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

Support non-str column names

Browse Source
This commit is contained in:
sinhrks 2015-10-04 13:30:01 +09:00
parent 2859c190cd
commit dbcb4c8729
2 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
python-package/xgboost/core.py
View File

@ -153,7 +153,7 @@ def _maybe_from_pandas(data, feature_names, feature_types):
raise ValueError('DataFrame.dtypes must be int, float or bool') raise ValueError('DataFrame.dtypes must be int, float or bool')
if feature_names is None: if feature_names is None:
feature_names = data.columns.tolist() feature_names = data.columns.format()
if feature_types is None: if feature_types is None:
mapper = {'int64': 'int', 'float64': 'q', 'bool': 'i'} mapper = {'int64': 'int', 'float64': 'q', 'bool': 'i'}
feature_types = [mapper[dtype.name] for dtype in dtypes] feature_types = [mapper[dtype.name] for dtype in dtypes]

15
tests/python/test_basic.py
View File

@ -118,6 +118,21 @@ class TestBasic(unittest.TestCase):
df = pd.DataFrame([[1, 2., 'x'], [2, 3., 'y']], columns=['a', 'b', 'c']) df = pd.DataFrame([[1, 2., 'x'], [2, 3., 'y']], columns=['a', 'b', 'c'])
self.assertRaises(ValueError, xgb.DMatrix, df) self.assertRaises(ValueError, xgb.DMatrix, df)
# numeric columns
df = pd.DataFrame([[1, 2., True], [2, 3., False]])
dm = xgb.DMatrix(df, label=pd.Series([1, 2]))
assert dm.feature_names == ['0', '1', '2']
assert dm.feature_types == ['int', 'q', 'i']
assert dm.num_row() == 2
assert dm.num_col() == 3
df = pd.DataFrame([[1, 2., 1], [2, 3., 1]], columns=[4, 5, 6])
dm = xgb.DMatrix(df, label=pd.Series([1, 2]))
assert dm.feature_names == ['4', '5', '6']
assert dm.feature_types == ['int', 'q', 'int']
assert dm.num_row() == 2
assert dm.num_col() == 3
def test_load_file_invalid(self): def test_load_file_invalid(self):
self.assertRaises(ValueError, xgb.Booster, self.assertRaises(ValueError, xgb.Booster,