From ae89ac4f1b6e1367f69604324e6d144c3729a125 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 12:31:15 +0100
Subject: [PATCH 01/20] - Use x-feature-map - Change predict to use
 predict_proba instead for QSVM

---
 pyriemann_qiskit/classification.py | 16 ++++++++++------
 pyriemann_qiskit/pipelines.py      | 18 +++++++-----------
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 56d9ff8c..187455f3 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -5,6 +5,7 @@
 quantum computer.
 """
 from datetime import datetime
+from scipy.special import softmax
 import logging
 import numpy as np
 
@@ -256,6 +257,7 @@ class QuanticSVM(QuanticClassifierBase):
         Fix: copy estimator not keeping base class parameters.
     .. versionchanged:: 0.2.0
         Add seed parameter
+        Predict is now using predict_proba with a softmax.
 
     Parameters
     ----------
@@ -360,6 +362,7 @@ def _init_algo(self, n_features):
                     gamma=self.gamma,
                     C=self.C,
                     max_iter=max_iter,
+                    probability=True
                 )
         else:
             max_iter = -1 if self.max_iter is None else self.max_iter
@@ -386,11 +389,10 @@ def predict_proba(self, X):
             prob[n, 0] == True if the nth sample is assigned to 1st class;
             prob[n, 1] == True if the nth sample is assigned to 2nd class.
         """
-        predicted_labels = self.predict(X)
-        ret = [
-            np.array([c == self.classes_[0], c == self.classes_[1]])
-            for c in predicted_labels
-        ]
+
+        proba = self._classifier.predict_proba(X)
+        ret = softmax(proba, axis=0)
+
         return np.array(ret)
 
     def predict(self, X):
@@ -407,7 +409,9 @@ def predict(self, X):
         pred : array, shape (n_samples,)
             Class labels for samples in X.
         """
-        labels = self._predict(X)
+        probs = self.predict_proba(X)
+        labels = [1 if prob[0] < prob[1] else 0 for prob in probs]
+        self._log("Prediction finished.")
         return self._map_indices_to_classes(labels)
 
 
diff --git a/pyriemann_qiskit/pipelines.py b/pyriemann_qiskit/pipelines.py
index 85bb6eb5..b6db7f4a 100644
--- a/pyriemann_qiskit/pipelines.py
+++ b/pyriemann_qiskit/pipelines.py
@@ -10,6 +10,7 @@
 from pyriemann_qiskit.utils.filtering import NoDimRed
 from pyriemann_qiskit.utils.hyper_params_factory import (
     gen_zz_feature_map,
+    gen_x_feature_map,
     gen_two_local,
     get_spsa,
 )
@@ -175,12 +176,6 @@ class QuantumClassifierWithDefaultRiemannianPipeline(BasePipeline):
     shots : int | None (default: 1024)
         Number of repetitions of each circuit, for sampling.
         If None, classical computation will be performed.
-    feature_entanglement : str | list[list[list[int]]] | \
-                   Callable[int, list[list[list[int]]]]
-        Specifies the entanglement structure for the ZZFeatureMap.
-        Entanglement structure can be provided with indices or string.
-        Possible string values are: 'full', 'linear', 'circular' and 'sca'.
-        See [2]_ for more details on entanglement structure.
     feature_reps : int (default: 2)
         The number of repeated circuits for the ZZFeatureMap,
         greater or equal to 1.
@@ -206,12 +201,15 @@ class QuantumClassifierWithDefaultRiemannianPipeline(BasePipeline):
     Notes
     -----
     .. versionadded:: 0.0.1
+    .. versionchanged:: 0.2.0
+        Change feature map from ZZFeatureMap to XFeatureMap.
+        Therefore remove unused parameter `feature_entanglement`.
 
     See Also
     --------
     XdawnCovariances
     TangentSpace
-    gen_zz_feature_map
+    gen_x_feature_map
     gen_two_local
     get_spsa
     QuanticVQC
@@ -236,7 +234,6 @@ def __init__(
         C=1.0,
         max_iter=None,
         shots=1024,
-        feature_entanglement="full",
         feature_reps=2,
         spsa_trials=None,
         two_local_reps=None,
@@ -248,7 +245,6 @@ def __init__(
         self.C = C
         self.max_iter = max_iter
         self.shots = shots
-        self.feature_entanglement = feature_entanglement
         self.feature_reps = feature_reps
         self.spsa_trials = spsa_trials
         self.two_local_reps = two_local_reps
@@ -261,7 +257,7 @@ def _create_pipe(self):
         is_vqc = self.spsa_trials and self.two_local_reps
         is_quantum = self.shots is not None
 
-        feature_map = gen_zz_feature_map(self.feature_reps, self.feature_entanglement)
+        feature_map = gen_x_feature_map(self.feature_reps)
 
         if is_vqc:
             self._log("QuanticVQC chosen.")
@@ -320,7 +316,7 @@ class QuantumMDMWithRiemannianPipeline(BasePipeline):
     shots : int (default:1024)
         Number of repetitions of each circuit, for sampling.
     gen_feature_map : Callable[int, QuantumCircuit | FeatureMap] \
-                      (default : Callable[int, ZZFeatureMap])
+                      (default : Callable[int, XFeatureMap])
         Function generating a feature map to encode data into a quantum state.
 
