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

Support latest pandas Index type. (#7595)

Browse Source
This commit is contained in:
Jiaming Yuan 2022-01-26 18:20:10 +08:00 committed by GitHub
parent 511805c981
commit 24789429fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
python-package/xgboost/compat.py
View File

@ -33,14 +33,13 @@ def lazy_isinstance(instance, module, name):
# pandas # pandas
try: try:
from pandas import DataFrame, Series from pandas import DataFrame, Series
from pandas import MultiIndex, Int64Index from pandas import MultiIndex
from pandas import concat as pandas_concat from pandas import concat as pandas_concat
PANDAS_INSTALLED = True PANDAS_INSTALLED = True
except ImportError: except ImportError:
MultiIndex = object MultiIndex = object
Int64Index = object
DataFrame: Any = object DataFrame: Any = object
Series = object Series = object
pandas_concat = None pandas_concat = None

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

@ -264,7 +264,7 @@ def _transform_pandas_df(
if feature_names is None and meta is None: if feature_names is None and meta is None:
if isinstance(data.columns, pd.MultiIndex): if isinstance(data.columns, pd.MultiIndex):
feature_names = [" ".join([str(x) for x in i]) for i in data.columns] feature_names = [" ".join([str(x) for x in i]) for i in data.columns]
elif isinstance(data.columns, (pd.Int64Index, pd.RangeIndex)): elif isinstance(data.columns, (pd.Index, pd.RangeIndex)):
feature_names = list(map(str, data.columns)) feature_names = list(map(str, data.columns))
else: else:
feature_names = data.columns.format() feature_names = data.columns.format()

6
tests/python/test_with_pandas.py
View File

@ -109,6 +109,12 @@ class TestPandas:
assert dm.num_row() == 2 assert dm.num_row() == 2
assert dm.num_col() == 6 assert dm.num_col() == 6
# test Index as columns
df = pd.DataFrame([[1, 1.1], [2, 2.2]], columns=pd.Index([1, 2]))
print(df.columns, isinstance(df.columns, pd.Index))
Xy = xgb.DMatrix(df)
np.testing.assert_equal(np.array(Xy.feature_names), np.array(["1", "2"]))
def test_slice(self): def test_slice(self):
rng = np.random.RandomState(1994) rng = np.random.RandomState(1994)
rows = 100 rows = 100