Added test for eta decay (+3 squashed commits)

Squashed commits:
[9109887] Added test for eta decay(+1 squashed commit)
Squashed commits:
[1336bd4] Added tests for eta decay (+2 squashed commit)
Squashed commits:
[91aac2d] Added tests for eta decay (+1 squashed commit)
Squashed commits:
[3ff48e7] Added test for eta decay
[6bb1eed] Rewrote Rd files
[bf0dec4] Added learning_rates for diff eta in each boosting round

R-package/man/predict-xgb.Booster-method.Rd

@@ -5,7 +5,7 @@
 \alias{predict,xgb.Booster-method}
 \title{Predict method for eXtreme Gradient Boosting model}
 \usage{
-\S4method{predict}{xgb.Booster}(object, newdata, missing = NULL,
+\S4method{predict}{xgb.Booster}(object, newdata, missing = NA,
   outputmargin = FALSE, ntreelimit = NULL, predleaf = FALSE)
 }
 \arguments{

R-package/man/xgb.DMatrix.Rd

@@ -4,7 +4,7 @@
 \alias{xgb.DMatrix}
 \title{Contruct xgb.DMatrix object}
 \usage{
-xgb.DMatrix(data, info = list(), missing = 0, ...)
+xgb.DMatrix(data, info = list(), missing = NA, ...)
 }
 \arguments{
 \item{data}{a \code{matrix} object, a \code{dgCMatrix} object or a character

R-package/man/xgb.cv.Rd

@@ -4,11 +4,10 @@
 \alias{xgb.cv}
 \title{Cross Validation}
 \usage{
-xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
+xgb.cv(params = list(), data, nrounds, nfold, label = NULL, missing = NA,
-  missing = NULL, prediction = FALSE, showsd = TRUE, metrics = list(),
+  prediction = FALSE, showsd = TRUE, metrics = list(), obj = NULL,
-  obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
+  feval = NULL, stratified = TRUE, folds = NULL, verbose = T,
-  verbose = T, print.every.n = 1L, early.stop.round = NULL,
+  print.every.n = 1L, early.stop.round = NULL, maximize = NULL, ...)
-  maximize = NULL, ...)
 }
 \arguments{
 \item{params}{the list of parameters. Commonly used ones are:

R-package/man/xgboost.Rd

@@ -4,7 +4,7 @@
 \alias{xgboost}
 \title{eXtreme Gradient Boosting (Tree) library}
 \usage{
-xgboost(data = NULL, label = NULL, missing = NULL, weight = NULL,
+xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
   params = list(), nrounds, verbose = 1, print.every.n = 1L,
   early.stop.round = NULL, maximize = NULL, save_period = 0,
   save_name = "xgboost.model", ...)

R-package/tests/testthat/test_custom_objective.R

@@ -2,12 +2,13 @@ context('Test models with custom objective')
 
 require(xgboost)
 
-test_that("custom objective works", {
 data(agaricus.train, package='xgboost')
 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)
 
+test_that("custom objective works", {
+
   watchlist <- list(eval = dtest, train = dtrain)
   num_round <- 2
 
@@ -45,3 +46,13 @@ test_that("custom objective works", {
   expect_equal(class(bst), "xgb.Booster")
   expect_equal(length(bst$raw), 1064)
 })
+
+test_that("different eta for each boosting round works", {
+  num_round <- 2
+  watchlist <- list(eval = dtest, train = dtrain)
+  param <- list(max.depth=2, eta=1, nthread = 2, silent=1)
+  
+  bst <- xgb.train(param, dtrain, num_round, watchlist, learning_rates = c(0.2, 0.3))
+})
+
+

tests/python/test_models.py

@@ -1,5 +1,6 @@
 import numpy as np
 import xgboost as xgb
+import unittest
 
 dpath = 'demo/data/'
 dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
@@ -7,7 +8,9 @@ dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
 
 rng = np.random.RandomState(1994)
 
-def test_glm():
+class TestModels(unittest.TestCase):
+
+	def test_glm(self):
 		param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear', 'alpha': 0.0001, 'lambda': 1 }
 		watchlist  = [(dtest,'eval'), (dtrain,'train')]
 		num_round = 4
@@ -18,7 +21,25 @@ def test_glm():
 		err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
 		assert err < 0.1
 
-def test_custom_objective():
+	def test_eta_decay(self):
+		param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
+		watchlist  = [(dtest,'eval'), (dtrain,'train')]
+		num_round = 2
+		# learning_rates as a list
+		bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0.4, 0.3])
+		assert isinstance(bst, xgb.core.Booster)
+		# different length
+		num_round = 4
+		self.assertRaises(ValueError, xgb.train, param, dtrain, num_round, watchlist, learning_rates=[0.4, 0.3, 0.2])
+
+		# learning_rates as a customized decay function
+		def eta_decay(ithround, num_boost_round):
+			return num_boost_round / ithround
+		bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=eta_decay)
+		assert isinstance(bst, xgb.core.Booster)
+
+
+	def test_custom_objective(self):
 		param = {'max_depth':2, 'eta':1, 'silent':1 }
 		watchlist  = [(dtest,'eval'), (dtrain,'train')]
 		num_round = 2
@@ -44,7 +65,7 @@ def test_custom_objective():
 		xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
 	       obj = logregobj, feval=evalerror)
 
-def test_fpreproc():
+	def test_fpreproc(self):
 		param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
 		num_round = 2
 		def fpreproc(dtrain, dtest, param):
@@ -55,7 +76,7 @@ def test_fpreproc():
 		xgb.cv(param, dtrain, num_round, nfold=5,
 	       metrics={'auc'}, seed = 0, fpreproc = fpreproc)
 
-def test_show_stdv():
+	def test_show_stdv(self):
 		param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
 		num_round = 2
 		xgb.cv(param, dtrain, num_round, nfold=5,