[DOC] Remove optional from docstrings (#1458)

* [DOC] Remove optional from docstrings (#1451)
* find `optional \(default=(.*)\)`, replace with `default=$1`
* review all changes

* add my contribution

.all-contributorsrc

@@ -2387,6 +2387,15 @@
       "contributions": [
         "doc"
       ]
+    },
+    {
+      "login": "griegner",
+      "name": "Gabriel Riegner",
+      "avatar_url": "https://avatars.githubusercontent.com/u/54326829?v=4",
+      "profile": "https://github.com/griegner",
+      "contributions": [
+        "doc"
+      ]
     }
   ],
   "commitType": "docs"

aeon/annotation/base/_base.py

@@ -31,11 +31,11 @@ class BaseSeriesAnnotator(BaseEstimator):
 
     Parameters
     ----------
-    fmt : str {"dense", "sparse"}, optional (default="dense")
+    fmt : str {"dense", "sparse"}, default="dense"
         annotation output format:
         * If "sparse", a sub-series of labels for only the outliers in X is returned,
         * If "dense", a series of labels for all values in X is returned.
-    labels : str {"indicator", "score"}, optional (default="indicator")
+    labels : str {"indicator", "score"}, default="indicator"
         annotation output labels:
         * If "indicator", returned values are boolean, indicating whether a value is an
         outlier,
@@ -210,7 +210,7 @@ def fit_predict(self, X, Y=None):
         ----------
         X : pd.DataFrame, pd.Series or np.ndarray
             Data to be transformed
-        Y : pd.Series or np.ndarray, optional (default=None)
+        Y : pd.Series or np.ndarray, default=None
             Target values of data to be predicted.
 
         Returns

aeon/anomaly_detection/_stray.py

@@ -27,22 +27,22 @@ class STRAY(BaseTransformer):
 
     Parameters
     ----------
-    alpha : float, optional (default=0.01)
+    alpha : float, default=0.01
         Threshold for determining the cutoff for outliers. Observations are
         considered outliers if they fall in the (1 - alpha) tail of
         the distribution of the nearest-neighbor distances between exemplars.
-    k : int, optional (default=10)
+    k : int, default=10
         Number of neighbours considered.
     knn_algorithm : str {"auto", "ball_tree", "kd_tree", "brute"}, optional
         (default="brute")
         Algorithm used to compute the nearest neighbors, from
         sklearn.neighbors.NearestNeighbors
-    p : float, optional (default=0.5)
+    p : float, default=0.5
         Proportion of possible candidates for outliers. This defines the starting point
         for the bottom up searching algorithm.
-    size_threshold : int, optional (default=50)
+    size_threshold : int, default=50
         Sample size to calculate an emperical threshold.
-    outlier_tail : str {"min", "max"}, optional (default="max")
+    outlier_tail : str {"min", "max"}, default="max"
         Direction of the outlier tail.
 
     Attributes

aeon/benchmarking/benchmarks.py

@@ -38,7 +38,7 @@ def add_estimator(
         ----------
         estimator : BaseEstimator object
             Estimator to add to the benchmark.
-        estimator_id : str, optional (default=None)
+        estimator_id : str, default=None
             Identifier for estimator. If none given then uses estimator's class name.
 
         """

aeon/benchmarking/forecasting.py

@@ -84,7 +84,7 @@ def add_task(
             Splitter used for generating validation folds.
         scorers : a list of Callable scoring functions
             Each scoring function output will be included in the results.
-        task_id : str, optional (default=None)
+        task_id : str, default=None
             Identifier for the benchmark task. If none given then uses dataset loader
             name combined with cv_splitter class name.
 

aeon/clustering/_kernel_k_means.py

@@ -44,7 +44,7 @@ class TimeSeriesKernelKMeans(BaseClusterer):
         convergence.
     verbose: bool, default=False
         Verbosity mode.
-    n_jobs : int or None, optional (default=None)
+    n_jobs : int or None, default=None
         The number of jobs to run in parallel for GAK cross-similarity matrix
         computations.
         ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.

