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

Follow PEP 257 -- Docstring Conventions (#4959)

Browse Source
This commit is contained in:
Jacob Kim 2019-10-18 12:45:25 +09:00 committed by Jiaming Yuan
parent 60748b2071
commit a78d4e7aa8
1 changed files with 25 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
python-package/xgboost/core.py
View File

@ -108,7 +108,7 @@ def from_cstr_to_pystr(data, length):
def _expect(expectations, got): def _expect(expectations, got):
'''Translate input error into string. """Translate input error into string.
Parameters Parameters
---------- ----------
@ -119,7 +119,8 @@ def _expect(expectations, got):
Returns Returns
------- -------
msg: str''' msg: str
"""
msg = 'Expecting ' msg = 'Expecting '
for t in range(len(expectations) - 1): for t in range(len(expectations) - 1):
msg += str(expectations[t]) msg += str(expectations[t])
@ -202,8 +203,7 @@ def _check_call(ret):
def ctypes2numpy(cptr, length, dtype): def ctypes2numpy(cptr, length, dtype):
"""Convert a ctypes pointer array to a numpy array. """Convert a ctypes pointer array to a numpy array."""
"""
NUMPY_TO_CTYPES_MAPPING = { NUMPY_TO_CTYPES_MAPPING = {
np.float32: ctypes.c_float, np.float32: ctypes.c_float,
np.uint32: ctypes.c_uint, np.uint32: ctypes.c_uint,
@ -244,19 +244,19 @@ def c_array(ctype, values):
def _use_columnar_initializer(data): def _use_columnar_initializer(data):
'''Whether should we use columnar format initializer (pass data in as json """Whether should we use columnar format initializer (pass data in as json
string). Currently cudf is the only valid option. For other dataframe string). Currently cudf is the only valid option. For other dataframe
types, use their sepcific API instead. types, use their sepcific API instead.
"""
'''
if CUDF_INSTALLED and (isinstance(data, (CUDF_DataFrame, CUDF_Series))): if CUDF_INSTALLED and (isinstance(data, (CUDF_DataFrame, CUDF_Series))):
return True return True
return False return False
def _extract_interface_from_cudf_series(data): def _extract_interface_from_cudf_series(data):
"""This returns the array interface from the cudf series. This function should """This returns the array interface from the cudf series. This function
be upstreamed to cudf.""" should be upstreamed to cudf.
"""
interface = data.__cuda_array_interface__ interface = data.__cuda_array_interface__
if data.has_null_mask: if data.has_null_mask:
interface['mask'] = interface['mask'].__cuda_array_interface__ interface['mask'] = interface['mask'].__cuda_array_interface__
@ -289,7 +289,7 @@ PANDAS_DTYPE_MAPPER = {'int8': 'int', 'int16': 'int', 'int32': 'int', 'int64': '
def _maybe_pandas_data(data, feature_names, feature_types): def _maybe_pandas_data(data, feature_names, feature_types):
""" Extract internal data from pd.DataFrame for DMatrix data """ """Extract internal data from pd.DataFrame for DMatrix data"""
if not (PANDAS_INSTALLED and isinstance(data, DataFrame)): if not (PANDAS_INSTALLED and isinstance(data, DataFrame)):
return data, feature_names, feature_types return data, feature_names, feature_types
@ -340,7 +340,7 @@ def _maybe_pandas_label(label):
def _maybe_cudf_dataframe(data, feature_names, feature_types): def _maybe_cudf_dataframe(data, feature_names, feature_types):
'''Extract internal data from cudf.DataFrame for DMatrix data.''' """Extract internal data from cudf.DataFrame for DMatrix data."""
if not (CUDF_INSTALLED and isinstance(data, if not (CUDF_INSTALLED and isinstance(data,
(CUDF_DataFrame, CUDF_Series))): (CUDF_DataFrame, CUDF_Series))):
return data, feature_names, feature_types return data, feature_names, feature_types
@ -369,9 +369,7 @@ DT_TYPE_MAPPER2 = {'bool': 'i', 'int': 'int', 'real': 'float'}
def _maybe_dt_data(data, feature_names, feature_types): def _maybe_dt_data(data, feature_names, feature_types):
""" """Validate feature names and types if data table"""
Validate feature names and types if data table
"""
if not isinstance(data, DataTable): if not isinstance(data, DataTable):
return data, feature_names, feature_types return data, feature_names, feature_types
@ -396,7 +394,7 @@ def _maybe_dt_data(data, feature_names, feature_types):
def _maybe_dt_array(array): def _maybe_dt_array(array):
""" Extract numpy array from single column data table """ """Extract numpy array from single column data table"""
if not isinstance(array, DataTable) or array is None: if not isinstance(array, DataTable) or array is None:
return array return array
@ -473,7 +471,6 @@ class DMatrix(object):
nthread : integer, optional nthread : integer, optional
Number of threads to use for loading data from numpy array. If -1, Number of threads to use for loading data from numpy array. If -1,
uses maximum threads available on the system. uses maximum threads available on the system.
""" """
# force into void_p, mac need to pass things in as void_p # force into void_p, mac need to pass things in as void_p
if data is None: if data is None:
@ -539,9 +536,7 @@ class DMatrix(object):
self.feature_types = feature_types self.feature_types = feature_types
def _init_from_csr(self, csr): def _init_from_csr(self, csr):
""" """Initialize data from a CSR matrix."""
Initialize data from a CSR matrix.
"""
if len(csr.indices) != len(csr.data): if len(csr.indices) != len(csr.data):
