remove old R demo files
This commit is contained in:
unknown
parent
247e0d5d78
commit
a060a2e9a6
@ -1,151 +0,0 @@
|
||||
require(xgboost)
|
||||
require(methods)
|
||||
|
||||
# helper function to read libsvm format this is very badly written, load in dense, and convert to sparse
|
||||
# use this only for demo purpose adopted from
|
||||
# https://github.com/zygmuntz/r-libsvm-format-read-write/blob/master/f_read.libsvm.r
|
||||
read.libsvm <- function(fname, maxcol) {
|
||||
content <- readLines(fname)
|
||||
nline <- length(content)
|
||||
label <- numeric(nline)
|
||||
mat <- matrix(0, nline, maxcol + 1)
|
||||
for (i in 1:nline) {
|
||||
arr <- as.vector(strsplit(content[i], " ")[[1]])
|
||||
label[i] <- as.numeric(arr[[1]])
|
||||
for (j in 2:length(arr)) {
|
||||
kv <- strsplit(arr[j], ":")[[1]]
|
||||
# to avoid 0 index
|
||||
findex <- as.integer(kv[1]) + 1
|
||||
fvalue <- as.numeric(kv[2])
|
||||
mat[i, findex] <- fvalue
|
||||
}
|
||||
}
|
||||
mat <- as(mat, "sparseMatrix")
|
||||
return(list(label = label, data = mat))
|
||||
}
|
||||
|
||||
############################ Test xgb.DMatrix with local file, sparse matrix and dense matrix in R.
|
||||
|
||||
# Directly read in local file
|
||||
dtrain <- xgb.DMatrix("agaricus.txt.train")
|
||||
class(dtrain)
|
||||
|
||||
# read file in R
|
||||
csc <- read.libsvm("agaricus.txt.train", 126)
|
||||
y <- csc$label
|
||||
x <- csc$data
|
||||
|
||||
# x as Sparse Matrix
|
||||
class(x)
|
||||
dtrain <- xgb.DMatrix(x, label = y)
|
||||
|
||||
# x as dense matrix
|
||||
dense.x <- as.matrix(x)
|
||||
dtrain <- xgb.DMatrix(dense.x, label = y)
|
||||
|
||||
############################ Test xgboost with local file, sparse matrix and dense matrix in R.
|
||||
|
||||
# Test with DMatrix object
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Verbose = 0,1,2
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 0)
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 1)
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 2)
|
||||
|
||||
# Test with local file
|
||||
bst <- xgboost(data = "agaricus.txt.train", max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Test with Sparse Matrix
|
||||
bst <- xgboost(data = x, label = y, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Test with dense Matrix
|
||||
bst <- xgboost(data = dense.x, label = y, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
|
||||
############################ Test predict
|
||||
|
||||
# Prediction with DMatrix object
|
||||
dtest <- xgb.DMatrix("agaricus.txt.test")
|
||||
pred <- predict(bst, dtest)
|
||||
|
||||
# Prediction with local test file
|
||||
pred <- predict(bst, "agaricus.txt.test")
|
||||
|
||||
# Prediction with Sparse Matrix
|
||||
csc <- read.libsvm("agaricus.txt.test", 126)
|
||||
test.y <- csc$label
|
||||
test.x <- csc$data
|
||||
pred <- predict(bst, test.x)
|
||||
|
||||
# Extrac label with xgb.getinfo
|
||||
labels <- xgb.getinfo(dtest, "label")
|
||||
err <- as.numeric(sum(as.integer(pred > 0.5) != labels))/length(labels)
|
||||
print(paste("error=", err))
|
||||
|
||||
############################ Save and load model to hard disk
|
||||
|
||||
# save model to binary local file
|
||||
xgb.save(bst, "model.save")
|
||||
|
||||
# load binary model to R
|
||||
bst <- xgb.load("model.save")
|
||||
pred <- predict(bst, test.x)
|
||||
|
||||
# save model to text file
|
||||
xgb.dump(bst, "model.dump")
|
||||
|
||||
# save a DMatrix object to hard disk
|
||||
xgb.DMatrix.save(dtrain, "dtrain.save")
|
||||
|
||||
# load a DMatrix object to R
|
||||
dtrain <- xgb.DMatrix("dtrain.save")
|
||||
|
||||
############################ More flexible training function xgb.train
|
||||
|
||||
param <- list(max_depth = 2, eta = 1, silent = 1, objective = "binary:logistic")
|
||||
watchlist <- list(eval = dtest, train = dtrain)
|
||||
|
||||
# training xgboost model
|
||||
bst <- xgb.train(param, dtrain, nround = 2, watchlist = watchlist)
|
||||
|
||||
############################ cutomsized loss function
|
||||
|
||||
