0.17.0

design

Author: bartzbeielstein

RELEASE_NOTES.txt

@@ -1,3 +1,13 @@
+spotpython-0.17.0
+
+- designs.py and spacefilling.py:
+Naming Conventions: The class names have been capitalized to follow the PEP 8 convention for class naming:
+1. `designs` -> `Designs`
+2. `spacefilling` -> `SpaceFilling`
+
+- The dimension of the design, k (int), must be specified by the user. There is not default dimension "2" anymore.
+
+
 spotpython-0.16.19:
 
 - kriging.py update completed

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotpython"
-version = "0.16.19"
+version = "0.17.0"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]
@@ -71,7 +71,7 @@ namespaces = true
 where = ["src"]
 
 [tool.black]
-line-length = 120
+line-length = 200
 target-version = ["py312"]
 
 [tool.pytest.ini_options]

src/spotpython/build/kriging.py

@@ -15,7 +15,7 @@
 from scipy.optimize import differential_evolution
 from scipy.linalg import cholesky as scipy_cholesky
 import pylab
-from spotpython.design.spacefilling import spacefilling
+from spotpython.design.spacefilling import SpaceFilling
 from spotpython.build.surrogates import surrogates
 from scipy.spatial.distance import squareform
 from scipy.spatial.distance import pdist
@@ -725,7 +725,7 @@ def initialize_matrices(self) -> None:
         The `pen_val` attribute is initialized as the natural logarithm of the
         variance of `nat_y`, multiplied by `n`, plus 1e4.
         The `negLnLike`, `LnDetPsi`, `mu`, `U`, `SigmaSqr`, and `Lambda` attributes are all set to None.
-        The `gen` attribute is initialized using the `spacefilling` function with arguments `k` and `seed`.
+        The `gen` attribute is initialized using the `SpaceFilling` function with arguments `k` and `seed`.
         The `Psi` attribute is initialized as a zero matrix with shape `(n, n)` and dtype `float64`.
         The `psi` attribute is initialized as a zero matrix with shape `(n, 1)`.
         The `one` attribute is initialized as a list of ones with length `n`.
@@ -780,7 +780,7 @@ def initialize_matrices(self) -> None:
         self.Lambda = None
 
         # Initialize generator
-        self.gen = spacefilling(k=self.k, seed=self.seed)
+        self.gen = SpaceFilling(k=self.k, seed=self.seed)
         logger.debug("In initialize_matrices(): self.gen: %s", self.gen)
 
         # Initialize matrix Psi and vector psi

src/spotpython/data/base.py

@@ -240,9 +240,7 @@ def __repr__(self):
         l_len = max(map(len, self._repr_content.keys()))
         r_len = max(map(len, self._repr_content.values()))
 
-        out = f"{self.desc}\n\n" + "\n".join(
-            k.rjust(l_len) + "  " + v.ljust(r_len) for k, v in self._repr_content.items()
-        )
+        out = f"{self.desc}\n\n" + "\n".join(k.rjust(l_len) + "  " + v.ljust(r_len) for k, v in self._repr_content.items())
 
         if "Parameters\n    ----------" in self.__doc__:
             params = re.split(
@@ -361,11 +359,7 @@ def _get_params(self) -> typing.Dict[str, typing.Any]:
              'n_outputs': 1,
              'sparse': False}
         """
-        return {
-            name: getattr(self, name)
-            for name, param in inspect.signature(self.__init__).parameters.items()  # type: ignore
-            if param.kind != param.VAR_KEYWORD
-        }
+        return {name: getattr(self, name) for name, param in inspect.signature(self.__init__).parameters.items() if param.kind != param.VAR_KEYWORD}  # type: ignore
 
 
 class FileConfig(Config):

src/spotpython/data/california_housing.py

@@ -57,9 +57,7 @@ class CaliforniaHousing(Dataset):
                 print(f"Targets: {targets}")
     """
 
-    def __init__(
-        self, feature_type: torch.dtype = torch.float, target_type: torch.dtype = torch.float, train: bool = True
-    ) -> None:
+    def __init__(self, feature_type: torch.dtype = torch.float, target_type: torch.dtype = torch.float, train: bool = True) -> None:
         super().__init__()
         self.feature_type = feature_type
         self.target_type = target_type

src/spotpython/data/csvdataset.py

@@ -69,21 +69,15 @@ def _load_data(self) -> tuple:
         # Apply OrdinalEncoder to non-numerical feature columns
         if non_numerical_columns:
             if self.oe is None:
-                raise ValueError(
-                    f"\n!!! non_numerical_columns in data: {non_numerical_columns}"
-                    "\nOrdinalEncoder object oe must be provided for encoding non-numerical columns"
-                )
+                raise ValueError(f"\n!!! non_numerical_columns in data: {non_numerical_columns}" "\nOrdinalEncoder object oe must be provided for encoding non-numerical columns")
             feature_df[non_numerical_columns] = self.oe.fit_transform(feature_df[non_numerical_columns])
 
         target_df = df[self.target_column]
 