aeon/datasets/_data_loaders.py

@@ -493,10 +493,10 @@ def _load_tsc_dataset(
     Parameters
     ----------
     name : string, file name to load from
-    split: None or one of "TRAIN", "TEST", optional (default=None)
+    split: None or one of "TRAIN", "TEST", default=None
         Whether to load the train or test instances of the problem.
         By default it loads both train and test instances (in a single container).
-    return_X_y: bool, optional (default=True)
+    return_X_y: bool, default=True
         If True, returns (features, target) separately instead of a single
         dataframe with columns for features and the target.
     return_data_type : str, optional, default = None

aeon/datasets/_single_problem_loaders.py

@@ -51,7 +51,7 @@ def load_gunpoint(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -97,7 +97,7 @@ def load_osuleaf(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -143,7 +143,7 @@ def load_italy_power_demand(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -196,7 +196,7 @@ def load_unit_test(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure containing series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -245,7 +245,7 @@ def load_arrow_head(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -293,7 +293,7 @@ def load_acsf1(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Raises
@@ -342,7 +342,7 @@ def load_basic_motions(split=None, return_X_y=True, return_type="numpy3d"):
     return_X_y: bool, default=True
         If True, returns (features, target) separately instead of as single data
         structure.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be "numpy3d" or "np-list".
 
     Raises
@@ -430,10 +430,10 @@ def load_japanese_vowels(split=None, return_X_y=True, return_type="np-list"):
 
     Parameters
     ----------
-    split: None or one of "TRAIN", "TEST", optional (default=None)
+    split: None or one of "TRAIN", "TEST", default=None
         Whether to load the train or test instances of the problem. By default it
         loads both train and test instances into a single array.
-    return_X_y: bool, optional (default=True)
+    return_X_y: bool, default=True
         If True, returns (features, target) separately instead of a single
         dataframe with columns for features and the target.
     return_type: string, default="np-list"
@@ -510,7 +510,7 @@ def load_longley(y_name="TOTEMP"):
 
     Parameters
     ----------
-    y_name: str, optional (default="TOTEMP")
+    y_name: str, default="TOTEMP"
         Name of target variable (y)
 
     Returns
@@ -1029,14 +1029,14 @@ def load_covid_3month(split=None, return_X_y=True, return_type="numpy3d"):
 
     Parameters
     ----------
-    split: None or str{"train", "test"}, optional (default=None)
+    split: None or str{"train", "test"}, default=None
         Whether to load the train or test partition of the problem. By
         default, it loads both.
-    return_X_y: bool, optional (default=True)
+    return_X_y: bool, default=True
         If True, returns (features, target) separately instead of a single
         dataframe with columns for
         features and the target.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Returns
@@ -1084,14 +1084,14 @@ def load_cardano_sentiment(split=None, return_X_y=True, return_type="numpy3d"):
 
     Parameters
     ----------
-    split: None or str{"train", "test"}, optional (default=None)
+    split: None or str{"train", "test"}, default=None
         Whether to load the train or test partition of the problem. By
         default, it loads both.
-    return_X_y: bool, optional (default=True)
+    return_X_y: bool, default=True
         If True, returns (features, target) separately instead of a single
         dataframe with columns for
         features and the target.
-    return_type: string, optional (default="numpy3d")
+    return_type: string, default="numpy3d"
         Data structure to use for time series, should be either "numpy2d" or "numpy3d".
 
     Returns

aeon/forecasting/ardl.py

@@ -306,7 +306,7 @@ def _fit(self, y, X=None, fh=None):
             if self.get_tag("y_input_type")=="univariate":
                 guaranteed to have a single column/variable
             A 1-d endogenous response variable. The dependent variable.
-        X : optional (default=None)
+        X : default=None
             guaranteed to be of a type in self.get_tag("X_inner_type")
             Exogeneous time series to fit to.
             Exogenous variables to include in the model. Either a DataFrame or
@@ -392,10 +392,10 @@ def _predict(self, fh, X=None):
 
         Parameters
         ----------
-        fh : guaranteed to be ForecastingHorizon or None, optional (default=None)
+        fh : guaranteed to be ForecastingHorizon or None, default=None
             The forecasting horizon with the steps ahead to to predict.
             If not passed in _fit, guaranteed to be passed here
-        X : optional (default=None)
+        X : default=None
             guaranteed to be of a type in self.get_tag("X_inner_type")
             Exogeneous time series for the forecast
 
@@ -442,10 +442,10 @@ def _update(self, y, X=None, update_params=True):
             if self.get_tag("y_input_type")=="multivariate":
                 guaranteed to have 2 or more columns
             if self.get_tag("y_input_type")=="both": no restrictions apply
-        X : optional (default=None)
+        X : default=None
             guaranteed to be of a type in self.get_tag("X_inner_type")
             Exogeneous time series for the forecast
-        update_params : bool, optional (default=True)
+        update_params : bool, default=True
             whether model parameters should be updated
 
         Returns