Merge branch 'isolate-numba' of https://github.com/fkiraly/tsbootstrap …

…into isolate-numba

.github/workflows/CI.yml

@@ -2,14 +2,14 @@
 name: CI
 
 on:
-  push:
-    paths:
-      - 'src/**'
-      - 'tests/**'
-      - '.github/workflows/CI.yml'
-      - 'pyproject.toml'
-      - 'poetry.lock'
-      - 'docs/**'
+  # push:
+  #   paths:
+  #     - 'src/**'
+  #     - 'tests/**'
+  #     - '.github/workflows/CI.yml'
+  #     - 'pyproject.toml'
+  #     - 'poetry.lock'
+  #     - 'docs/**'
   pull_request:
     branches:
       - main
@@ -178,13 +178,13 @@ jobs:
     #    fail_ci_if_error: true
     #    verbose: true
 
-  commitlint:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - uses: wagoid/commitlint-github-action@v4
+  # commitlint:
+  #   runs-on: ubuntu-latest
+  #   steps:
+  #     - uses: actions/checkout@v3
+  #       with:
+  #         fetch-depth: 0
+  #     - uses: wagoid/commitlint-github-action@v4
 
 
   docs:

.gitignore

@@ -133,3 +133,6 @@ README_template.md
 
 # scratch file
 scratch*
+
+# poetry.lock
+poetry.lock

README.md

@@ -17,8 +17,8 @@
     <a href="https://pypi.org/project/tsbootstrap/">
         <img src="https://img.shields.io/pypi/pyversions/tsbootstrap?color=5D6D7E&logo=python" alt="pypi-python-version" />
     </a>
-    <a href="https://pypi.org/project/tsbootstrap/">
-        <img src="https://img.shields.io/pypi/dt/tsbootstrap?color=5D6D7E" alt="pypi-downloads" />
+    <a href="https://pepy.tech/project/tsbootstrap">
+        <img src="https://static.pepy.tech/badge/tsbootstrap" alt="Downloads"/>
     </a>
     <img src="https://img.shields.io/github/license/eli64s/readme-ai?color=5D6D7E" alt="github-license" />
     </a>
@@ -140,7 +140,6 @@ The `tsbootstrap` package contains various modules that handle tasks such as boo
 | [.codeclimate.yml](https://github.com/astrogilda/tsbootstrap/blob/main/.codeclimate.yml)                 | Configuration for Code Climate quality checks. |
 | [.gitignore](https://github.com/astrogilda/tsbootstrap/blob/main/.gitignore)                 | Specifies files and folders to be ignored by Git. |
 | [.pre-commit-config.yaml](https://github.com/astrogilda/tsbootstrap/blob/main/.pre-commit-config.yaml)                 | Configuration for pre-commit hooks. |
-| [poetry.lock](https://github.com/astrogilda/tsbootstrap/blob/main/poetry.lock)                 | Lock file generated by Poetry, pinning exact package versions. |
 | [poetry.toml](https://github.com/astrogilda/tsbootstrap/blob/main/poetry.toml)                 | Configuration file for Poetry package management. |
 | [tsbootstrap_logo.png](https://github.com/astrogilda/tsbootstrap/blob/main/tsbootstrap_logo.png)                 | Project logo image. |
 

src/tsbootstrap/base_bootstrap.py

@@ -42,7 +42,7 @@ def bootstrap(
         self,
         X: np.ndarray,
         return_indices: bool = False,
-        exog: np.ndarray | None = None,
+        y: np.ndarray | None = None,
         test_ratio: float = None,
     ) -> Iterator[np.ndarray] | Iterator[tuple[list[np.ndarray], np.ndarray]]:
         """Generate indices to split data into training and test set.
@@ -56,7 +56,7 @@ def bootstrap(
             If True, a second output is retured, integer locations of
             index references for the bootstrap sample, in reference to original indices.
             Indexed values do are not necessarily identical with bootstrapped values.
-        exog : array-like of shape (n_timepoints, n_features_exog), default=None
+        y : array-like of shape (n_timepoints, n_features_exog), default=None
             Exogenous time series to use in bootstrapping.
         test_ratio : float, default=0.2
             The ratio of test samples to total samples.
@@ -92,14 +92,14 @@ def bootstrap(
 
         X_train, X_test = time_series_split(X, test_ratio=test_ratio)
 
-        if exog is not None:
-            self._check_input(exog)
-            exog_train, _ = time_series_split(exog, test_ratio=test_ratio)
+        if y is not None:
+            self._check_input(y)
+            exog_train, _ = time_series_split(y, test_ratio=test_ratio)
         else:
             exog_train = None
 
         tuple_iter = self._generate_samples(
-            X=X_train, return_indices=return_indices, exog=exog_train
+            X=X_train, return_indices=return_indices, y=exog_train
         )
 
         yield from tuple_iter
@@ -108,7 +108,7 @@ def _generate_samples(
         self,
         X: np.ndarray,
         return_indices: bool = False,
-        exog: np.ndarray | None = None,
+        y: np.ndarray | None = None,
     ) -> Iterator[np.ndarray] | Iterator[tuple[list[np.ndarray], np.ndarray]]:
         """Generates bootstrapped samples directly.
 
