Remvoed an error

autoqild/bayes_search/bayes_search_cv.py

@@ -98,18 +98,7 @@ class BayesSearchCV(BayesSearchCVSK):
         configurations based on the Bayesian optimization strategy.
     """
 
-    def __init__(
-        self,
-        estimator,
-        search_spaces,
-        optimizer_kwargs=None,
-        n_iter=50,
-        scoring=None,
-        fit_params=None,
-        n_jobs=1,
-        n_points=1,
-        iid=True,
-        refit=True,
+    def __init__(self, estimator, search_spaces, optimizer_kwargs=None, n_iter=50, scoring=None, fit_params=None, n_jobs=1, n_points=1, iid=True, refit=True,
         cv=None,
         verbose=0,
         pre_dispatch="2*n_jobs",

autoqild/dataset_readers/open_ml_padding_dr.py

@@ -7,7 +7,7 @@
 
 from .open_ml_timming_dr import OpenMLTimingDatasetReader
 from .utils import *
-
+import pandas as pd
 
 class OpenMLPaddingDatasetReader(OpenMLTimingDatasetReader):
     """Reader for OpenML datasets related to leakages with respect to the error
@@ -118,6 +118,8 @@ def __read_dataset__(self):
         vulnerable_classes_str = description.split("\n")[-1].split("vulnerable_classes ")[-1]
         vulnerable_classes_str = vulnerable_classes_str.strip("[]")
         self.vulnerable_classes = [s.strip() for s in vulnerable_classes_str.split(",")]
+        if self.vulnerable_classes == ['']:
+            self.vulnerable_classes = []
         self.n_features = len(self.dataset.features) - 1
         self.server = self.dataset.name.split("padding-attack-dataset-")[-1]
 
@@ -143,7 +145,7 @@ def get_data(self, class_label=1):
         y : array-like of shape (n_samples,)
             Target vector.
         """
-        super().get_data(class_label=class_label)
+        return super().get_data(class_label=class_label)
 
     def get_sampled_imbalanced_data(self, X, y):
         """Creates an imbalanced dataset by sampling from the data.
@@ -164,4 +166,4 @@ def get_sampled_imbalanced_data(self, X, y):
         y : array-like of shape (n_samples,)
             Target vector after applying sampling to create imbalance.
         """
-        super().get_sampled_imbalanced_data(X=X, y=y)
+        return super().get_sampled_imbalanced_data(X=X, y=y)

autoqild/dataset_readers/utils.py

@@ -5,14 +5,7 @@
 
 import numpy as np
 
-__all__ = [
-    "GEN_TYPES",
-    "FACTOR",
-    "LABEL_COL",
-    "generate_samples_per_class",
-    "clean_class_label",
-    "pdf",
-]
+__all__ = ["GEN_TYPES", "FACTOR", "LABEL_COL", "generate_samples_per_class", "clean_class_label", "pdf"]
 
 GEN_TYPES = ["single", "multiple"]
 """
@@ -29,9 +22,7 @@
 """Default label column name used in datasets."""
 
 
-def generate_samples_per_class(
-    n_classes, samples=1000, imbalance=0.05, gen_type="single", logger=None, verbose=1
-):
+def generate_samples_per_class(n_classes, samples=1000, imbalance=0.05, gen_type="single", logger=None, verbose=1):
     """Generate the number of samples per class with a specified imbalance.
 
     This function calculates the number of samples for each class based on the provided imbalance ratio and the generation type.

autoqild/utilities/statistical_tests.py

@@ -39,15 +39,7 @@ def wilcoxon_signed_rank_test(accuracies, accuracies2, alternative="two-sided",
     return p_value
 
 
-def paired_ttest(
-    x1,
-    x2,
-    n_training_folds,
-    n_test_folds,
-    correction=True,
-    alternative="two-sided",
-    verbose=False,
-):
+def paired_ttest(x1, x2, n_training_folds, n_test_folds, correction=True, alternative="two-sided", verbose=False,):
     """Performs a paired t-test on two sets of values with and without
     correction.
 
@@ -110,22 +102,9 @@ def paired_ttest(
     elif alternative == "two-sided":
         p_value = 2 * t.sf(np.abs(t_static), df)
     if verbose:
-        logger.info(
-            "Final Variance {} Sigma {} t_static {} p {}".format(
-                sigma2, np.sqrt(sigma2), t_static, p_value
-            )
-        )
-        logger.info(
-            "np.isnan(p) {}, np.isinf {},  d_bar == 0 {}, sigma2_mod == 0 {}, np.isinf(t_static) {}, "
-            "np.isnan(t_static) {}".format(
-                np.isnan(p_value),
-                np.isinf(p_value),
-                d_bar == 0,
-                sigma2 == 0,
-                np.isinf(t_static),
-                np.isnan(t_static),
-            )
-        )
+        logger.info(f"Final Variance {sigma2} Sigma {np.sqrt(sigma2)} t_static {t_static} p {p_value}")
+        logger.info(f"np.isnan(p) {np.isnan(p_value)}, np.isinf {np.isinf(p_value)},  d_bar == 0 {d_bar == 0}, sigma2_mod == 0 {sigma2 == 0}, np.isinf(t_static) {np.isinf(t_static)}, "
+                    f"np.isnan(t_static) {np.isnan(t_static)}")
     if (
         np.isnan(p_value)
         or np.isinf(p_value)