v0.6.3

documentation

Author: bartzbeielstein

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotPython"
-version = "0.6.2"
+version = "0.6.3"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotPython/data/base.py

@@ -271,7 +271,7 @@ class SyntheticDataset(Dataset):
         sparse (bool): Whether the dataset is sparse or not.
 
     Returns:
-        SyntheticDataset: A synthetic dataset object.
+        (SyntheticDataset): A synthetic dataset object.
 
     Examples:
         >>> from sklearn.datasets import make_classification
@@ -379,7 +379,7 @@ class FileConfig(Config):
         desc (dict): Extra config parameters to pass as keyword arguments.
 
     Returns:
-        FileConfig: A FileConfig object.
+        (FileConfig): A FileConfig object.
 
     Examples:
         >>> config = FileConfig(filename="config.json", directory="/path/to/directory")
@@ -436,7 +436,7 @@ class FileDataset(Dataset):
         desc (dict): Extra dataset parameters to pass as keyword arguments.
 
     Returns:
-        FileDataset: A FileDataset object.
+        (FileDataset): A FileDataset object.
 
     Examples:
         >>> dataset = FileDataset(filename="dataset.csv", directory="/path/to/directory")
@@ -494,7 +494,7 @@ class RemoteDataset(FileDataset):
         unpack (bool): Whether to unpack the download or not. Defaults to True.
         filename (str):
             An optional name to given to the file if the file is unpacked. Defaults to None.
-        desc: Extra dataset parameters to pass as keyword arguments.
+        desc (dict): Extra dataset parameters to pass as keyword arguments.
 
     Examples:
 
@@ -507,7 +507,7 @@ class RemoteDataset(FileDataset):
 
     """
 
-    def __init__(self, url: str, size: int, unpack: bool = True, filename: str = None, **desc):
+    def __init__(self, url: str, size: int, unpack: bool = True, filename: str = None, **desc: dict):
         if filename is None:
             filename = path.basename(url)
 
@@ -621,7 +621,8 @@ class GenericFileDataset(Dataset):
         parse_dates (list): A list of columns to parse as dates. Defaults to None.
         directory (str):
             The directory where the file is contained. Defaults to the location of the `datasets` module.
-        desc: Extra dataset parameters to pass as keyword arguments.
+        desc (dict): Extra dataset parameters to pass as keyword arguments.
+
 
     Examples:
 
@@ -630,7 +631,11 @@ class GenericFileDataset(Dataset):
         >>> for x, y in dataset:
         ...     print(x, y)
         ...     break
-        ({'sepal_length': 5.1, 'sepal_width': 3.5, 'petal_length': 1.4, 'petal_width': 0.2}, 'setosa')
+        ({'sepal_length': 5.1,
+          'sepal_width': 3.5,
+          'petal_length': 1.4,
+          'petal_width': 0.2},
+          'setosa')
 
     """
 
@@ -641,7 +646,7 @@ def __init__(
         converters: dict = None,
         parse_dates: list = None,
         directory: str = None,
-        **desc,
+        **desc: dict,
     ):
         super().__init__(**desc)
         self.filename = filename

src/spotPython/data/light_hyper_dict.py

@@ -1,16 +1,39 @@
 import json
-from . import base
+from spotPython.data import base
 
 
 class LightHyperDict(base.FileConfig):
-    """Lightning hyperparameter dictionary."""
+    """Lightning hyperparameter dictionary.
+
+    This class extends the FileConfig class to provide a dictionary for storing hyperparameters.
+
+    Attributes:
+        filename (str):
+            The name of the file where the hyperparameters are stored.
+    """
 
     def __init__(self):
+        """Initialize the LightHyperDict object.
+
+        Examples:
+            >>> lhd = LightHyperDict()
+        """
         super().__init__(
             filename="light_hyper_dict.json",
         )
 
