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

[doc] Remove parameter type in Python doc strings. (#9005)

Browse Source
This commit is contained in:
Jiaming Yuan
2023-04-01 04:04:30 +08:00
committed by GitHub
parent 4caca2947d
commit 720a8c3273
6 changed files with 105 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
python-package/xgboost/core.py
View File

@@ -94,9 +94,9 @@ def from_cstr_to_pystr(data: CStrPptr, length: c_bst_ulong) -> List[str]:
Parameters
----------
data : ctypes pointer
data :
pointer to data
length : ctypes pointer
length :
pointer to length of data
"""
res = []
@@ -131,9 +131,9 @@ def _expect(expectations: Sequence[Type], got: Type) -> str:
Parameters
----------
expectations: sequence
expectations :
a list of expected value.
got:
got :
actual input
Returns
@@ -263,7 +263,7 @@ def _check_call(ret: int) -> None:
Parameters
----------
ret : int
ret :
return value from API calls
"""
if ret != 0:
@@ -271,10 +271,10 @@ def _check_call(ret: int) -> None:
def build_info() -> dict:
"""Build information of XGBoost. The returned value format is not stable. Also, please
note that build time dependency is not the same as runtime dependency. For instance,
it's possible to build XGBoost with older CUDA version but run it with the lastest
one.
"""Build information of XGBoost. The returned value format is not stable. Also,
please note that build time dependency is not the same as runtime dependency. For
instance, it's possible to build XGBoost with older CUDA version but run it with the
lastest one.
.. versionadded:: 1.6.0
@@ -658,28 +658,28 @@ class DMatrix: # pylint: disable=too-many-instance-attributes,too-many-public-m
data :
Data source of DMatrix. See :ref:`py-data` for a list of supported input
types.
label : array_like
label :
Label of the training data.
weight : array_like
weight :
Weight for each instance.
.. note:: For ranking task, weights are per-group.
.. note::
In ranking task, one weight is assigned to each group (not each
data point). This is because we only care about the relative
ordering of data points within each group, so it doesn't make
sense to assign weights to individual data points.
For ranking task, weights are per-group. In ranking task, one weight
is assigned to each group (not each data point). This is because we
only care about the relative ordering of data points within each group,
so it doesn't make sense to assign weights to individual data points.
base_margin: array_like
base_margin :
Base margin used for boosting from existing model.
missing : float, optional
Value in the input data which needs to be present as a missing
value. If None, defaults to np.nan.
silent : boolean, optional
missing :
Value in the input data which needs to be present as a missing value. If
None, defaults to np.nan.
silent :
Whether print messages during construction
feature_names : list, optional
feature_names :
Set names for features.
feature_types : FeatureTypes
feature_types :
Set types for features. When `enable_categorical` is set to `True`, string
"c" represents categorical data type while "q" represents numerical feature
@@ -689,20 +689,20 @@ class DMatrix: # pylint: disable=too-many-instance-attributes,too-many-public-m
`.cat.codes` method. This is useful when users want to specify categorical
features without having to construct a dataframe as input.
nthread : integer, optional
nthread :
Number of threads to use for loading data when parallelization is
applicable. If -1, uses maximum threads available on the system.
group : array_like
group :
Group size for all ranking group.
qid : array_like
qid :
Query ID for data samples, used for ranking.
label_lower_bound : array_like
label_lower_bound :
Lower bound for survival training.
label_upper_bound : array_like
label_upper_bound :
Upper bound for survival training.
feature_weights : array_like, optional
feature_weights :
Set feature weights for column sampling.
enable_categorical: boolean, optional
enable_categorical :
.. versionadded:: 1.3.0
@@ -1712,6 +1712,7 @@ class Booster:
string.
.. versionadded:: 1.0.0
"""
json_string = ctypes.c_char_p()
length = c_bst_ulong()
@@ -1744,8 +1745,8 @@ class Booster:
Returns
-------
booster: `Booster`
a copied booster model
booster :
A copied booster model
"""
return copy.copy(self)
@@ -1754,12 +1755,12 @@ class Booster:
Parameters
----------
key : str
key :
The key to get attribute from.
Returns
-------
value : str
value :
The attribute value of the key, returns None if attribute do not exist.
"""
ret = ctypes.c_char_p()
@@ -1878,9 +1879,9 @@ class Booster:
Parameters
----------
params: dict/list/str
params :
list of key,value pairs, dict of key to value or simply str key
value: optional
value :
value of the specified parameter, when params is str key
"""
if isinstance(params, Mapping):
@@ -1903,11 +1904,11 @@ class Booster:
Parameters
----------
dtrain : DMatrix
dtrain :
Training data.
iteration : int
iteration :
Current iteration number.
fobj : function
fobj :
Customized objective function.
"""
@@ -2205,8 +2206,7 @@ class Booster:
Parameters
----------
data : numpy.ndarray/scipy.sparse.csr_matrix/cupy.ndarray/
cudf.DataFrame/pd.DataFrame
data :
The input data, must not be a view for numpy array. Set
``predictor`` to ``gpu_predictor`` for running prediction on CuPy
array or CuDF DataFrame.
@@ -2390,7 +2390,7 @@ class Booster:
Parameters
----------
fname : string or os.PathLike
fname :
Output file name
"""
@@ -2494,13 +2494,13 @@ class Booster:
Parameters
----------
fout : string or os.PathLike
fout :
Output file name.
fmap : string or os.PathLike, optional
fmap :
Name of the file containing feature map names.
with_stats : bool, optional
with_stats :
Controls whether the split statistics are output.
dump_format : string, optional
dump_format :
Format of model dump file. Can be 'text' or 'json'.
"""
if isinstance(fout, (str, os.PathLike)):
@@ -2604,9 +2604,9 @@ class Booster:
Parameters
----------
fmap:
fmap :
The name of feature map file.
importance_type:
importance_type :
One of the importance types defined above.
Returns
@@ -2655,7 +2655,7 @@ class Booster:
Parameters
----------
fmap: str or os.PathLike (optional)
fmap :
The name of feature map file.
"""
# pylint: disable=too-many-locals
@@ -2821,15 +2821,15 @@ class Booster:
Parameters
----------
feature: str
feature :
The name of the feature.
fmap: str or os.PathLike (optional)
fmap:
The name of feature map file.
bin: int, default None
bin :
The maximum number of bins.
Number of bins equals number of unique split values n_unique,
if bins == None or bins > n_unique.
as_pandas: bool, default True
as_pandas :
Return pd.DataFrame when pandas is installed.
If False or pandas is not installed, return numpy ndarray.

