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

[R] adopt demos and vignettes to a more consistent parameter style

Browse Source
This commit is contained in:
Vadim Khotilovich
2016-06-27 02:00:39 -05:00
parent a0aa305268
commit 3b6b344561
11 changed files with 59 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
R-package/demo/basic_walkthrough.R
View File

@@ -1,7 +1,8 @@
require(xgboost)
require(methods)
# we load in the agaricus dataset
# In this example, we are aiming to predict whether a mushroom can be eaten
# In this example, we are aiming to predict whether a mushroom is edible
data(agaricus.train, package='xgboost')
data(agaricus.test, package='xgboost')
train <- agaricus.train
@@ -15,33 +16,33 @@ class(train$data)
# note: we are putting in sparse matrix here, xgboost naturally handles sparse input
# use sparse matrix when your feature is sparse(e.g. when you are using one-hot encoding vector)
print("Training xgboost with sparseMatrix")
bst <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nround = 2,
bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, nrounds = 2,
nthread = 2, objective = "binary:logistic")
# alternatively, you can put in dense matrix, i.e. basic R-matrix
print("Training xgboost with Matrix")
bst <- xgboost(data = as.matrix(train$data), label = train$label, max.depth = 2, eta = 1, nround = 2,
bst <- xgboost(data = as.matrix(train$data), label = train$label, max_depth = 2, eta = 1, nrounds = 2,
nthread = 2, objective = "binary:logistic")
# you can also put in xgb.DMatrix object, which stores label, data and other meta datas needed for advanced features
print("Training xgboost with xgb.DMatrix")
dtrain <- xgb.DMatrix(data = train$data, label = train$label)
bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2, nthread = 2,
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, nthread = 2,
objective = "binary:logistic")
# Verbose = 0,1,2
print("Train xgboost with verbose 0, no message")
bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
nthread = 2, objective = "binary:logistic", verbose = 0)
print("Train xgboost with verbose 1, print evaluation metric")
bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
nthread = 2, objective = "binary:logistic", verbose = 1)
print("Train xgboost with verbose 2, also print information about tree")
bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
bst <- xgboost(data = dtrain, max_depth = 2, eta = 1, nrounds = 2,
nthread = 2, objective = "binary:logistic", verbose = 2)
# you can also specify data as file path to a LibSVM format input
# since we do not have this file with us, the following line is just for illustration
# bst <- xgboost(data = 'agaricus.train.svm', max.depth = 2, eta = 1, nround = 2,objective = "binary:logistic")
# bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nrounds = 2,objective = "binary:logistic")
#--------------------basic prediction using xgboost--------------
# you can do prediction using the following line
@@ -77,19 +78,19 @@ watchlist <- list(train=dtrain, test=dtest)
# to train with watchlist, use xgb.train, which contains more advanced features
# watchlist allows us to monitor the evaluation result on all data in the list
print("Train xgboost using xgb.train with watchlist")
bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nround=2, watchlist=watchlist,
bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
nthread = 2, objective = "binary:logistic")
# we can change evaluation metrics, or use multiple evaluation metrics
print("train xgboost using xgb.train with watchlist, watch logloss and error")
bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nround=2, watchlist=watchlist,
eval.metric = "error", eval.metric = "logloss",
bst <- xgb.train(data=dtrain, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
eval_metric = "error", eval_metric = "logloss",
nthread = 2, objective = "binary:logistic")
# xgb.DMatrix can also be saved using xgb.DMatrix.save
xgb.DMatrix.save(dtrain, "dtrain.buffer")
# to load it in, simply call xgb.DMatrix
dtrain2 <- xgb.DMatrix("dtrain.buffer")
bst <- xgb.train(data=dtrain2, max.depth=2, eta=1, nround=2, watchlist=watchlist,
bst <- xgb.train(data=dtrain2, max_depth=2, eta=1, nrounds=2, watchlist=watchlist,
nthread = 2, objective = "binary:logistic")
# information can be extracted from xgb.DMatrix using getinfo
label = getinfo(dtest, "label")
@@ -98,11 +99,11 @@ err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
print(paste("test-error=", err))
# You can dump the tree you learned using xgb.dump into a text file
xgb.dump(bst, "dump.raw.txt", with.stats = T)
xgb.dump(bst, "dump.raw.txt", with_stats = T)
# Finally, you can check which features are the most important.
print("Most important features (look at column Gain):")
imp_matrix <- xgb.importance(feature_names = train$data@Dimnames[[2]], model = bst)
imp_matrix <- xgb.importance(feature_names = colnames(train$data), model = bst)
print(imp_matrix)
# Feature importance bar plot by gain