param <- list(max_depth = 2, eta = 1, silent = 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
|
||||
|
||||
# user define objective function, given prediction, return gradient and second order gradient this is
|
||||
# loglikelihood loss
|
||||
logregobj <- function(preds, dtrain) {
|
||||
labels <- xgb.getinfo(dtrain, "label")
|
||||
preds <- 1/(1 + exp(-preds))
|
||||
grad <- preds - labels
|
||||
hess <- preds * (1 - preds)
|
||||
return(list(grad = grad, hess = hess))
|
||||
}
|
||||
# user defined evaluation function, return a list(metric='metric-name', value='metric-value') 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 Take this in mind when you use the customization, and maybe you need write customized
|
||||
# evaluation function
|
||||
evalerror <- function(preds, dtrain) {
|
||||
labels <- xgb.getinfo(dtrain, "label")
|
||||
err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
|
||||
return(list(metric = "error", value = err))
|
||||
}
|
||||
|
||||
# training with customized objective, we can also do step by step training simply look at xgboost.py's
|
||||
# implementation of train
|
||||
bst <- xgb.train(param, dtrain, nround = 2, watchlist, logregobj, evalerror)
|
||||
|
||||
|
||||
@ -1,127 +0,0 @@
|
||||
# load xgboost library
|
||||
require(xgboost)
|
||||
require(methods)
|
||||
|
||||
# helper function to read libsvm format
|
||||
# this is very badly written, load in dense, and convert to sparse
|
||||
# use this only for demo purpose
|
||||
# adopted from https://github.com/zygmuntz/r-libsvm-format-read-write/blob/master/f_read.libsvm.r
|
||||
read.libsvm <- function(fname, maxcol) {
|
||||
content <- readLines(fname)
|
||||
nline <- length(content)
|
||||
label <- numeric(nline)
|
||||
mat <- matrix(0, nline, maxcol+1)
|
||||
for (i in 1:nline) {
|
||||
arr <- as.vector(strsplit(content[i], " ")[[1]])
|
||||
label[i] <- as.numeric(arr[[1]])
|
||||
for (j in 2:length(arr)) {
|
||||
kv <- strsplit(arr[j], ":")[[1]]
|
||||
# to avoid 0 index
|
||||
findex <- as.integer(kv[1]) + 1
|
||||
fvalue <- as.numeric(kv[2])
|
||||
mat[i,findex] <- fvalue
|
||||
}
|
||||
}
|
||||
mat <- as(mat, "sparseMatrix")
|
||||
return(list(label=label, data=mat))
|
||||
}
|
||||
|
||||
# test code here
|
||||
dtrain <- xgb.DMatrix("agaricus.txt.train")
|
||||
dtest <- xgb.DMatrix("agaricus.txt.test")
|
||||
param = list("bst:max_depth"=2, "bst:eta"=1, "silent"=1, "objective"="binary:logistic")
|
||||
watchlist <- list("eval"=dtest,"train"=dtrain)
|
||||
# training xgboost model
|
||||
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
|
||||
# make prediction
|
||||
preds <- xgb.predict(bst, dtest)
|
||||
labels <- xgb.getinfo(dtest, "label")
|
||||
err <- as.numeric(sum(as.integer(preds > 0.5) != labels)) / length(labels)
|
||||
# print error rate
|
||||
print(paste("error=",err))
|
||||
|
||||
# dump model
|
||||
xgb.dump(bst, "dump.raw.txt")
|
||||
# dump model with feature map
|
||||
xgb.dump(bst, "dump.nice.txt", "featmap.txt")
|
||||
|
||||
# save dmatrix into binary buffer
|
||||
succ <- xgb.save(dtest, "dtest.buffer")
|
||||
# save model into file
|
||||
succ <- xgb.save(bst, "xgb.model")
|
||||
# load model and data in
|
||||
bst2 <- xgb.Booster(modelfile="xgb.model")
|
||||
dtest2 <- xgb.DMatrix("dtest.buffer")
|
||||
preds2 <- xgb.predict(bst2, dtest2)
|
||||
# assert they are the same
|
||||
stopifnot(sum(abs(preds2-preds)) == 0)
|
||||
|
||||
###
|
||||
# build dmatrix from sparseMatrix
|
||||
###
|
||||
print ('start running example of build DMatrix from R.sparseMatrix')
|
||||
csc <- read.libsvm("agaricus.txt.train", 126)
|
||||
label <- csc$label
|
||||
data <- csc$data
|
||||
dtrain <- xgb.DMatrix(data, info=list(label=label) )
|
||||
watchlist <- list("eval"=dtest,"train"=dtrain)
|
||||
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
|
||||
|
||||
###
|
||||
# build dmatrix from dense matrix
|
||||
###
|
||||
print ('start running example of build DMatrix from R.Matrix')
|
||||
mat = as.matrix(data)
|
||||
dtrain <- xgb.DMatrix(mat, info=list(label=label) )
|
||||
watchlist <- list("eval"=dtest,"train"=dtrain)