@@ -124,9 +124,7 @@ def _generate_samples(
 
         """
         for _ in range(self.config.n_bootstraps):
-            indices, data = self._generate_samples_single_bootstrap(
-                X=X, exog=exog
-            )
+            indices, data = self._generate_samples_single_bootstrap(X=X, y=y)
             data = np.concatenate(data, axis=0)
             if return_indices:
                 yield indices, data  # type: ignore
@@ -135,7 +133,7 @@ def _generate_samples(
 
     @abstractmethod
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         """Generates list of bootstrapped indices and samples for a single bootstrap iteration.
 
@@ -216,9 +214,7 @@ def __init__(
         self.X_fitted = None
         self.coefs = None
 
-    def _fit_model(
-        self, X: np.ndarray, exog: np.ndarray | None = None
-    ) -> None:
+    def _fit_model(self, X: np.ndarray, y: np.ndarray | None = None) -> None:
         """Fits the model to the data and stores the residuals."""
         if (
             self.resids is None
@@ -232,7 +228,7 @@ def _fit_model(
                 save_models=self.config.save_models,
                 **self.config.model_params,
             )
-            self.fit_model = fit_obj.fit(X=X, exog=exog).model
+            self.fit_model = fit_obj.fit(X=X, y=y).model
             self.X_fitted = fit_obj.get_fitted_X()
             self.resids = fit_obj.get_residuals()
             self.order = fit_obj.get_order()
@@ -534,7 +530,7 @@ def _fit_resids_model(self, X: np.ndarray) -> None:
                 save_models=self.config.save_resids_models,
                 **self.config.resids_model_params,
             )
-            resids_fit_model = resids_fit_obj.fit(X, exog=None).model
+            resids_fit_model = resids_fit_obj.fit(X, y=None).model
             resids_order = resids_fit_obj.get_order()
             resids_coefs = resids_fit_obj.get_coefs()
             self.resids_fit_model = resids_fit_model

src/tsbootstrap/block_bootstrap.py

@@ -99,7 +99,7 @@ def _generate_blocks(self, X: np.ndarray) -> list[np.ndarray]:
         return blocks
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         """
         Generate a single bootstrap sample.
@@ -174,7 +174,7 @@ def __init__(self, config: BaseBlockBootstrapConfig, **kwargs):
             ](config=config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         """
         Generate a single bootstrap sample using either the base BlockBootstrap method or the specified bootstrap_type.
@@ -194,7 +194,7 @@ def _generate_samples_single_bootstrap(
             (
                 block_indices,
                 block_data,
-            ) = super()._generate_samples_single_bootstrap(X=X, exog=exog)
+            ) = super()._generate_samples_single_bootstrap(X=X, y=y)
         else:
             # Generate samples using the specified bootstrap_type
             if hasattr(
@@ -204,7 +204,7 @@ def _generate_samples_single_bootstrap(
                     block_indices,
                     block_data,
                 ) = self.bootstrap_instance._generate_samples_single_bootstrap(
-                    X=X, exog=exog
+                    X=X, y=y
                 )
             else:
                 raise NotImplementedError(

src/tsbootstrap/bootstrap.py

@@ -57,9 +57,9 @@ def __init__(self, config: BaseResidualBootstrapConfig):
         super().__init__(config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
-        self._fit_model(X=X, exog=exog)
+        self._fit_model(X=X, y=y)
 
         # Resample residuals
         resampled_indices = generate_random_indices(
@@ -105,10 +105,10 @@ def __init__(
         self.block_bootstrap = BaseBlockBootstrap(config=block_config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and store residuals, fitted values, etc.
-        BaseResidualBootstrap._fit_model(self, X=X, exog=exog)
+        BaseResidualBootstrap._fit_model(self, X=X, y=y)
 
         # Generate blocks of residuals
         (
@@ -144,10 +144,10 @@ class WholeMarkovBootstrap(BaseMarkovBootstrap):
     """
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and store residuals, fitted values, etc.
-        self._fit_model(X=X, exog=exog)
+        self._fit_model(X=X, y=y)
 
         # Fit HMM to residuals, just once.
         random_seed = self.config.rng.integers(0, 1000)
@@ -217,10 +217,10 @@ def __init__(
         self.block_bootstrap = BaseBlockBootstrap(config=block_config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and store residuals, fitted values, etc.
-        super()._fit_model(X=X, exog=exog)
+        super()._fit_model(X=X, y=y)
 