     Attributes

From 5382e1f208b10bb22881bda0e62b60daf914aad8 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 12:48:35 +0100
Subject: [PATCH 02/20] - test for predict proba - add multiclass FVT for QSVM

---
 tests/conftest.py            |  1 +
 tests/test_classification.py | 28 +++++++++++++++++++++-------
 2 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 45d4a28f..8b439e8d 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -179,6 +179,7 @@ class BinaryFVT(BinaryTest):
     def additional_steps(self):
         self.quantum_instance.fit(self.samples, self.labels)
         self.prediction = self.quantum_instance.predict(self.samples)
+        self.predict_proab = self.quantum_instance.predict_proba(self.samples)
         print(self.labels, self.prediction)
 
 
diff --git a/tests/test_classification.py b/tests/test_classification.py
index c93c4dad..4c1dbed0 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -114,13 +114,15 @@ def get_params(self):
         }
 
     def check(self):
-        assert (
-            self.prediction[: self.class_len].all() == self.quantum_instance.classes_[0]
-        )
-        assert (
-            self.prediction[self.class_len :].all() == self.quantum_instance.classes_[1]
-        )
-
+        # Check that all classes are predicted
+        assert len(self.prediction) == len(self.labels)
+        # Check the proba for each classes are returned
+        assert self.predict_proab.shape[1] == len(self.labels)
+        for i in len(self.quantum_instance.classes_):
+            assert (
+                self.prediction[self.class_len * i : self.class_len * (i + 1)].all() == \
+                    self.quantum_instance.classes_[i]
+            )
 
 class TestQuanticSVM(TestClassicalSVM):
     """Tests the Quantum version of Quantic SVM.
@@ -140,6 +142,16 @@ def get_params(self):
             "type": "bin",
         }
 
+class TestQuanticSVM_MultiClass(MultiClassFVT):
+    """Perform SVM on a simulated quantum computer
+    (multi-label classification)"""
+
+    def get_params(self):
+        # multi-inheritance pattern
+        return TestQuanticSVM.get_params(self)
+
+    def check(self):
+        TestQuanticSVM.check(self)
 
 class TestQuanticPegasosSVM(TestClassicalSVM):
     """Same as TestQuanticSVM, except it uses
@@ -176,6 +188,8 @@ def check(self):
         assert len(self.prediction) == len(self.labels)
         # Check the number of classes is consistent
         assert len(np.unique(self.prediction)) == len(np.unique(self.labels))
+        # Check the proba for each classes are returned
+        assert self.predict_proab.shape[1] == len(self.labels)
 
 
 class TestQuanticVQC_MultiClass(MultiClassFVT):

From 9941d7c14d04c811903051268c74f1b53f110126 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 13:51:35 +0100
Subject: [PATCH 03/20] - fix predict_proba for multiclass - use predict_proba
 inside for qsvm predictions - add multiclass test for MDM

---
 pyriemann_qiskit/classification.py | 100 ++++++++++++++++-------------
 tests/test_classification.py       |  30 +++++----
 2 files changed, 73 insertions(+), 57 deletions(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 187455f3..872f8267 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -237,6 +237,40 @@ def _predict(self, X):
         result = self._classifier.predict(X)
         self._log("Prediction finished.")
         return result
+    
+    def predict_proba(self, X):
+        """Return the probabilities associated with predictions.
+
+        The default behavior is to return the nested classifier probabilities.
+        In case where no `predict_proba` method is available inside the classifier,
+        the method the predicted label number (0 or 1 for examples) and applies a
+        softmax in top of it.
+
+        Parameters
+        ----------
+        X : ndarray, shape (n_samples, n_features)
+            Input vector, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        Returns
+        -------
+        prob : ndarray, shape (n_samples, n_classes)
+            prob[n, i] == 1 if the nth sample is assigned to class `i`;
+        """
+
+        if(not hasattr(self._classifier, "predict_proba")):
+            # Classifier has no predict_proba
+            # Use the result from predict and apply a softmax
+            proba = self._classifier.predict(X)
+            proba = [
+                np.array([1 if c == self.classes_[i] else 0 for i in range(len(self.classes_))])
+                for c in proba
+            ]
+            proba = softmax(proba, axis=0)
+        else:
+            proba = self._classifier.predict_proba(X)
+
+        return np.array(proba)
 
