0.14.57

Improved plots for oml-book

Author: bartzbeielstein

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotpython"
-version = "0.14.56"
+version = "0.14.57"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotPython/plot/ts.py

@@ -0,0 +1,56 @@
+from spotPython.data.friedman import FriedmanDriftDataset
+import matplotlib.pyplot as plt
+
+
+def plot_friedman_drift_data(
+    n_samples, seed, change_point1, change_point2, constant=True, show=True, filename=None
+) -> None:
+    """Plot the Friedman dataset with drifts at change_point1 and change_point2.
+
+    Args:
+        n_samples (int):
+            Number of samples to generate.
+        seed (int):
+            Seed for the random number generator.
+        change_point1 (int):
+            Index of the first drift point.
+        change_point2 (int):
+            Index of the second drift point.
+        constant (bool, optional):
+            If True, the drifts are constant. Defaults to True.
+        filename (str, optional):
+            Name of the file to save the plot. Defaults to None.
+
+    Returns:
+        None
+
+    Examples:
+        >>> from spotPython.plot.ts import plot_friedman_drift_data
+        >>> plot_friedman_drift_data(n_samples=100, seed=42, change_point1=50, change_point2=75, constant=False)
+        >>> plot_friedman_drift_data(n_samples=100, seed=42, change_point1=50, change_point2=75, constant=True)
+    """
+    data_generator = FriedmanDriftDataset(
+        n_samples=n_samples, seed=seed, change_point1=change_point1, change_point2=change_point2, constant=constant
+    )
+    data = [data for data in data_generator]
+    indices = [i for _, _, i in data]
+    values = {f"x{i}": [] for i in range(5)}
+    values["y"] = []
+    for x, y, _ in data:
+        for i in range(5):
+            values[f"x{i}"].append(x[i])
+        values["y"].append(y)
+
+    plt.figure(figsize=(10, 6))
+    for label, series in values.items():
+        plt.plot(indices, series, label=label)
+    plt.xlabel("Index")
+    plt.ylabel("Value")
+    plt.axvline(x=change_point1, color="k", linestyle="--", label="Drift Point 1")
+    plt.axvline(x=change_point2, color="r", linestyle="--", label="Drift Point 2")
+    plt.legend()
+    plt.grid(True)
+    if filename is not None:
+        plt.savefig(filename)
+    if show:
+        plt.show()

src/spotPython/plot/validation.py

@@ -239,14 +239,20 @@ def plot_confusion_matrix(
         plt.show()
 
 
-def plot_actual_vs_predicted(y_test, y_pred, title=None, show=True) -> None:
+def plot_actual_vs_predicted(y_test, y_pred, title=None, show=True, filename=None) -> None:
     """Plot actual vs. predicted values.
 
     Args:
-        y_test (np.ndarray): True values.
-        y_pred (np.ndarray): Predicted values.
-        title (str, optional): Title of the plot. Defaults to None.
-        show (bool, optional): If True, the plot is shown. Defaults to True.
+        y_test (np.ndarray):
+            True values.
+        y_pred (np.ndarray):
+            Predicted values.
+        title (str, optional):
+            Title of the plot. Defaults to None.
+        show (bool, optional):
+            If True, the plot is shown. Defaults to True.
+        filename (str, optional):
+            Name of the file to save the plot. Defaults to None.
 
     Returns:
         (NoneType): None
@@ -284,5 +290,7 @@ def plot_actual_vs_predicted(y_test, y_pred, title=None, show=True) -> None:
     if title is not None:
         fig.suptitle(title)
     plt.tight_layout()
+    if filename is not None:
+        plt.savefig(filename)
     if show:
         plt.show()

src/spotPython/plot/xy.py

@@ -22,7 +22,7 @@ def plot_y_vs_X(X, y, nrows=5, ncols=2, figsize=(30, 20), ylabel="y", feature_na
         feature_names (list of str, optional):
             List of feature names. Defaults to None. If None, generates feature names as x0, x1, etc.
 
-    Example:
+    Examples:
         >>> from sklearn.datasets import load_diabetes
         >>> from spotPython.plot.xy import plot_y_vs_X
         >>> data = load_diabetes()