4
R-package/demo/boost_from_prediction.R
View File

@@ -11,8 +11,8 @@ watchlist <- list(eval = dtest, train = dtrain)
#
print('start running example to start from a initial prediction')
# train xgboost for 1 round
param <- list(max.depth=2,eta=1,nthread = 2, silent=1,objective='binary:logistic')
bst <- xgb.train( param, dtrain, 1, watchlist )
param <- list(max_depth=2, eta=1, nthread = 2, silent=1, objective='binary:logistic')
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 <- predict(bst, dtrain, outputmargin=TRUE)

7
R-package/demo/create_sparse_matrix.R
View File

@@ -65,11 +65,10 @@ output_vector = df[,Y:=0][Improved == "Marked",Y:=1][,Y]
# Following is the same process as other demo
cat("Learning...\n")
bst <- xgboost(data = sparse_matrix, label = output_vector, max.depth = 9,
eta = 1, nthread = 2, nround = 10,objective = "binary:logistic")
bst <- xgboost(data = sparse_matrix, label = output_vector, max_depth = 9,
eta = 1, nthread = 2, nrounds = 10, objective = "binary:logistic")
# sparse_matrix@Dimnames[[2]] represents the column names of the sparse matrix.
importance <- xgb.importance(feature_names = sparse_matrix@Dimnames[[2]], model = bst)
importance <- xgb.importance(feature_names = colnames(sparse_matrix), model = bst)
print(importance)
# According to the matrix below, the most important feature in this dataset to predict if the treatment will work is the Age. The second most important feature is having received a placebo or not. The sex is third. Then we see our generated features (AgeDiscret). We can see that their contribution is very low (Gain column).

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

@@ -6,7 +6,7 @@ dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
nround <- 2
param <- list(max.depth=2,eta=1,silent=1,nthread = 2, objective='binary:logistic')
param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
cat('running cross validation\n')
# do cross validation, this will print result out as
@@ -19,7 +19,7 @@ cat('running cross validation, disable standard deviation display\n')
# [iteration] metric_name:mean_value+std_value
# std_value is standard deviation of the metric
xgb.cv(param, dtrain, nround, nfold=5,
metrics={'error'}, showsd = FALSE)
metrics='error', showsd = FALSE)
###
# you can also do cross validation with cutomized loss function
@@ -40,12 +40,12 @@ evalerror <- function(preds, dtrain) {
return(list(metric = "error", value = err))
}
param <- list(max.depth=2,eta=1,silent=1,
param <- list(max_depth=2, eta=1, silent=1,
objective = logregobj, eval_metric = evalerror)
# train with customized objective
xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5)
# do cross validation with prediction values for each fold
res <- xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5, prediction = TRUE)
res$dt
res$evaluation_log
length(res$pred)

4
R-package/demo/custom_objective.R
View File

@@ -33,7 +33,7 @@ evalerror <- function(preds, dtrain) {
return(list(metric = "error", value = err))
}
param <- list(max.depth=2, eta=1, nthread = 2, silent=1,
param <- list(max_depth=2, eta=1, nthread = 2, silent=1,
objective=logregobj, eval_metric=evalerror)
print ('start training with user customized objective')
# training with customized objective, we can also do step by step training
@@ -57,7 +57,7 @@ logregobjattr <- function(preds, dtrain) {
hess <- preds * (1 - preds)
return(list(grad = grad, hess = hess))
}
param <- list(max.depth=2, eta=1, nthread = 2, silent=1,
param <- list(max_depth=2, eta=1, nthread = 2, silent=1,
objective=logregobjattr, eval_metric=evalerror)
print ('start training with user customized objective, with additional attributes in DMatrix')
# training with customized objective, we can also do step by step training

6
R-package/demo/early_stopping.R
View File

@@ -7,7 +7,7 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
# 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(max.depth=2,eta=1,nthread = 2, silent=1)
param <- list(max_depth=2, eta=1, nthread = 2, silent=1)
watchlist <- list(eval = dtest)
num_round <- 20
# user define objective function, given prediction, return gradient and second order gradient
@@ -34,7 +34,7 @@ print ('start training with early Stopping setting')
bst <- xgb.train(param, dtrain, num_round, watchlist,
objective = logregobj, eval_metric = evalerror, maximize = FALSE,
early.stop.round = 3)
early_stopping_round = 3)
bst <- xgb.cv(param, dtrain, num_round, nfold = 5,
objective = logregobj, eval_metric = evalerror,
maximize = FALSE, early.stop.round = 3)
maximize = FALSE, early_stopping_rounds = 3)

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

@@ -5,7 +5,7 @@ data(agaricus.test, package='xgboost')
dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
param <- list(max.depth=2,eta=1,silent=1,objective='binary:logistic')
param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
watchlist <- list(eval = dtest, train = dtrain)
nround = 2

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

@@ -10,7 +10,7 @@ data(agaricus.test, package='xgboost')
dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
param <- list(max.depth=2, eta=1, silent=1, objective='binary:logistic')
param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
nround = 4
# training the model for two rounds