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

Merge pull request #503 from sinhrks/feature_types

Browse Source 
Python: Add feature_types to DMatrix
This commit is contained in:
Tianqi Chen 2015-09-29 14:14:48 -07:00
commit db490d1c75
3 changed files with 143 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

132
python-package/xgboost/core.py
View File

@ -146,10 +146,12 @@ class DMatrix(object):
You can construct DMatrix from numpy.arrays
"""
feature_names = None # for previous version's pickle
_feature_names = None # for previous version's pickle
_feature_types = None
def __init__(self, data, label=None, missing=0.0,
weight=None, silent=False, feature_names=None):
weight=None, silent=False,
feature_names=None, feature_types=None):
"""
Data matrix used in XGBoost.
@ -169,6 +171,8 @@ class DMatrix(object):
Whether print messages during construction
feature_names : list, optional
Labels for features.
feature_types : list, optional
Labels for features.
"""
# force into void_p, mac need to pass things in as void_p
if data is None:
@ -196,20 +200,8 @@ class DMatrix(object):
if weight is not None:
self.set_weight(weight)
# validate feature name
if not feature_names is None:
if not isinstance(feature_names, list):
feature_names = list(feature_names)
if len(feature_names) != len(set(feature_names)):
raise ValueError('feature_names must be unique')
if len(feature_names) != self.num_col():
msg = 'feature_names must have the same length as data'
raise ValueError(msg)
# prohibit to use symbols may affect to parse. e.g. ``[]=.``
if not all(isinstance(f, STRING_TYPES) and f.isalnum()
for f in feature_names):
raise ValueError('all feature_names must be alphanumerics')
self.feature_names = feature_names
self.feature_types = feature_types
def _init_from_csr(self, csr):
"""
@ -461,6 +453,88 @@ class DMatrix(object):
ctypes.byref(res.handle)))
return res
@property
def feature_names(self):
"""Get feature names (column labels).
Returns
-------
feature_names : list or None
"""
return self._feature_names
@property
def feature_types(self):
"""Get feature types (column types).
Returns
-------
feature_types : list or None
"""
return self._feature_types
@feature_names.setter
def feature_names(self, feature_names):
"""Set feature names (column labels).
Parameters
----------
feature_names : list or None
Labels for features. None will reset existing feature names
"""
if not feature_names is None:
# validate feature name
if not isinstance(feature_names, list):
feature_names = list(feature_names)
if len(feature_names) != len(set(feature_names)):
raise ValueError('feature_names must be unique')
if len(feature_names) != self.num_col():
msg = 'feature_names must have the same length as data'
raise ValueError(msg)
# prohibit to use symbols may affect to parse. e.g. ``[]=.``
if not all(isinstance(f, STRING_TYPES) and f.isalnum()
for f in feature_names):
raise ValueError('all feature_names must be alphanumerics')
else:
# reset feature_types also
self.feature_types = None
self._feature_names = feature_names
@feature_types.setter
def feature_types(self, feature_types):
"""Set feature types (column types).
This is for displaying the results and unrelated
to the learning process.
Parameters
----------
feature_types : list or None
Labels for features. None will reset existing feature names
"""
if not feature_types is None:
if self.feature_names is None:
msg = 'Unable to set feature types before setting names'
raise ValueError(msg)
if isinstance(feature_types, STRING_TYPES):
# single string will be applied to all columns
feature_types = [feature_types] * self.num_col()
if not isinstance(feature_types, list):
feature_types = list(feature_types)
if len(feature_types) != self.num_col():
msg = 'feature_types must have the same length as data'
raise ValueError(msg)
# prohibit to use symbols may affect to parse. e.g. ``[]=.``
valid = ('q', 'i', 'int', 'float')
if not all(isinstance(f, STRING_TYPES) and f in valid
for f in feature_types):
raise ValueError('all feature_names must be {i, q, int, float}')
self._feature_types = feature_types
class Booster(object):
""""A Booster of of XGBoost.
@ -487,7 +561,8 @@ class Booster(object):
for d in cache:
if not isinstance(d, DMatrix):
raise TypeError('invalid cache item: {}'.format(type(d).__name__))
self._validate_feature_names(d)
self._validate_features(d)
dmats = c_array(ctypes.c_void_p, [d.handle for d in cache])
self.handle = ctypes.c_void_p()
_check_call(_LIB.XGBoosterCreate(dmats, len(cache), ctypes.byref(self.handle)))
@ -572,7 +647,7 @@ class Booster(object):
"""
if not isinstance(dtrain, DMatrix):
raise TypeError('invalid training matrix: {}'.format(type(dtrain).__name__))
self._validate_feature_names(dtrain)
self._validate_features(dtrain)
if fobj is None:
_check_call(_LIB.XGBoosterUpdateOneIter(self.handle, iteration, dtrain.handle))
@ -598,7 +673,7 @@ class Booster(object):
raise ValueError('grad / hess length mismatch: {} / {}'.format(len(grad), len(hess)))
if not isinstance(dtrain, DMatrix):
raise TypeError('invalid training matrix: {}'.format(type(dtrain).__name__))
self._validate_feature_names(dtrain)
self._validate_features(dtrain)
_check_call(_LIB.XGBoosterBoostOneIter(self.handle, dtrain.handle,
c_array(ctypes.c_float, grad),
@ -629,7 +704,7 @@ class Booster(object):
raise TypeError('expected DMatrix, got {}'.format(type(d[0]).__name__))
if not isinstance(d[1], STRING_TYPES):
raise TypeError('expected string, got {}'.format(type(d[1]).__name__))
self._validate_feature_names(d[0])
self._validate_features(d[0])
dmats = c_array(ctypes.c_void_p, [d[0].handle for d in evals])
evnames = c_array(ctypes.c_char_p, [c_str(d[1]) for d in evals])
@ -664,7 +739,7 @@ class Booster(object):
result: str
Evaluation result string.
"""
self._validate_feature_names(data)
self._validate_features(data)
return self.eval_set([(data, name)], iteration)
def predict(self, data, output_margin=False, ntree_limit=0, pred_leaf=False):
@ -703,7 +778,7 @@ class Booster(object):
if pred_leaf:
option_mask |= 0x02
self._validate_feature_names(data)
self._validate_features(data)
length = ctypes.c_ulong()
preds = ctypes.POINTER(ctypes.c_float)()
@ -805,9 +880,12 @@ class Booster(object):
fname = from_pystr_to_cstr(self.feature_names)
# supports quantitative type only
# {'q': quantitative, 'i': indicator}
ftype = from_pystr_to_cstr(['q'] * flen)
if self.feature_types is None:
# use quantitative as default
# {'q': quantitative, 'i': indicator}
ftype = from_pystr_to_cstr(['q'] * flen)
else:
ftype = from_pystr_to_cstr(self.feature_types)
_check_call(_LIB.XGBoosterDumpModelWithFeatures(self.handle,
flen,
fname,
@ -849,12 +927,14 @@ class Booster(object):
fmap[fid] += 1
return fmap
def _validate_feature_names(self, data):
def _validate_features(self, data):
"""
Validate Booster and data's feature_names are identical
Validate Booster and data's feature_names are identical.
Set feature_names and feature_types from DMatrix
"""
if self.feature_names is None:
self.feature_names = data.feature_names
self.feature_types = data.feature_types
else:
# Booster can't accept data with different feature names
if self.feature_names != data.feature_names:

