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

Support pandas SparseArray. (#5431)

Browse Source
This commit is contained in:
Jiaming Yuan 2020-03-20 21:40:22 +08:00 committed by GitHub
parent 3cf665d3ec
commit abca9908ba
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 25 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
python-package/xgboost/core.py
View File

@ -246,12 +246,13 @@ def _has_cuda_array_interface(data):
def _maybe_pandas_data(data, feature_names, feature_types,
meta=None, meta_type=None):
"""Extract internal data from pd.DataFrame for DMatrix data"""
if not (PANDAS_INSTALLED and isinstance(data, DataFrame)):
return data, feature_names, feature_types
from pandas.api.types import is_sparse
data_dtypes = data.dtypes
if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in data_dtypes):
if not all(dtype.name in PANDAS_DTYPE_MAPPER or is_sparse(dtype)
for dtype in data_dtypes):
bad_fields = [
str(data.columns[i]) for i, dtype in enumerate(data_dtypes)
if dtype.name not in PANDAS_DTYPE_MAPPER
@ -272,9 +273,12 @@ def _maybe_pandas_data(data, feature_names, feature_types,
feature_names = data.columns.format()
if feature_types is None and meta is None:
feature_types = [
PANDAS_DTYPE_MAPPER[dtype.name] for dtype in data_dtypes
]
feature_types = []
for dtype in data_dtypes:
if is_sparse(dtype):
feature_types.append(PANDAS_DTYPE_MAPPER[dtype.subtype.name])
else:
feature_types.append(PANDAS_DTYPE_MAPPER[dtype.name])
if meta and len(data.columns) > 1:
raise ValueError(

16
tests/python/test_with_pandas.py
View File

@ -109,6 +109,22 @@ class TestPandas(unittest.TestCase):
assert dm.num_row() == 2
assert dm.num_col() == 6
def test_pandas_sparse(self):
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(
[True, False] * (rows // 2)))}
)
y = pd.Series(pd.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))
predt_dense = booster.predict(xgb.DMatrix(X.sparse.to_dense()))
np.testing.assert_allclose(predt_sparse, predt_dense)
def test_pandas_label(self):
# label must be a single column
df = pd.DataFrame({'A': ['X', 'Y', 'Z'], 'B': [1, 2, 3]})