|
||||
bst <- xgb.train(param, dtrain, nround=2, watchlist=watchlist)
|
||||
|
||||
###
|
||||
# advanced: cutomsized loss function
|
||||
#
|
||||
print("start running example to used cutomized objective function")
|
||||
# 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("bst:max_depth" = 2, "bst:eta" = 1, "silent" =1)
|
||||
# user define objective function, given prediction, return gradient and second order gradient
|
||||
# this is loglikelihood loss
|
||||
logregobj <- function(preds, dtrain) {
|
||||
labels <- xgb.getinfo(dtrain, "label")
|
||||
preds <- 1.0 / (1.0 + exp(-preds))
|
||||
grad <- preds - labels
|
||||
hess <- preds * (1.0-preds)
|
||||
return(list(grad=grad, hess=hess))
|
||||
}
|
||||
# user defined evaluation function, return a list(metric="metric-name", value="metric-value")
|
||||
# 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
|
||||
# Take this in mind when you use the customization, and maybe you need write customized evaluation function
|
||||
evalerror <- function(preds, dtrain) {
|
||||
labels <- xgb.getinfo(dtrain, "label")
|
||||
err <- as.numeric(sum(labels != (preds > 0.0))) / length(labels)
|
||||
return(list(metric="error", value=err))
|
||||
}
|
||||
|
||||
# training with customized objective, we can also do step by step training
|
||||
# simply look at xgboost.py"s implementation of train
|
||||
bst <- xgb.train(param, dtrain, nround=2, watchlist, logregobj, evalerror)
|
||||
|
||||
###
|
||||
# advanced: start from a initial base prediction
|
||||
#
|
||||
print ("start running example to start from a initial prediction")
|
||||
# specify parameters via map, definition are same as c++ version
|
||||
param = list("bst:max_depth"=2, "bst:eta"=1, "silent"=1, "objective"="binary:logistic")
|
||||
# train xgboost for 1 round
|
||||
bst <- xgb.train( param, dtrain, 1, watchlist )
|
||||
# Note: we need the margin value instead of transformed prediction in set_base_margin
|
||||
# do predict with output_margin=True, will always give you margin values before logistic transformation
|
||||
ptrain <- xgb.predict(bst, dtrain, outputmargin=TRUE)
|
||||
ptest <- xgb.predict(bst, dtest, outputmargin=TRUE)
|
||||
succ <- xgb.setinfo(dtrain, "base_margin", ptrain)
|
||||
succ <- xgb.setinfo(dtest, "base_margin", ptest)
|
||||
print ("this is result of running from initial prediction")
|
||||
bst <- xgb.train( param, dtrain, 1, watchlist )
|
||||
@ -24,45 +24,104 @@ read.libsvm <- function(fname, maxcol) {
|
||||
return(list(label = label, data = mat))
|
||||
}
|
||||
|
||||
# Parameter setting
|
||||
############################ Test xgb.DMatrix with local file, sparse matrix and dense matrix in R.
|
||||
|
||||
# Directly read in local file
|
||||
dtrain <- xgb.DMatrix("agaricus.txt.train")
|
||||
dtest <- xgb.DMatrix("agaricus.txt.test")
|
||||
param <- list(`bst:max_depth` = 2, `bst:eta` = 1, silent = 1, objective = "binary:logistic")
|
||||
watchlist <- list(eval = dtest, train = dtrain)
|
||||
|
||||
########################### Train from local file
|
||||
|
||||
# Training
|
||||
bst <- xgboost(file = "agaricus.txt.train", params = param, watchlist = watchlist)
|
||||
# Prediction
|
||||
pred <- predict(bst, "agaricus.txt.test")
|
||||
# Performance
|
||||
labels <- xgb.getinfo(dtest, "label")
|
||||
err <- as.numeric(sum(as.integer(pred > 0.5) != labels))/length(labels)
|
||||
print(paste("error=", err))
|
||||
|
||||
########################### Train from R object
|
||||
class(dtrain)
|
||||
|
||||
# read file in R
|
||||
csc <- read.libsvm("agaricus.txt.train", 126)
|
||||
y <- csc$label
|
||||
x <- csc$data
|
||||
|
||||
# x as Sparse Matrix
|
||||
class(x)
|
||||
dtrain <- xgb.DMatrix(x, label = y)
|
||||
|
||||
# Training
|
||||
bst <- xgboost(x, y, params = param, watchlist = watchlist)
|
||||
# Prediction
|
||||
# x as dense matrix
|
||||
dense.x <- as.matrix(x)
|
||||
dtrain <- xgb.DMatrix(dense.x, label = y)
|
||||
|
||||
############################ Test xgboost with local file, sparse matrix and dense matrix in R.
