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

Fix metainfo from DataFrame. (#5216)

Browse Source 
* Fix metainfo from DataFrame.

* Unify helper functions for data and meta.
This commit is contained in:
Jiaming Yuan
2020-01-22 16:29:44 +08:00
committed by GitHub
parent 5d4c24a1fc
commit 1891cc766d
5 changed files with 225 additions and 237 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
tests/python/test_with_pandas.py
View File

@@ -29,6 +29,7 @@ class TestPandas(unittest.TestCase):
assert dm.feature_types == ['int', 'float', 'i']
assert dm.num_row() == 2
assert dm.num_col() == 3
np.testing.assert_array_equal(dm.get_label(), np.array([1, 2]))
# overwrite feature_names and feature_types
dm = xgb.DMatrix(df, label=pd.Series([1, 2]),
@@ -51,6 +52,7 @@ class TestPandas(unittest.TestCase):
assert dm.feature_types == ['int', 'float', 'i']
assert dm.num_row() == 2
assert dm.num_col() == 3
np.testing.assert_array_equal(dm.get_label(), np.array([1, 2]))
df = pd.DataFrame([[1, 2., 1], [2, 3., 1]], columns=[4, 5, 6])
dm = xgb.DMatrix(df, label=pd.Series([1, 2]))
@@ -110,21 +112,38 @@ class TestPandas(unittest.TestCase):
def test_pandas_label(self):
# label must be a single column
df = pd.DataFrame({'A': ['X', 'Y', 'Z'], 'B': [1, 2, 3]})
self.assertRaises(ValueError, xgb.core._maybe_pandas_label, df)
self.assertRaises(ValueError, xgb.core._maybe_pandas_data, df,
None, None, 'label', 'float')
# label must be supported dtype
df = pd.DataFrame({'A': np.array(['a', 'b', 'c'], dtype=object)})
self.assertRaises(ValueError, xgb.core._maybe_pandas_label, df)
self.assertRaises(ValueError, xgb.core._maybe_pandas_data, df,
None, None, 'label', 'float')
df = pd.DataFrame({'A': np.array([1, 2, 3], dtype=int)})
result = xgb.core._maybe_pandas_label(df)
result, _, _ = xgb.core._maybe_pandas_data(df, None, None,
'label', 'float')
np.testing.assert_array_equal(result, np.array([[1.], [2.], [3.]],
dtype=float))
dm = xgb.DMatrix(np.random.randn(3, 2), label=df)
assert dm.num_row() == 3
assert dm.num_col() == 2
def test_pandas_weight(self):
kRows = 32
kCols = 8
X = np.random.randn(kRows, kCols)
y = np.random.randn(kRows)
w = np.random.randn(kRows).astype(np.float32)
w_pd = pd.DataFrame(w)
data = xgb.DMatrix(X, y, w_pd)
assert data.num_row() == kRows
assert data.num_col() == kCols
np.testing.assert_array_equal(data.get_weight(), w)
def test_cv_as_pandas(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,