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

Enable categorical data support on Python DMatrix. (#6166)

Browse Source 
* Only pandas is recognized.
This commit is contained in:
Jiaming Yuan
2020-09-29 11:22:56 +08:00
committed by GitHub
parent 52c0b3f100
commit 7622b8cdb8
4 changed files with 57 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/python/test_with_modin.py
View File

@@ -67,7 +67,8 @@ class TestModin(unittest.TestCase):
# 0 1 1 0 0
# 1 2 0 1 0
# 2 3 0 0 1
result, _, _ = xgb.data._transform_pandas_df(dummies)
result, _, _ = xgb.data._transform_pandas_df(dummies,
enable_categorical=False)
exp = np.array([[1., 1., 0., 0.],
[2., 0., 1., 0.],
[3., 0., 0., 1.]])
@@ -113,15 +114,15 @@ class TestModin(unittest.TestCase):
# label must be a single column
df = md.DataFrame({'A': ['X', 'Y', 'Z'], 'B': [1, 2, 3]})
self.assertRaises(ValueError, xgb.data._transform_pandas_df, df,
None, None, 'label', 'float')
False, None, None, 'label', 'float')
# label must be supported dtype
df = md.DataFrame({'A': np.array(['a', 'b', 'c'], dtype=object)})
self.assertRaises(ValueError, xgb.data._transform_pandas_df, df,
None, None, 'label', 'float')
False, None, None, 'label', 'float')
df = md.DataFrame({'A': np.array([1, 2, 3], dtype=int)})
result, _, _ = xgb.data._transform_pandas_df(df, None, None,
result, _, _ = xgb.data._transform_pandas_df(df, False, None, None,
'label', 'float')
np.testing.assert_array_equal(result, np.array([[1.], [2.], [3.]],
dtype=float))