|
||||
|
||||
# Test with DMatrix object
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Verbose = 0,1,2
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 0)
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 1)
|
||||
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic", verbose = 2)
|
||||
|
||||
# Test with local file
|
||||
bst <- xgboost(data = "agaricus.txt.train", max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Test with Sparse Matrix
|
||||
bst <- xgboost(data = x, label = y, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
# Test with dense Matrix
|
||||
bst <- xgboost(data = dense.x, label = y, max_depth = 2, eta = 1,
|
||||
objective = "binary:logistic")
|
||||
|
||||
|
||||
############################ Test predict
|
||||
|
||||
# Prediction with DMatrix object
|
||||
dtest <- xgb.DMatrix("agaricus.txt.test")
|
||||
pred <- predict(bst, dtest)
|
||||
|
||||
# Prediction with local test file
|
||||
pred <- predict(bst, "agaricus.txt.test")
|
||||
# Performance
|
||||
|
||||
# Prediction with Sparse Matrix
|
||||
csc <- read.libsvm("agaricus.txt.test", 126)
|
||||
test.y <- csc$label
|
||||
test.x <- csc$data
|
||||
pred <- predict(bst, test.x)
|
||||
|
||||
# Extrac label with xgb.getinfo
|
||||
labels <- xgb.getinfo(dtest, "label")
|
||||
err <- as.numeric(sum(as.integer(pred > 0.5) != labels))/length(labels)
|
||||
print(paste("error=", err))
|
||||
|
||||
# Training with dense matrix
|
||||
x <- as.matrix(x)
|
||||
bst <- xgboost(x, y, params = param, watchlist = watchlist)
|
||||
############################ Save and load model to hard disk
|
||||
|
||||
########################### Train with customization
|
||||
# save model to binary local file
|
||||
xgb.save(bst, "model.save")
|
||||
|
||||
# load binary model to R
|
||||
bst <- xgb.load("model.save")
|
||||
pred <- predict(bst, test.x)
|
||||
|
||||
# save model to text file
|
||||
xgb.dump(bst, "model.dump")
|
||||
|
||||
# save a DMatrix object to hard disk
|
||||
xgb.DMatrix.save(dtrain, "dtrain.save")
|
||||
|
||||
# load a DMatrix object to R
|
||||
dtrain <- xgb.DMatrix("dtrain.save")
|
||||
|
||||
############################ More flexible training function xgb.train
|
||||
|
||||
param <- list(max_depth = 2, eta = 1, silent = 1, objective = "binary:logistic")
|
||||
watchlist <- list(eval = dtest, train = dtrain)
|
||||
|
||||
# training xgboost model
|
||||
bst <- xgb.train(param, dtrain, nround = 2, watchlist = watchlist)
|
||||
|
||||
############################ cutomsized loss function
|
||||
|
||||
param <- list(max_depth = 2, eta = 1, silent = 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
|
||||
|
||||
# user define objective function, given prediction, return gradient and second order gradient this is
|
||||
# loglikelihood loss
|
||||
@ -85,10 +144,8 @@ evalerror <- function(preds, dtrain) {
|
||||
return(list(metric = "error", value = err))
|
||||
}
|
||||
|
||||
bst <- xgboost(x, y, params = param, watchlist = watchlist, obj = logregobj, feval = evalerror)
|
||||
# training with customized objective, we can also do step by step training simply look at xgboost.py's
|
||||
# implementation of train
|
||||
bst <- xgb.train(param, dtrain, nround = 2, watchlist, logregobj, evalerror)
|
||||
|
||||
############################ Train with previous result
|
||||
|
||||
bst <- xgboost(x, y, params = param, watchlist = watchlist)
|
||||
pred <- predict(bst, "agaricus.txt.train", outputmargin = TRUE)
|
||||
bst2 <- xgboost(x, y, params = param, watchlist = watchlist, margin = pred)
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user