Merge pull request #582 from terrytangyuan/test
Test (eta decay) and bug fix
This commit is contained in:
Yuan (Terry) Tang
commit
9e1690defe
@ -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{
|
||||
|
||||
@ -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
|
||||
|
||||
@ -4,11 +4,10 @@
|
||||
\alias{xgb.cv}
|
||||
\title{Cross Validation}
|
||||
\usage{
|
||||
xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
|
||||
missing = NULL, prediction = FALSE, showsd = TRUE, metrics = list(),
|
||||
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
|
||||
verbose = T, print.every.n = 1L, early.stop.round = NULL,
|
||||
maximize = NULL, ...)
|
||||
xgb.cv(params = list(), data, nrounds, nfold, label = NULL, missing = NA,
|
||||
prediction = FALSE, showsd = TRUE, metrics = list(), obj = NULL,
|
||||
feval = NULL, stratified = TRUE, folds = NULL, verbose = T,
|
||||
print.every.n = 1L, early.stop.round = NULL, maximize = NULL, ...)
|
||||
}
|
||||
\arguments{
|
||||
\item{params}{the list of parameters. Commonly used ones are:
|
||||
|
||||
@ -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", ...)
|
||||
|
||||
@ -2,11 +2,12 @@ context('Test models with custom objective')
|
||||
|
||||
require(xgboost)
|
||||
|
||||
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", {
|
||||
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)
|
||||
|
||||
watchlist <- list(eval = dtest, train = dtrain)
|
||||
num_round <- 2
|
||||
@ -44,4 +45,4 @@ test_that("custom objective works", {
|
||||
bst <- xgb.train(param, dtrain, num_round, watchlist)
|
||||
expect_equal(class(bst), "xgb.Booster")
|
||||
expect_equal(length(bst$raw), 1064)
|
||||
})
|
||||
})
|
||||
|
||||
@ -98,7 +98,8 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
|
||||
if len(evals) < 1:
|
||||
raise ValueError('For early stopping you need at least one set in evals.')
|
||||
|
||||
sys.stderr.write("Will train until {} error hasn't decreased in {} rounds.\n".format(\
|
||||
if verbose_eval:
|
||||
sys.stderr.write("Will train until {} error hasn't decreased in {} rounds.\n".format(\
|
||||
evals[-1][1], early_stopping_rounds))
|
||||
|
||||
# is params a list of tuples? are we using multiple eval metrics?
|
||||
@ -123,7 +124,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
|
||||
best_msg = ''
|
||||
best_score_i = 0
|
||||
|
||||
if isinstance(learning_rates, list) and len(learning_rates) < num_boost_round:
|
||||
if isinstance(learning_rates, list) and len(learning_rates) != num_boost_round:
|
||||
raise ValueError("Length of list 'learning_rates' has to equal 'num_boost_round'.")
|
||||
|
||||
for i in range(num_boost_round):
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
import numpy as np
|
||||
import xgboost as xgb
|
||||
import unittest
|
||||
|
||||
dpath = 'demo/data/'
|
||||
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
|
||||
@ -7,56 +8,73 @@ dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
|
||||
|
||||
rng = np.random.RandomState(1994)
|
||||
|
||||
def test_glm():
|
||||
param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear', 'alpha': 0.0001, 'lambda': 1 }
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 4
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist)
|
||||
assert isinstance(bst, xgb.core.Booster)
|
||||
preds = bst.predict(dtest)
|
||||
labels = dtest.get_label()
|
||||
err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
|
||||
assert err < 0.1
|
||||
class TestModels(unittest.TestCase):
|
||||
|
||||
def test_custom_objective():
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1 }
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 2
|
||||
def logregobj(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
preds = 1.0 / (1.0 + np.exp(-preds))
|
||||
grad = preds - labels
|
||||
hess = preds * (1.0-preds)
|
||||
return grad, hess
|
||||
def evalerror(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
|
||||
|
||||
# test custom_objective in training
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
|
||||
assert isinstance(bst, xgb.core.Booster)
|
||||
preds = bst.predict(dtest)
|
||||
labels = dtest.get_label()
|
||||
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_glm(self):
|
||||
param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear', 'alpha': 0.0001, 'lambda': 1 }
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 4
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist)
|
||||
assert isinstance(bst, xgb.core.Booster)
|
||||
preds = bst.predict(dtest)
|
||||
labels = dtest.get_label()
|
||||
err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
|
||||
assert err < 0.1
|
||||
|
||||
# test custom_objective in cross-validation
|
||||
xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
|
||||
obj = logregobj, feval=evalerror)
|
||||
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)
|
||||
|
||||
def test_fpreproc():
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
|
||||
num_round = 2
|
||||
def fpreproc(dtrain, dtest, param):
|
||||
label = dtrain.get_label()
|
||||
ratio = float(np.sum(label == 0)) / np.sum(label==1)
|
||||
param['scale_pos_weight'] = ratio
|
||||
return (dtrain, dtest, param)
|
||||
xgb.cv(param, dtrain, num_round, nfold=5,
|
||||
metrics={'auc'}, seed = 0, fpreproc = fpreproc)
|
||||
# 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_show_stdv():
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
|
||||
num_round = 2
|
||||
xgb.cv(param, dtrain, num_round, nfold=5,
|
||||
metrics={'error'}, seed = 0, show_stdv = False)
|
||||
|
||||
def test_custom_objective(self):
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1 }
|
||||
watchlist = [(dtest,'eval'), (dtrain,'train')]
|
||||
num_round = 2
|
||||
def logregobj(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
preds = 1.0 / (1.0 + np.exp(-preds))
|
||||
grad = preds - labels
|
||||
hess = preds * (1.0-preds)
|
||||
return grad, hess
|
||||
def evalerror(preds, dtrain):
|
||||
labels = dtrain.get_label()
|
||||
return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
|
||||
|
||||
# test custom_objective in training
|
||||
bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
|
||||
assert isinstance(bst, xgb.core.Booster)
|
||||
preds = bst.predict(dtest)
|
||||
labels = dtest.get_label()
|
||||
err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
|
||||
assert err < 0.1
|
||||
|
||||
# test custom_objective in cross-validation
|
||||
xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
|
||||
obj = logregobj, feval=evalerror)
|
||||
|
||||
def test_fpreproc(self):
|
||||
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
|
||||
num_round = 2
|
||||
def fpreproc(dtrain, dtest, param):
|
||||
label = dtrain.get_label()
|
||||
ratio = float(np.sum(label == 0)) / np.sum(label==1)
|
||||
param['scale_pos_weight'] = ratio
|
||||
return (dtrain, dtest, param)
|
||||
xgb.cv(param, dtrain, num_round, nfold=5,
|
||||
metrics={'auc'}, seed = 0, fpreproc = fpreproc)
|
||||
|
||||
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,
|
||||
metrics={'error'}, seed = 0, show_stdv = False)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user