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

[backport] Fix tests with pandas 2.0. (#9014) (#9289)

Browse Source 
* Fix tests with pandas 2.0.

- `is_categorical` is replaced by `is_categorical_dtype`.
- one hot encoding returns boolean type instead of integer type.
This commit is contained in:
Jiaming Yuan 2023-06-11 00:52:44 +08:00 committed by GitHub
parent 03f3879b71
commit 14476e8868
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/python/test_basic_models.py
View File

@ -578,7 +578,7 @@ class TestModels:
y = rng.randn(rows)
feature_names = ["test_feature_" + str(i) for i in range(cols)]
X_pd = pd.DataFrame(X, columns=feature_names)
X_pd.iloc[:, 3] = X_pd.iloc[:, 3].astype(np.int32)
X_pd[f"test_feature_{3}"] = X_pd.iloc[:, 3].astype(np.int32)
Xy = xgb.DMatrix(X_pd, y)
assert Xy.feature_types[3] == "int"

5
tests/python/test_with_pandas.py
View File

@ -75,7 +75,10 @@ class TestPandas:
np.testing.assert_array_equal(result, exp)
dm = xgb.DMatrix(dummies)
assert dm.feature_names == ['B', 'A_X', 'A_Y', 'A_Z']
assert dm.feature_types == ['int', 'int', 'int', 'int']
if int(pd.__version__[0]) >= 2:
assert dm.feature_types == ['int', 'i', 'i', 'i']
else:
assert dm.feature_types == ['int', 'int', 'int', 'int']
assert dm.num_row() == 3
assert dm.num_col() == 4