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

Enable categorical data support on Python DMatrix. (#6166)

Browse Source 
* Only pandas is recognized.
This commit is contained in:
Jiaming Yuan
2020-09-29 11:22:56 +08:00
committed by GitHub
parent 52c0b3f100
commit 7622b8cdb8
4 changed files with 57 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
python-package/xgboost/core.py
View File

@@ -384,7 +384,8 @@ class DMatrix: # pylint: disable=too-many-instance-attributes
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/
@@ -419,6 +420,16 @@ class DMatrix: # pylint: disable=too-many-instance-attributes
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.')
@@ -437,7 +448,8 @@ class DMatrix: # pylint: disable=too-many-instance-attributes
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

36
python-package/xgboost/data.py
View File

@@ -184,20 +184,24 @@ _pandas_dtype_mapper = {
}
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:
@@ -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])
@@ -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)
@@ -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
@@ -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)
@@ -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,
@@ -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,
@@ -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):
@@ -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):