         # Check if the target column is non-numerical using dtype
         if not pd.api.types.is_numeric_dtype(target_df):
             if self.le is None:
-                raise ValueError(
-                    f"\n!!! The target column '{self.target_column}' is non-numerical"
-                    "\nLabelEncoder object le must be provided for encoding non-numerical target"
-                )
+                raise ValueError(f"\n!!! The target column '{self.target_column}' is non-numerical" "\nLabelEncoder object le must be provided for encoding non-numerical target")
             target_df = self.le.fit_transform(target_df)
 
         # Convert DataFrames to NumPy arrays and then to PyTorch tensors

src/spotpython/data/diabetes.py

@@ -52,9 +52,7 @@ class Diabetes(Dataset):
                 print(f"Targets: {targets}")
     """
 
-    def __init__(
-        self, feature_type: torch.dtype = torch.float, target_type: torch.dtype = torch.float, train: bool = True
-    ) -> None:
+    def __init__(self, feature_type: torch.dtype = torch.float, target_type: torch.dtype = torch.float, train: bool = True) -> None:
         super().__init__()
         self.feature_type = feature_type
         self.target_type = target_type

src/spotpython/data/lightcrossvalidationdatamodule.py

@@ -96,9 +96,7 @@ def setup(self, stage: Optional[str] = None) -> None:
             self.data_train = [(self.scaler.transform(data), target) for data, target in self.data_train]
             data_tensors_train = [data.clone().detach() for data, target in self.data_train]
             target_tensors_train = [target.clone().detach() for data, target in self.data_train]
-            self.data_train = TensorDataset(
-                torch.stack(data_tensors_train).squeeze(1), torch.stack(target_tensors_train)
-            )
+            self.data_train = TensorDataset(torch.stack(data_tensors_train).squeeze(1), torch.stack(target_tensors_train))
             self.data_val = [(self.scaler.transform(data), target) for data, target in self.data_val]
             data_tensors_val = [data.clone().detach() for data, target in self.data_val]
             target_tensors_val = [target.clone().detach() for data, target in self.data_val]

src/spotpython/data/lightdatamodule.py

@@ -160,9 +160,7 @@ def setup(self, stage: Optional[str] = None) -> None:
             if self.verbosity > 0:
                 print(f"train_size: {train_size}, val_size: {val_size} used for train & val data.")
             generator_fit = torch.Generator().manual_seed(self.test_seed)
-            self.data_train, self.data_val, _ = random_split(
-                self.data_full, [train_size, val_size, test_size], generator=generator_fit
-            )
+            self.data_train, self.data_val, _ = random_split(self.data_full, [train_size, val_size, test_size], generator=generator_fit)
             if self.scaler is not None:
                 # Fit the scaler on training data
                 scaler_train_data = torch.stack([self.data_train[i][0] for i in range(len(self.data_train))]).squeeze(1)
@@ -189,9 +187,7 @@ def setup(self, stage: Optional[str] = None) -> None:
             if self.verbosity > 0:
                 print(f"test_size: {test_size} used for predict dataset.")
             generator_predict = torch.Generator().manual_seed(self.test_seed)
-            self.data_predict, _ = random_split(
-                self.data_full, [test_size, full_train_size], generator=generator_predict
-            )
+            self.data_predict, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_predict)
             if self.scaler is not None:
                 # Transform the predict data
                 self.data_predict = self.transform_dataset(self.data_predict)

src/spotpython/design/designs.py

@@ -2,40 +2,41 @@
 from typing import List
 
 
-class designs:
+class Designs:
     """
-    Super class for all design classes (factorial and spacefilling).
+    Super class for all design classes (factorial and space-filling).
 
     Attributes:
-        designs (List):
-            A list of designs.
-        k (int):
-            The dimension of the design.
-        seed (int):
-            The seed for the random number generator.
-        rng (Generator):
-            A random number generator instance.
+        designs (List): A list of design instances.
+        k (int): The dimension of the design.
+        seed (int): The seed for the random number generator.
+        rng (Generator): A random number generator instance.
     """
 
-    def __init__(self, k: int = 2, seed: int = 123) -> None:
+    def __init__(self, k: int, seed: int = 123) -> None:
         """
         Initializes a Designs object with the given dimension and seed.
 
         Args:
-            k (int):
-                The dimension of the design. Defaults to 2.
-            seed (int):
-                The seed for the random number generator. Defaults to 123.
+            k (int): The dimension of the design.
+            seed (int): The seed for the random number generator. Defaults to 123.
+
+        Raises:
+            ValueError: If 'k' is not an integer.
+
         Examples:
-            >>> designs = designs(k=2, seed=123)
+            >>> from spotpython.design.designs import Designs
+            >>> designs = Designs(k=2, seed=123)
             >>> designs.get_dim()
             2
-
         """
-        self.designs: List = []
+        if not isinstance(k, int):
+            raise ValueError("The dimension of the design must be an integer.")
+
         self.k: int = k
         self.seed: int = seed
         self.rng = default_rng(self.seed)
+        self.designs: List = []
 
     def get_dim(self) -> int:
         """