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

Make missing handling consistent with sklearn's portion of the python package

Browse Source
This commit is contained in:
Maxim Grechkin 2016-01-28 14:16:11 -08:00
parent 21d5ec7275
commit f5e96eba72
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
python-package/xgboost/core.py
View File

@ -184,7 +184,7 @@ class DMatrix(object):
_feature_names = None # for previous version's pickle
_feature_types = None
def __init__(self, data, label=None, missing=0.0,
def __init__(self, data, label=None, missing=None,
weight=None, silent=False,
feature_names=None, feature_types=None):
"""
@ -199,7 +199,8 @@ class DMatrix(object):
label : list or numpy 1-D array, optional
Label of the training data.
missing : float, optional
Value in the data which needs to be present as a missing value.
Value in the data which needs to be present as a missing value. If
None, defaults to np.nan.
weight : list or numpy 1-D array , optional
Weight for each instance.
silent : boolean, optional
@ -278,6 +279,7 @@ class DMatrix(object):
raise ValueError('Input numpy.ndarray must be 2 dimensional')
data = np.array(mat.reshape(mat.size), dtype=np.float32)
self.handle = ctypes.c_void_p()
missing = missing if missing is not None else np.nan
_check_call(_LIB.XGDMatrixCreateFromMat(data.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),
mat.shape[0], mat.shape[1],
ctypes.c_float(missing),
@ -988,4 +990,3 @@ class Booster(object):
msg = 'feature_names mismatch: {0} {1}'
raise ValueError(msg.format(self.feature_names,
data.feature_names))