63
python-package/xgboost/plotting.py
View File

@@ -1,10 +1,9 @@
# pylint: disable=too-many-locals, too-many-arguments, invalid-name,
# pylint: disable=too-many-branches
# coding: utf-8
"""Plotting Library."""
import json
from io import BytesIO
from typing import Any, Optional
from typing import Any, Optional, Union
import numpy as np
@@ -17,7 +16,7 @@ GraphvizSource = Any # real type is graphviz.Source
def plot_importance(
booster: Booster,
booster: Union[XGBModel, Booster, dict],
ax: Optional[Axes] = None,
height: float = 0.2,
xlim: Optional[tuple] = None,
@@ -37,40 +36,42 @@ def plot_importance(
Parameters
----------
booster : Booster, XGBModel or dict
booster :
Booster or XGBModel instance, or dict taken by Booster.get_fscore()
ax : matplotlib Axes, default None
ax : matplotlib Axes
Target axes instance. If None, new figure and axes will be created.
grid : bool, Turn the axes grids on or off. Default is True (On).
importance_type : str, default "weight"
grid :
Turn the axes grids on or off. Default is True (On).
importance_type :
How the importance is calculated: either "weight", "gain", or "cover"
* "weight" is the number of times a feature appears in a tree
* "gain" is the average gain of splits which use the feature
* "cover" is the average coverage of splits which use the feature
where coverage is defined as the number of samples affected by the split
max_num_features : int, default None
Maximum number of top features displayed on plot. If None, all features will be displayed.
height : float, default 0.2
max_num_features :
Maximum number of top features displayed on plot. If None, all features will be
displayed.
height :
Bar height, passed to ax.barh()
xlim : tuple, default None
xlim :
Tuple passed to axes.xlim()
ylim : tuple, default None
ylim :
Tuple passed to axes.ylim()
title : str, default "Feature importance"
title :
Axes title. To disable, pass None.
xlabel : str, default "F score"
xlabel :
X axis title label. To disable, pass None.
ylabel : str, default "Features"
ylabel :
Y axis title label. To disable, pass None.
fmap: str or os.PathLike (optional)
fmap :
The name of feature map file.
show_values : bool, default True
show_values :
Show values on plot. To disable, pass False.
values_format : str, default "{v}"
Format string for values. "v" will be replaced by the value of the feature importance.
e.g. Pass "{v:.2f}" in order to limit the number of digits after the decimal point
to two, for each value printed on the graph.
values_format :
Format string for values. "v" will be replaced by the value of the feature
importance. e.g. Pass "{v:.2f}" in order to limit the number of digits after
the decimal point to two, for each value printed on the graph.
kwargs :
Other keywords passed to ax.barh()
@@ -146,7 +147,7 @@ def plot_importance(
def to_graphviz(
booster: Booster,
booster: Union[Booster, XGBModel],
fmap: PathLike = "",
num_trees: int = 0,
rankdir: Optional[str] = None,
@@ -162,19 +163,19 @@ def to_graphviz(
Parameters
----------
booster : Booster, XGBModel
booster :
Booster or XGBModel instance
fmap: str (optional)
fmap :
The name of feature map file
num_trees : int, default 0
num_trees :
Specify the ordinal number of target tree
rankdir : str, default "UT"
rankdir :
Passed to graphviz via graph_attr
yes_color : str, default '#0000FF'
yes_color :
Edge color when meets the node condition.
no_color : str, default '#FF0000'
no_color :
Edge color when doesn't meet the node condition.
condition_node_params : dict, optional
condition_node_params :
Condition node configuration for for graphviz. Example:
.. code-block:: python
@@ -183,7 +184,7 @@ def to_graphviz(
'style': 'filled,rounded',
'fillcolor': '#78bceb'}
leaf_node_params : dict, optional
leaf_node_params :
Leaf node configuration for graphviz. Example:
.. code-block:: python
@@ -192,7 +193,7 @@ def to_graphviz(
'style': 'filled',
'fillcolor': '#e48038'}
\\*\\*kwargs: dict, optional
kwargs :
Other keywords passed to graphviz graph_attr, e.g. ``graph [ {key} = {value} ]``
Returns