raise ValueError('length mismatch: {} vs {}'.format(len(csr.indices), len(csr.data))) raise ValueError('length mismatch: {} vs {}'.format(len(csr.indices), len(csr.data)))
handle = ctypes.c_void_p() handle = ctypes.c_void_p()
@ -555,9 +550,7 @@ class DMatrix(object):
self.handle = handle self.handle = handle
def _init_from_csc(self, csc): def _init_from_csc(self, csc):
""" """Initialize data from a CSC matrix."""
Initialize data from a CSC matrix.
"""
if len(csc.indices) != len(csc.data): if len(csc.indices) != len(csc.data):
raise ValueError('length mismatch: {} vs {}'.format(len(csc.indices), len(csc.data))) raise ValueError('length mismatch: {} vs {}'.format(len(csc.indices), len(csc.data)))
handle = ctypes.c_void_p() handle = ctypes.c_void_p()
@ -571,8 +564,7 @@ class DMatrix(object):
self.handle = handle self.handle = handle
def _init_from_npy2d(self, mat, missing, nthread): def _init_from_npy2d(self, mat, missing, nthread):
""" """Initialize data from a 2-D numpy matrix.
Initialize data from a 2-D numpy matrix.
If ``mat`` does not have ``order='C'`` (aka row-major) or is not contiguous, If ``mat`` does not have ``order='C'`` (aka row-major) or is not contiguous,
a temporary copy will be made. a temporary copy will be made.
@ -609,9 +601,7 @@ class DMatrix(object):
self.handle = handle self.handle = handle
def _init_from_dt(self, data, nthread): def _init_from_dt(self, data, nthread):
""" """Initialize data from a datatable Frame."""
Initialize data from a datatable Frame.
"""
ptrs = (ctypes.c_void_p * data.ncols)() ptrs = (ctypes.c_void_p * data.ncols)()
if hasattr(data, "internal") and hasattr(data.internal, "column"): if hasattr(data, "internal") and hasattr(data.internal, "column"):
# datatable>0.8.0 # datatable>0.8.0
@ -640,9 +630,7 @@ class DMatrix(object):
self.handle = handle self.handle = handle
def _init_from_columnar(self, df, missing): def _init_from_columnar(self, df, missing):
'''Initialize DMatrix from columnar memory format. """Initialize DMatrix from columnar memory format."""
'''
interfaces = _extract_interface_from_cudf(df) interfaces = _extract_interface_from_cudf(df)
handle = ctypes.c_void_p() handle = ctypes.c_void_p()
has_missing = missing is not None has_missing = missing is not None
@ -721,7 +709,7 @@ class DMatrix(object):
c_bst_ulong(len(data)))) c_bst_ulong(len(data))))
def set_interface_info(self, field, data): def set_interface_info(self, field, data):
'''Set info type peoperty into DMatrix.''' """Set info type peoperty into DMatrix."""
interfaces = _extract_interface_from_cudf(data) interfaces = _extract_interface_from_cudf(data)
_check_call(_LIB.XGDMatrixSetInfoFromInterface(self.handle, _check_call(_LIB.XGDMatrixSetInfoFromInterface(self.handle,
c_str(field), c_str(field),
@ -1350,8 +1338,7 @@ class Booster(object):
def predict(self, data, output_margin=False, ntree_limit=0, pred_leaf=False, def predict(self, data, output_margin=False, ntree_limit=0, pred_leaf=False,
pred_contribs=False, approx_contribs=False, pred_interactions=False, pred_contribs=False, approx_contribs=False, pred_interactions=False,
validate_features=True): validate_features=True):
""" """Predict with data.
Predict with data.
.. note:: This function is not thread safe. .. note:: This function is not thread safe.
@ -1461,8 +1448,7 @@ class Booster(object):
return preds return preds
def save_model(self, fname): def save_model(self, fname):
""" """Save the model to a file.
Save the model to a file.
The model is saved in an XGBoost internal binary format which is The model is saved in an XGBoost internal binary format which is
universal among the various XGBoost interfaces. Auxiliary attributes of universal among the various XGBoost interfaces. Auxiliary attributes of
@ -1480,8 +1466,7 @@ class Booster(object):
raise TypeError("fname must be a string") raise TypeError("fname must be a string")
def save_raw(self): def save_raw(self):
""" """Save the model to a in memory buffer representation
Save the model to a in memory buffer representation
Returns Returns
------- -------
@ -1495,8 +1480,7 @@ class Booster(object):
return ctypes2buffer(cptr, length.value) return ctypes2buffer(cptr, length.value)
def load_model(self, fname): def load_model(self, fname):
""" """Load the model from a file.
Load the model from a file.
The model is loaded from an XGBoost internal binary format which is The model is loaded from an XGBoost internal binary format which is
universal among the various XGBoost interfaces. Auxiliary attributes of universal among the various XGBoost interfaces. Auxiliary attributes of
@ -1518,8 +1502,7 @@ class Booster(object):
_check_call(_LIB.XGBoosterLoadModelFromBuffer(self.handle, ptr, length)) _check_call(_LIB.XGBoosterLoadModelFromBuffer(self.handle, ptr, length))
def dump_model(self, fout, fmap='', with_stats=False, dump_format="text"): def dump_model(self, fout, fmap='', with_stats=False, dump_format="text"):
""" """Dump model into a text or JSON file.
Dump model into a text or JSON file.
Parameters Parameters
---------- ----------
@ -1553,8 +1536,7 @@ class Booster(object):
fout.close() fout.close()
def get_dump(self, fmap='', with_stats=False, dump_format="text"): def get_dump(self, fmap='', with_stats=False, dump_format="text"):
""" """Returns the model dump as a list of strings.
Returns the model dump as a list of strings.
Parameters Parameters
---------- ----------