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

Python verbose_eval extension

Browse Source 
This is an extension of the verbose_eval abilities.

Removed some trailing-whitespaces
This commit is contained in:
Johan Manders 2015-11-12 20:22:36 +01:00
parent cb5171914e
commit e68e9659ab
1 changed files with 29 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
python-package/xgboost/training.py
View File

@ -48,9 +48,15 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
and a paramater containing ('eval_metric', 'logloss')
Returns: {'train': {'logloss': ['0.48253', '0.35953']},
'eval': {'logloss': ['0.480385', '0.357756']}}
verbose_eval : bool
If `verbose_eval` then the evaluation metric on the validation set, if
given, is printed at each boosting stage.
verbose_eval : bool or int
Requires at least one item in evals.
If `verbose_eval` is True then the evaluation metric on the validation set is
printed at each boosting stage.
If `verbose_eval` is an integer then the evaluation metric on the validation set
is printed at every given `verbose_eval` boosting stage. The last boosting stage
/ the boosting stage found by using `early_stopping_rounds` is also printed.
Example: with verbose_eval=4 and at least one item in evals, an evaluation metric
is printed every 4 boosting stages, instead of every boosting stage.
learning_rates: list or function
List of learning rate for each boosting round
or a customized function that calculates eta in terms of
@ -80,6 +86,13 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
nboost = 0
num_parallel_tree = 1
if isinstance(verbose_eval, bool):
verbose_eval_every_line = False
else:
if isinstance(verbose_eval, int):
verbose_eval_every_line = verbose_eval
verbose_eval = True
if xgb_model is not None:
if not isinstance(xgb_model, STRING_TYPES):
xgb_model = xgb_model.save_raw()
@ -115,7 +128,12 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
msg = bst_eval_set.decode()
if verbose_eval:
if verbose_eval_every_line:
if i % verbose_eval_every_line == 0 or i == num_boost_round - 1:
sys.stderr.write(msg + '\n')
else:
sys.stderr.write(msg + '\n')
if evals_result is not None:
res = re.findall("([0-9a-zA-Z@]+[-]*):-?([0-9.]+).", msg)
for key in evals_name:
@ -187,6 +205,10 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
msg = bst_eval_set.decode()
if verbose_eval:
if verbose_eval_every_line:
if i % verbose_eval_every_line == 0:
sys.stderr.write(msg + '\n')
else:
sys.stderr.write(msg + '\n')
if evals_result is not None:
@ -210,6 +232,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
best_score_i = (nboost - 1)
best_msg = msg
elif i - best_score_i >= early_stopping_rounds:
if verbose_eval:
sys.stderr.write("Stopping. Best iteration:\n{}\n\n".format(best_msg))
bst.best_score = best_score
bst.best_iteration = best_score_i