18
python-package/xgboost/sklearn.py
View File

@@ -1012,9 +1012,9 @@ class XGBModel(XGBModelBase):
verbose :
If `verbose` is True and an evaluation set is used, the evaluation metric
measured on the validation set is printed to stdout at each boosting stage.
If `verbose` is an integer, the evaluation metric is printed at each `verbose`
boosting stage. The last boosting stage / the boosting stage found by using
`early_stopping_rounds` is also printed.
If `verbose` is an integer, the evaluation metric is printed at each
`verbose` boosting stage. The last boosting stage / the boosting stage found
by using `early_stopping_rounds` is also printed.
xgb_model :
file name of stored XGBoost model or 'Booster' instance XGBoost model to be
loaded before training (allows training continuation).
@@ -1590,12 +1590,12 @@ class XGBClassifier(XGBModel, XGBClassifierMixIn, XGBClassifierBase):
Parameters
----------
X : array_like
X :
Feature matrix. See :ref:`py-data` for a list of supported types.
validate_features : bool
validate_features :
When this is True, validate that the Booster's and data's feature_names are
identical. Otherwise, it is assumed that the feature_names are the same.
base_margin : array_like
base_margin :
Margin added to prediction.
iteration_range :
Specifies which layer of trees are used in prediction. For example, if a
@@ -1964,9 +1964,9 @@ class XGBRanker(XGBModel, XGBRankerMixIn):
verbose :
If `verbose` is True and an evaluation set is used, the evaluation metric
measured on the validation set is printed to stdout at each boosting stage.
If `verbose` is an integer, the evaluation metric is printed at each `verbose`
boosting stage. The last boosting stage / the boosting stage found by using
`early_stopping_rounds` is also printed.
If `verbose` is an integer, the evaluation metric is printed at each
`verbose` boosting stage. The last boosting stage / the boosting stage found
by using `early_stopping_rounds` is also printed.
xgb_model :
file name of stored XGBoost model or 'Booster' instance XGBoost model to be
loaded before training (allows training continuation).

2
python-package/xgboost/training.py
View File

@@ -95,7 +95,7 @@ def train(
feval :
.. deprecated:: 1.6.0
Use `custom_metric` instead.
maximize : bool
maximize :
Whether to maximize feval.
early_stopping_rounds :
Activates early stopping. Validation metric needs to improve at least once in