class CVPack(object):
""""Auxiliary datastruct to hold one fold of CV."""
def __init__(self, dtrain, dtest, param):
""""Initialize the CVPack"""
self.dtrain = dtrain
self.dtest = dtest
self.watchlist = [(dtrain, 'train'), (dtest, 'test')]
self.bst = Booster(param, [dtrain, dtest])
def update(self, iteration, fobj):
""""Update the boosters for one iteration"""
self.bst.update(self.dtrain, iteration, fobj)
def eval(self, iteration, feval):
""""Evaluate the CVPack for one iteration."""
return self.bst.eval_set(self.watchlist, iteration, feval)
def _train_internal(params,
dtrain,
num_boost_round=10,
evals=(),
obj=None,
feval=None,
xgb_model=None,
callbacks=None):
"""internal training function"""
callbacks = [] if callbacks is None else callbacks
evals = list(evals)
if isinstance(params, dict) \
and 'eval_metric' in params \
and isinstance(params['eval_metric'], list):
params = dict((k, v) for k, v in params.items())
eval_metrics = params['eval_metric']
params.pop("eval_metric", None)
params = list(params.items())
for eval_metric in eval_metrics:
params += [('eval_metric', eval_metric)]
bst = Booster(params, [dtrain] + [d[0] for d in evals])
nboost = 0
num_parallel_tree = 1
if xgb_model is not None:
if not isinstance(xgb_model, STRING_TYPES):
xgb_model = xgb_model.save_raw()
bst = Booster(params, [dtrain] + [d[0] for d in evals],
model_file=xgb_model)
nboost = len(bst.get_dump())
_params = dict(params) if isinstance(params, list) else params
if 'num_parallel_tree' in _params:
num_parallel_tree = _params['num_parallel_tree']
nboost //= num_parallel_tree
if 'num_class' in _params:
nboost //= _params['num_class']
# Distributed code: Load the checkpoint from rabit.
version = bst.load_rabit_checkpoint()
assert (rabit.get_world_size() != 1 or version == 0)
rank = rabit.get_rank()
start_iteration = int(version / 2)
nboost += start_iteration
callbacks_before_iter = [
cb for cb in callbacks if cb.__dict__.get('before_iteration', False)
]
callbacks_after_iter = [
cb for cb in callbacks
if not cb.__dict__.get('before_iteration', False)
]
for i in range(nboost, num_boost_round):
for cb in callbacks_before_iter:
cb(
CallbackEnv(model=bst,
cvfolds=None,
iteration=i,
begin_iteration=start_iteration,
end_iteration=num_boost_round,
rank=rank,
evaluation_result_list=None))
# Distributed code: need to resume to this point.
# Skip the first update if it is a recovery step.
if version % 2 == 0:
bst.update(dtrain, i, obj)
bst.save_rabit_checkpoint()
version += 1
assert (rabit.get_world_size() == 1
or version == rabit.version_number())
nboost += 1
evaluation_result_list = []
# check evaluation result.
if len(evals) != 0:
bst_eval_set = bst.eval_set(evals, i, feval)
if isinstance(bst_eval_set, STRING_TYPES):
msg = bst_eval_set
else:
msg = bst_eval_set.decode()
res = [x.split(':') for x in msg.split()]
evaluation_result_list = [(k, float(v)) for k, v in res[1:]]
try:
for cb in callbacks_after_iter:
cb(
CallbackEnv(model=bst,
cvfolds=None,
iteration=i,
begin_iteration=start_iteration,
end_iteration=num_boost_round,
rank=rank,
evaluation_result_list=evaluation_result_list))
except EarlyStopException:
break
# do checkpoint after evaluation, in case evaluation also updates booster.
bst.save_rabit_checkpoint()
version += 1
if bst.attr('best_score') is not None:
bst.best_score = float(bst.attr('best_score'))
bst.best_iteration = int(bst.attr('best_iteration'))
else:
bst.best_iteration = nboost - 1
bst.best_ntree_limit = (bst.best_iteration + 1) * num_parallel_tree
return bst
def _train_internal(params, dtrain,
num_boost_round=10, evals=(),
obj=None, feval=None,
xgb_model=None, callbacks=None):
"""internal training function"""
callbacks = [] if callbacks is None else callbacks
evals = list(evals)
if isinstance(params, dict) \
and 'eval_metric' in params \
and isinstance(params['eval_metric'], list):
params = dict((k, v) for k, v in params.items())
eval_metrics = params['eval_metric']
params.pop("eval_metric", None)
params = list(params.items())
for eval_metric in eval_metrics:
params += [('eval_metric', eval_metric)]
bst = Booster(params, [dtrain] + [d[0] for d in evals])
nboost = 0
num_parallel_tree = 1
if xgb_model is not None:
if not isinstance(xgb_model, STRING_TYPES):
xgb_model = xgb_model.save_raw()
bst = Booster(params, [dtrain] + [d[0] for d in evals],
model_file=xgb_model)
nboost = len(bst.get_dump())
_params = dict(params) if isinstance(params, list) else params
if 'num_parallel_tree' in _params:
num_parallel_tree = _params['num_parallel_tree']
nboost //= num_parallel_tree
if 'num_class' in _params:
nboost //= _params['num_class']
# Distributed code: Load the checkpoint from rabit.
version = bst.load_rabit_checkpoint()
assert (rabit.get_world_size() != 1 or version == 0)
rank = rabit.get_rank()
start_iteration = int(version / 2)
nboost += start_iteration
callbacks_before_iter = [
cb for cb in callbacks if cb.__dict__.get('before_iteration', False)]
callbacks_after_iter = [
cb for cb in callbacks if
not cb.__dict__.get('before_iteration', False)]
for i in range(nboost, num_boost_round):
for cb in callbacks_before_iter:
cb(CallbackEnv(model=bst,
cvfolds=None,
iteration=i,
begin_iteration=start_iteration,
end_iteration=num_boost_round,
rank=rank,
evaluation_result_list=None))
# Distributed code: need to resume to this point.
# Skip the first update if it is a recovery step.
if version % 2 == 0:
bst.update(dtrain, i, obj)
bst.save_rabit_checkpoint()
version += 1
assert (
rabit.get_world_size() == 1 or version == rabit.version_number())
nboost += 1
evaluation_result_list = []
# check evaluation result.
if len(evals) != 0:
bst_eval_set = bst.eval_set(evals, i, feval)
if isinstance(bst_eval_set, STRING_TYPES):
msg = bst_eval_set
else:
msg = bst_eval_set.decode()
res = [x.split(':') for x in msg.split()]
evaluation_result_list = [(k, float(v)) for k, v in res[1:]]
try:
for cb in callbacks_after_iter:
cb(CallbackEnv(model=bst,
cvfolds=None,
iteration=i,
begin_iteration=start_iteration,
end_iteration=num_boost_round,
rank=rank,
evaluation_result_list=evaluation_result_list))
except EarlyStopException:
break
# do checkpoint after evaluation, in case evaluation also updates booster.
bst.save_rabit_checkpoint()
version += 1
if bst.attr('best_score') is not None:
bst.best_score = float(bst.attr('best_score'))
bst.best_iteration = int(bst.attr('best_iteration'))
else:
bst.best_iteration = nboost - 1
bst.best_ntree_limit = (bst.best_iteration + 1) * num_parallel_tree
return bst