-    def load(self):
+    def load(self) -> dict:
+        """Load the hyperparameters from the file.
+
+        Returns:
+            dict: A dictionary containing the hyperparameters.
+
+        Examples:
+            >>> lhd = LightHyperDict()
+            >>> hyperparams = lhd.load()
+            >>> print(hyperparams)
+            {'learning_rate': 0.001, 'batch_size': 32, 'epochs': 10}
+        """
         with open(self.path, "r") as f:
             d = json.load(f)
         return d

src/spotPython/data/sklearn_hyper_dict.py

@@ -1,16 +1,49 @@
 import json
-from . import base
+from spotPython.data import base
 
 
 class SklearnHyperDict(base.FileConfig):
-    """River hyperparameter dictionary."""
+    """Scikit-learn hyperparameter dictionary.
+
+    This class extends the FileConfig class to provide a dictionary for storing hyperparameters.
+
+    Attributes:
+        filename (str): The name of the file where the hyperparameters are stored.
+    """
 
     def __init__(self):
+        """Initialize the SklearnHyperDict object.
+
+        Examples:
+            >>> shd = SklearnHyperDict()
+        """
         super().__init__(
             filename="sklearn_hyper_dict.json",
         )
 
-    def load(self):
+    def load(self) -> dict:
+        """Load the hyperparameters from the file.
+
+        Returns:
+            (dict): A dictionary containing the hyperparameters.
+        Examples:
+            >>> shd = SklearnHyperDict()
+            >>> hyperparams = shd.load()
+            >>> print(hyperparams)
+            {'learning_rate': 0.001, 'batch_size': 32, 'epochs': 10}
+        """
         with open(self.path, "r") as f:
             d = json.load(f)
         return d
+
+
+# Example usage
+if __name__ == "__main__":
+    # Create a SklearnHyperDict object
+    shd = SklearnHyperDict()
+
+    # Load the hyperparameters from the file
+    hyperparams = shd.load()
+
+    # Print the hyperparameters
+    print(hyperparams)

src/spotPython/data/torch_hyper_dict.py

@@ -1,16 +1,48 @@
 import json
-from . import base
+from spotPython.data import base
 
 
 class TorchHyperDict(base.FileConfig):
-    """Torch hyperparameter dictionary."""
+    """PyTorch hyperparameter dictionary.
+
+    This class extends the FileConfig class to provide a dictionary for storing hyperparameters.
+
+    Attributes:
+        filename (str): The name of the file where the hyperparameters are stored.
+    """
 
     def __init__(self):
+        """Initialize the TorchHyperDict object.
+        Examples:
+            >>> thd = TorchHyperDict()
+        """
         super().__init__(
             filename="torch_hyper_dict.json",
         )
 
-    def load(self):
+    def load(self) -> dict:
+        """Load the hyperparameters from the file.
+
+        Returns:
+            (dict): A dictionary containing the hyperparameters.
+        Examples:
+            >>> thd = TorchHyperDict()
+            >>> hyperparams = thd.load()
+            >>> print(hyperparams)
+            {'learning_rate': 0.001, 'batch_size': 32, 'epochs': 10}
+        """
         with open(self.path, "r") as f:
             d = json.load(f)
         return d
+
+
+# Example usage
+if __name__ == "__main__":
+    # Create a TorchHyperDict object
+    thd = TorchHyperDict()
+
+    # Load the hyperparameters from the file
+    hyperparams = thd.load()
+
+    # Print the hyperparameters
+    print(hyperparams)

src/spotPython/data/torchdata.py

@@ -1,12 +1,42 @@
 from torchvision import datasets
 import torchvision.transforms as transforms
+from typing import Tuple
 