27
python-package/xgboost/plotting.py
View File

@ -92,7 +92,7 @@ def plot_importance(booster, ax=None, height=0.2,
_NODEPAT = re.compile(r'(\d+):\[(.+)\]')
_LEAFPAT = re.compile(r'(\d+):(leaf=.+)')
_EDGEPAT = re.compile(r'yes=(\d+),no=(\d+),missing=(\d+)')
_EDGEPAT2 = re.compile(r'yes=(\d+),no=(\d+)')
def _parse_node(graph, text):
"""parse dumped node"""
@ -111,15 +111,24 @@ def _parse_node(graph, text):
def _parse_edge(graph, node, text, yes_color='#0000FF', no_color='#FF0000'):
"""parse dumped edge"""
match = _EDGEPAT.match(text)
try:
match = _EDGEPAT.match(text)
if match is not None:
yes, no, missing = match.groups()
if yes == missing:
graph.edge(node, yes, label='yes, missing', color=yes_color)
graph.edge(node, no, label='no', color=no_color)
else:
graph.edge(node, yes, label='yes', color=yes_color)
graph.edge(node, no, label='no, missing', color=no_color)
return
except ValueError:
pass
match = _EDGEPAT2.match(text)
if match is not None:
yes, no, missing = match.groups()
if yes == missing:
graph.edge(node, yes, label='yes, missing', color=yes_color)
graph.edge(node, no, label='no', color=no_color)
else:
graph.edge(node, yes, label='yes', color=yes_color)
graph.edge(node, no, label='no, missing', color=no_color)
yes, no = match.groups()
graph.edge(node, yes, label='yes', color=yes_color)
graph.edge(node, no, label='no', color=no_color)
return
raise ValueError('Unable to parse edge: {0}'.format(text))

19
tests/python/test_basic.py
View File

@ -47,6 +47,25 @@ class TestBasic(unittest.TestCase):
self.assertRaises(ValueError, xgb.DMatrix, data,
feature_names=['a', 'b', 'c', 'd', 'e=1'])
dm = xgb.DMatrix(data)
dm.feature_names = list('abcde')
assert dm.feature_names == list('abcde')
dm.feature_types = 'q'
assert dm.feature_types == list('qqqqq')
dm.feature_types = list('qiqiq')
assert dm.feature_types == list('qiqiq')
def incorrect_type_set():
dm.feature_types = list('abcde')
self.assertRaises(ValueError, incorrect_type_set)
# reset
dm.feature_names = None
assert dm.feature_names is None
assert dm.feature_types is None
def test_feature_names(self):
data = np.random.randn(100, 5)
target = np.array([0, 1] * 50)