Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Enable categorical data support on Python DMatrix. #6166

Merged
merged 3 commits into from
Sep 29, 2020
Merged

Enable categorical data support on Python DMatrix. #6166

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4759f9b
Enable categorical data support on Python DMatrix.
trivialfis Sep 25, 2020
648b442
Address outdated comment.
trivialfis Sep 25, 2020
565ff71
Modin.
trivialfis Sep 25, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions python-package/xgboost/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,7 +384,8 @@ def __init__(self, data, label=None, weight=None, base_margin=None,
silent=False,
feature_names=None,
feature_types=None,
nthread=None):
nthread=None,
enable_categorical=False):
"""Parameters
----------
data : os.PathLike/string/numpy.array/scipy.sparse/pd.DataFrame/
Expand Down Expand Up @@ -419,6 +420,16 @@ def __init__(self, data, label=None, weight=None, base_margin=None,
Number of threads to use for loading data when parallelization is
applicable. If -1, uses maximum threads available on the system.

enable_categorical: boolean, optional

.. versionadded:: 1.3.0

Experimental support of specializing for categorical features. Do
not set to True unless you are interested in development.
Currently it's only available for `gpu_hist` tree method with 1 vs
rest (one hot) categorical split. Also, JSON serialization format,
`gpu_predictor` and pandas input are required.

"""
if isinstance(data, list):
raise TypeError('Input data can not be a list.')
Expand All @@ -437,7 +448,8 @@ def __init__(self, data, label=None, weight=None, base_margin=None,
data, missing=self.missing,
threads=self.nthread,
feature_names=feature_names,
feature_types=feature_types)
feature_types=feature_types,
enable_categorical=enable_categorical)
assert handle is not None
self.handle = handle

Expand Down
36 changes: 23 additions & 13 deletions python-package/xgboost/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,20 +184,24 @@ def _is_modin_df(data):
}


def _transform_pandas_df(data, feature_names=None, feature_types=None,
def _transform_pandas_df(data, enable_categorical,
feature_names=None, feature_types=None,
meta=None, meta_type=None):
from pandas import MultiIndex, Int64Index
from pandas.api.types import is_sparse
from pandas.api.types import is_sparse, is_categorical

data_dtypes = data.dtypes
if not all(dtype.name in _pandas_dtype_mapper or is_sparse(dtype)
if not all(dtype.name in _pandas_dtype_mapper or is_sparse(dtype) or
(is_categorical(dtype) and enable_categorical)
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
]

msg = """DataFrame.dtypes for data must be int, float or bool.
Did not expect the data types in fields """
msg = """DataFrame.dtypes for data must be int, float, bool or categorical. When
categorical type is supplied, DMatrix parameter
`enable_categorical` must be set to `True`."""
raise ValueError(msg + ', '.join(bad_fields))

if feature_names is None and meta is None:
Expand All @@ -216,6 +220,8 @@ def _transform_pandas_df(data, feature_names=None, feature_types=None,
if is_sparse(dtype):
feature_types.append(_pandas_dtype_mapper[
dtype.subtype.name])
elif is_categorical(dtype) and enable_categorical:
feature_types.append('categorical')
else:
feature_types.append(_pandas_dtype_mapper[dtype.name])

Expand All @@ -226,13 +232,13 @@ def _transform_pandas_df(data, feature_names=None, feature_types=None,

dtype = meta_type if meta_type else np.float32
data = np.ascontiguousarray(data.values, dtype=dtype)

return data, feature_names, feature_types


def _from_pandas_df(data, missing, nthread, feature_names, feature_types):
def _from_pandas_df(data, enable_categorical, missing, nthread,
feature_names, feature_types):
data, feature_names, feature_types = _transform_pandas_df(
data, feature_names, feature_types)
data, enable_categorical, feature_names, feature_types)
return _from_numpy_array(data, missing, nthread, feature_names,
feature_types)

Expand All @@ -244,6 +250,7 @@ def _is_pandas_series(data):
return False
return isinstance(data, pd.Series)


def _is_modin_series(data):
try:
import modin.pandas as pd
Expand Down Expand Up @@ -507,7 +514,8 @@ def _has_array_protocol(data):


def dispatch_data_backend(data, missing, threads,
feature_names, feature_types):
feature_names, feature_types,
enable_categorical=False):
'''Dispatch data for DMatrix.'''
if _is_scipy_csr(data):
return _from_scipy_csr(data, missing, feature_names, feature_types)
Expand All @@ -525,7 +533,7 @@ def dispatch_data_backend(data, missing, threads,
if _is_tuple(data):
return _from_tuple(data, missing, feature_names, feature_types)
if _is_pandas_df(data):
return _from_pandas_df(data, missing, threads,
return _from_pandas_df(data, enable_categorical, missing, threads,
feature_names, feature_types)
if _is_pandas_series(data):
return _from_pandas_series(data, missing, threads, feature_names,
Expand All @@ -551,7 +559,7 @@ def dispatch_data_backend(data, missing, threads,
return _from_dt_df(data, missing, threads, feature_names,
feature_types)
if _is_modin_df(data):
return _from_pandas_df(data, missing, threads,
return _from_pandas_df(data, enable_categorical, missing, threads,
feature_names, feature_types)
if _is_modin_series(data):
return _from_pandas_series(data, missing, threads, feature_names,
Expand Down Expand Up @@ -655,7 +663,8 @@ def dispatch_meta_backend(matrix: DMatrix, data, name: str, dtype: str = None):
_meta_from_numpy(data, name, dtype, handle)
return
if _is_pandas_df(data):
data, _, _ = _transform_pandas_df(data, meta=name, meta_type=dtype)
data, _, _ = _transform_pandas_df(data, False, meta=name,
meta_type=dtype)
_meta_from_numpy(data, name, dtype, handle)
return
if _is_pandas_series(data):
Expand All @@ -680,7 +689,8 @@ def dispatch_meta_backend(matrix: DMatrix, data, name: str, dtype: str = None):
_meta_from_dt(data, name, dtype, handle)
return
if _is_modin_df(data):
data, _, _ = _transform_pandas_df(data, meta=name, meta_type=dtype)
data, _, _ = _transform_pandas_df(
data, False, meta=name, meta_type=dtype)
_meta_from_numpy(data, name, dtype, handle)
return
if _is_modin_series(data):
Expand Down
9 changes: 5 additions & 4 deletions tests/python/test_with_modin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,8 @@ def test_modin(self):
# 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.]])
Expand Down Expand Up @@ -113,15 +114,15 @@ def test_modin_label(self):
# 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))
Expand Down
19 changes: 15 additions & 4 deletions tests/python/test_with_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,8 @@ def test_pandas(self):
# 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.]])
Expand Down Expand Up @@ -109,6 +110,16 @@ def test_pandas(self):
assert dm.num_row() == 2
assert dm.num_col() == 6

def test_pandas_categorical(self):
rng = np.random.RandomState(1994)
rows = 100
X = rng.randint(3, 7, size=rows)
X = pd.Series(X, dtype="category")
X = pd.DataFrame({'f0': X})
y = rng.randn(rows)
m = xgb.DMatrix(X, y, enable_categorical=True)
assert m.feature_types[0] == 'categorical'

def test_pandas_sparse(self):
import pandas as pd
rows = 100
Expand All @@ -129,15 +140,15 @@ 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.data._transform_pandas_df, df,
None, None, 'label', 'float')
False, None, None, 'label', 'float')

# label must be supported dtype
df = pd.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 = pd.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))
Expand Down