
makeLogicalLearnerParam(id = "maximize", default = NULL, special.vals = list(NULL), tunable = FALSE),
makeDiscreteLearnerParam(id = "sample_type", default = "uniform", values = c("uniform", "weighted"), requires = quote(booster == "dart")),
makeDiscreteLearnerParam(id = "normalize_type", default = "tree", values = c("tree", "forest"), requires = quote(booster == "dart")),
makeNumericLearnerParam(id = "rate_drop", default = 0, lower = 0, upper = 1, requires = quote(booster == "dart")),
makeNumericLearnerParam(id = "skip_drop", default = 0, lower = 0, upper = 1, requires = quote(booster == "dart")),
# TODO: uncomment the following after the next CRAN update, and set max_depth's lower = 0L
#makeLogicalLearnerParam(id = "one_drop", default = FALSE, requires = quote(booster == "dart")),
#makeDiscreteLearnerParam(id = "tree_method", default = "exact", values = c("exact", "hist"), requires = quote(booster != "gblinear")),
#makeDiscreteLearnerParam(id = "grow_policy", default = "depthwise", values = c("depthwise", "lossguide"), requires = quote(tree_method == "hist")),
#makeIntegerLearnerParam(id = "max_leaves", default = 0L, lower = 0L, requires = quote(grow_policy == "lossguide")),
#makeIntegerLearnerParam(id = "max_bin", default = 256L, lower = 2L, requires = quote(tree_method == "hist")),
makeUntypedLearnerParam(id = "callbacks", default = list(), tunable = FALSE)
),
par.vals = list(nrounds = 1L, verbose = 0L),
properties = c("twoclass", "multiclass", "numerics", "prob", "weights", "missings", "featimp"),
name = "eXtreme Gradient Boosting",
short.name = "xgboost",
note = "All settings are passed directly, rather than through `xgboost`'s `params` argument. `nrounds` has been set to `1` and `verbose` to `0` by default. `num_class` is set internally, so do not set this manually.",
callees = "xgboost"
)
}
#' @export
trainLearner.classif.xgboost = function(.learner, .task, .subset, .weights = NULL, ...) {
td = getTaskDesc(.task)
parlist = list(...)
nc = length(td$class.levels)
if (is.null(parlist$objective))
parlist$objective = ifelse(nc == 2L, "binary:logistic", "multi:softprob")
if (.learner$predict.type == "prob" && parlist$objective == "multi:softmax")
stop("objective = 'multi:softmax' does not work with predict.type = 'prob'")
#if we use softprob or softmax as objective we have to add the number of classes 'num_class'
if (parlist$objective %in% c("multi:softprob", "multi:softmax"))
parlist$num_class = nc
task.data = getTaskData(.task, .subset, target.extra = TRUE)
label = match(as.character(task.data$target), td$class.levels) - 1
parlist$data = xgboost::xgb.DMatrix(data = data.matrix(task.data$data), label = label)
if (!is.null(.weights))
xgboost::setinfo(parlist$data, "weight", .weights)
if (is.null(parlist$watchlist))
parlist$watchlist = list(train = parlist$data)
do.call(xgboost::xgb.train, parlist)
}
#' @export
predictLearner.classif.xgboost = function(.learner, .model, .newdata, ...) {
td = .model$task.desc
m = .model$learner.model
cls = td$class.levels
nc = length(cls)
obj = .learner$par.vals$objective
if (is.null(obj))
.learner$par.vals$objective = ifelse(nc == 2L, "binary:logistic", "multi:softprob")
p = predict(m, newdata = data.matrix(.newdata), ...)
if (nc == 2L) { #binaryclass
if (.learner$par.vals$objective == "multi:softprob") {
y = matrix(p, nrow = length(p) / nc, ncol = nc, byrow = TRUE)
colnames(y) = cls
} else {
y = matrix(0, ncol = 2, nrow = nrow(.newdata))
colnames(y) = cls
y[, 1L] = 1 - p
y[, 2L] = p
}
if (.learner$predict.type == "prob") {
return(y)
} else {
p = colnames(y)[max.col(y)]
names(p) = NULL
p = factor(p, levels = colnames(y))
return(p)
}
} else { #multiclass
if (.learner$par.vals$objective == "multi:softmax") {
p = as.factor(p) #special handling for multi:softmax which directly predicts class levels
levels(p) = cls
return(p)
} else {
p = matrix(p, nrow = length(p) / nc, ncol = nc, byrow = TRUE)
colnames(p) = cls
if (.learner$predict.type == "prob") {
return(p)
} else {
ind = max.col(p)
cns = colnames(p)
return(factor(cns[ind], levels = cns))
}
}
}
}
#' @export
getFeatureImportanceLearner.classif.xgboost = function(.learner, .model, ...) {
mod = getLearnerModel(.model, more.unwrap = TRUE)
imp = xgboost::xgb.importance(feature_names = .model$features,
model = mod, ...)
fiv = imp$Gain
setNames(fiv, imp$Feature)
}
|
