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

Implement Python data handler. (#5689)

Browse Source 
* Define data handlers for DMatrix.
* Throw ValueError in scikit learn interface.
This commit is contained in:
Jiaming Yuan
2020-05-22 11:53:55 +08:00
committed by GitHub
parent 646def51e0
commit 5af8161a1a
7 changed files with 746 additions and 405 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
tests/python/test_with_pandas.py
View File

@@ -67,7 +67,8 @@ class TestPandas(unittest.TestCase):
# 0 1 1 0 0
# 1 2 0 1 0
# 2 3 0 0 1
result, _, _ = xgb.core._maybe_pandas_data(dummies, None, None)
pandas_handler = xgb.data.PandasHandler(np.nan, 0, False)
result, _, _ = pandas_handler._maybe_pandas_data(dummies, None, None)
exp = np.array([[1., 1., 0., 0.],
[2., 0., 1., 0.],
[3., 0., 0., 1.]])
@@ -113,12 +114,12 @@ class TestPandas(unittest.TestCase):
import pandas as pd
rows = 100
X = pd.DataFrame(
{"A": pd.SparseArray(np.random.randint(0, 10, size=rows)),
"B": pd.SparseArray(np.random.randn(rows)),
"C": pd.SparseArray(np.random.permutation(
{"A": pd.arrays.SparseArray(np.random.randint(0, 10, size=rows)),
"B": pd.arrays.SparseArray(np.random.randn(rows)),
"C": pd.arrays.SparseArray(np.random.permutation(
[True, False] * (rows // 2)))}
)
y = pd.Series(pd.SparseArray(np.random.randn(rows)))
y = pd.Series(pd.arrays.SparseArray(np.random.randn(rows)))
dtrain = xgb.DMatrix(X, y)
booster = xgb.train({}, dtrain, num_boost_round=4)
predt_sparse = booster.predict(xgb.DMatrix(X))
@@ -128,17 +129,18 @@ 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_data, df,
pandas_handler = xgb.data.PandasHandler(np.nan, 0, False)
self.assertRaises(ValueError, pandas_handler._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_data, df,
self.assertRaises(ValueError, pandas_handler._maybe_pandas_data, df,
None, None, 'label', 'float')
df = pd.DataFrame({'A': np.array([1, 2, 3], dtype=int)})
result, _, _ = xgb.core._maybe_pandas_data(df, None, None,
'label', 'float')
result, _, _ = pandas_handler._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)