 
-def load_data_cifar10(data_dir="./data"):
+def load_data_cifar10(data_dir: str = "./data") -> Tuple[datasets.CIFAR10, datasets.CIFAR10]:
+    """Load the CIFAR-10 dataset.
+        This function loads the CIFAR-10 dataset using the torchvision library.
+        The data is split into a training set and a test set.
+
+    Args:
+        data_dir (str):
+            The directory where the data is stored. Defaults to "./data".
+
+    Returns:
+        Tuple[datasets.CIFAR10, datasets.CIFAR10]:
+            A tuple containing the training set and the test set.
+    Examples:
+        >>> trainset, testset = load_data_cifar10()
+        >>> print(f"Training set size: {len(trainset)}")
+        Training set size: 50000
+        >>> print(f"Test set size: {len(testset)}")
+        Test set size: 10000
+
+    """
     transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
 
     trainset = datasets.CIFAR10(root=data_dir, train=True, download=True, transform=transform)
 
     testset = datasets.CIFAR10(root=data_dir, train=False, download=True, transform=transform)
 
     return trainset, testset
+
+
+# Example usage
+if __name__ == "__main__":
+    # Load the CIFAR-10 dataset
+    trainset, testset = load_data_cifar10()
+
+    # Print the size of the training set and the test set
+    print(f"Training set size: {len(trainset)}")
+    print(f"Test set size: {len(testset)}")

src/spotPython/data/vbdp.py

@@ -1,13 +1,23 @@
 # Purpose: Functions for the VBDP project
 
 
-def cluster_features(X):
-    """Clusters the features of a dataframe based on similarity
+import pandas as pd
+from sklearn.cluster import AffinityPropagation
+from sklearn.metrics.pairwise import manhattan_distances
+
+
+def cluster_features(X: pd.DataFrame) -> pd.DataFrame:
+    """Clusters the features of a dataframe based on similarity.
+
+    This function takes a dataframe with features and clusters them based on similarity.
+    The resulting dataframe contains the original features as well as new features representing the clusters.
 
     Args:
-        X (pd.DataFrame): dataframe with features
+        X (pd.DataFrame): A dataframe with features.
+
     Returns:
-        X (pd.DataFrame): dataframe with new features
+        (pd.DataFrame): A dataframe with the original features and new cluster features.
+
     Examples:
         >>> df = pd.DataFrame({"a": [True, False, True], "b": [True, True, False], "c": [False, False, True]})
         >>> df
@@ -16,10 +26,10 @@ def cluster_features(X):
         1 False   True  False
         2  True  False   True
         >>> cluster_features(df)
-            a      b      c  cluster
-        0  True   True  False       0
-        1 False   True  False       1
-        2  True  False   True        2
+            a      b      c  c_0  c_1  c_2  c_3
+        0  True   True  False    0    0    0    0
+        1 False   True  False    0    0    0    0
+        2  True  False   True    0    0    0    0
     """
     c_0 = X.columns[X.columns.str.contains("pain")]
     c_1 = X.columns[X.columns.str.contains("inflammation")]
@@ -32,13 +42,21 @@ def cluster_features(X):
     return X
 
 
-def affinity_propagation_features(X):
-    """Clusters the features of a dataframe using Affinity Propagation
+def affinity_propagation_features(X: pd.DataFrame) -> pd.DataFrame:
+    """Clusters the features of a dataframe using Affinity Propagation.
+
+    This function takes a dataframe with features and clusters them using the
+    Affinity Propagation algorithm. The resulting dataframe contains the original
+    features as well as a new feature representing the cluster labels.
 
     Args:
-        X (pd.DataFrame): dataframe with features
+        X (pd.DataFrame):
+            A dataframe with features.
+
     Returns:
-        X (pd.DataFrame): dataframe with new features
+        (pd.DataFrame):
+            A dataframe with the original features and a new cluster feature.
+
     Examples:
         >>> df = pd.DataFrame({"a": [True, False, True], "b": [True, True, False], "c": [False, False, True]})
         >>> df
@@ -47,14 +65,12 @@ def affinity_propagation_features(X):
         1  False  True   False
         2  True   False  True
         >>> affinity_propagation_features(df)
+        Estimated number of clusters: 3
             a      b      c  cluster
         0  True   True   False       0
         1  False  True   False       1
         2  True   False  True        2
     """
-    from sklearn.cluster import AffinityPropagation
-    from sklearn.metrics.pairwise import manhattan_distances
-
     D = manhattan_distances(X)
     af = AffinityPropagation(random_state=0, affinity="precomputed").fit(D)
     cluster_centers_indices = af.cluster_centers_indices_