         # Generate blocks of residuals
         (
@@ -279,7 +279,7 @@ class WholeStatisticPreservingBootstrap(BaseStatisticPreservingBootstrap):
     """
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         if self.statistic_X is None:
             self.statistic_X = self._calculate_statistic(X=X)
@@ -338,7 +338,7 @@ def __init__(
         self.block_bootstrap = BaseBlockBootstrap(config=block_config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         if self.statistic_X is None:
             self.statistic_X = super()._calculate_statistic(X=X)
@@ -385,10 +385,10 @@ class WholeDistributionBootstrap(BaseDistributionBootstrap):
     """
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and residuals
-        self._fit_model(X=X, exog=exog)
+        self._fit_model(X=X, y=y)
         # Fit the specified distribution to the residuals
         if not self.config.refit:
             if self.resids_dist is None or self.resids_dist_params == ():
@@ -474,10 +474,10 @@ def __init__(
         self.block_bootstrap = BaseBlockBootstrap(config=block_config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and residuals
-        super()._fit_model(X=X, exog=exog)
+        super()._fit_model(X=X, y=y)
         (
             block_indices,
             block_data,
@@ -538,9 +538,9 @@ class WholeSieveBootstrap(BaseSieveBootstrap):
     """
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
-        self._fit_model(X=X, exog=exog)
+        self._fit_model(X=X, y=y)
         self._fit_resids_model(X=self.resids)
 
         ts_simulator = TimeSeriesSimulator(
@@ -593,10 +593,10 @@ def __init__(
         self.block_bootstrap = BaseBlockBootstrap(config=block_config)
 
     def _generate_samples_single_bootstrap(
-        self, X: np.ndarray, exog: np.ndarray | None = None
+        self, X: np.ndarray, y: np.ndarray | None = None
     ) -> tuple[list[np.ndarray], list[np.ndarray]]:
         # Fit the model and residuals
-        super()._fit_model(X=X, exog=exog)
+        super()._fit_model(X=X, y=y)
         super()._fit_resids_model(X=self.resids)
 
         ts_simulator = TimeSeriesSimulator(

src/tsbootstrap/ranklags.py

@@ -43,7 +43,7 @@ def __init__(
         X: np.ndarray,
         model_type: ModelTypes,
         max_lag: Integral = 10,
-        exog: np.ndarray | None = None,
+        y: np.ndarray | None = None,
         save_models: bool = False,
     ) -> None:
         """
@@ -57,15 +57,15 @@ def __init__(
             The type of model to fit. One of 'ar', 'arima', 'sarima', 'var', 'arch'.
         max_lag : int, optional, default=10
             Maximum lag to consider.
-        exog : np.ndarray, optional, default=None
+        y : np.ndarray, optional, default=None
             Exogenous variables to include in the model.
         save_models : bool, optional, default=False
             Whether to save the models.
         """
         self.X = X
         self.max_lag = max_lag
         self.model_type = model_type
-        self.exog = exog
+        self.y = y
         self.save_models = save_models
         self.models = []
 
@@ -146,7 +146,7 @@ def model_type(self, value: ModelTypes) -> None:
         self._model_type = value.lower()
 
     @property
-    def exog(self) -> np.ndarray | None:
+    def y(self) -> np.ndarray | None:
         """
         Exogenous variables to include in the model.
 
@@ -155,21 +155,21 @@ def exog(self) -> np.ndarray | None:
         np.ndarray
             Exogenous variables to include in the model.
         """
-        return self._exog
+        return self._y
 
-    @exog.setter
-    def exog(self, value: np.ndarray | None) -> None:
+    @y.setter
+    def y(self, value: np.ndarray | None) -> None:
         """
         Set the exogenous variables to include in the model.
 
         Parameters
         ----------
-        exog : np.ndarray
+        y : np.ndarray
             Exogenous variables to include in the model.
         """
         if value is not None and not isinstance(value, np.ndarray):
-            raise TypeError("exog must be a numpy array.")
-        self._exog = value
+            raise TypeError("y must be a numpy array.")
+        self._y = value
 
     def rank_lags_by_aic_bic(self) -> tuple[np.ndarray, np.ndarray]:
         """
@@ -188,7 +188,7 @@ def rank_lags_by_aic_bic(self) -> tuple[np.ndarray, np.ndarray]:
         for lag in range(1, self.max_lag + 1):
             try:
                 fit_obj = TSFit(order=lag, model_type=self.model_type)
-                model = fit_obj.fit(X=self.X, exog=self.exog).model
+                model = fit_obj.fit(X=self.X, y=self.y).model
             except Exception as e:
                 # raise RuntimeError(f"An error occurred during fitting: {e}")
                 print(f"{e}")