 
 class QuanticSVM(QuanticClassifierBase):
@@ -257,7 +291,8 @@ class QuanticSVM(QuanticClassifierBase):
         Fix: copy estimator not keeping base class parameters.
     .. versionchanged:: 0.2.0
         Add seed parameter
-        Predict is now using predict_proba with a softmax.
+        SVC and QSVC now compute probability (may impact time performance)
+        Predict is now using predict_proba with a softmax, when using QSVC.
 
     Parameters
     ----------
@@ -353,7 +388,9 @@ def _init_algo(self, n_features):
                 self._log("[Warning] `gamma` is not supported by PegasosQSVC")
                 num_steps = 1000 if self.max_iter is None else self.max_iter
                 classifier = PegasosQSVC(
-                    quantum_kernel=quantum_kernel, C=self.C, num_steps=num_steps
+                    quantum_kernel=quantum_kernel,
+                    C=self.C,
+                    num_steps=num_steps
                 )
             else:
                 max_iter = -1 if self.max_iter is None else self.max_iter
@@ -366,7 +403,12 @@ def _init_algo(self, n_features):
                 )
         else:
             max_iter = -1 if self.max_iter is None else self.max_iter
-            classifier = SVC(gamma=self.gamma, C=self.C, max_iter=max_iter)
+            classifier = SVC(
+                    gamma=self.gamma,
+                    C=self.C,
+                    max_iter=max_iter,
+                    probability=True
+                )
         return classifier
 
     def predict_proba(self, X):
@@ -386,14 +428,15 @@ def predict_proba(self, X):
         Returns
         -------
         prob : ndarray, shape (n_samples, n_classes)
-            prob[n, 0] == True if the nth sample is assigned to 1st class;
-            prob[n, 1] == True if the nth sample is assigned to 2nd class.
+            prob[n, i] == 1 if the nth sample is assigned to class `i`;
         """
 
-        proba = self._classifier.predict_proba(X)
-        ret = softmax(proba, axis=0)
+        proba = super().predict_proba(X)
+        if(isinstance(self._classifier, QSVC)):
+            # apply additional softmax 
+            proba = softmax(proba)
 
-        return np.array(ret)
+        return np.array(proba)
 
     def predict(self, X):
         """Calculates the predictions.
@@ -409,8 +452,11 @@ def predict(self, X):
         pred : array, shape (n_samples,)
             Class labels for samples in X.
         """
-        probs = self.predict_proba(X)
-        labels = [1 if prob[0] < prob[1] else 0 for prob in probs]
+        if(isinstance(self._classifier, QSVC)):
+            probs = self.predict_proba(X)
+            labels = [1 if prob[0] < prob[1] else 0 for prob in probs]
+        else:
+            labels = self._predict(X)
         self._log("Prediction finished.")
         return self._map_indices_to_classes(labels)
 
@@ -518,24 +564,6 @@ def _init_algo(self, n_features):
         )
         return vqc
 
-    def predict_proba(self, X):
-        """Returns the probabilities associated with predictions.
-
-        Parameters
-        ----------
-        X : ndarray, shape (n_samples, n_features)
-            Input vector, where `n_samples` is the number of samples and
-            `n_features` is the number of features.
-
-        Returns
-        -------
-        prob : ndarray, shape (n_samples, n_classes)
-            prob[n, 0] == True if the nth sample is assigned to 1st class;
-            prob[n, 1] == True if the nth sample is assigned to 2nd class.
-        """
-        proba, _ = self._predict(X)
-        return proba
-
     def predict(self, X):
         """Calculates the predictions.
 
@@ -668,22 +696,6 @@ def _init_algo(self, n_features):
         set_global_optimizer(self._optimizer)
         return classifier
 
-    def predict_proba(self, X):
-        """Return the probabilities associated with predictions.
-
-        Parameters
-        ----------
-        X : ndarray, shape (n_trials, n_channels, n_channels)
-            ndarray of trials.
-
-        Returns
-        -------
-        prob : ndarray, shape (n_samples, n_classes)
-            prob[n, 0] == True if the nth sample is assigned to 1st class;
-            prob[n, 1] == True if the nth sample is assigned to 2nd class.
-        """
-        return self._classifier.predict_proba(X)
-
     def predict(self, X):
         """Calculates the predictions.
 
diff --git a/tests/test_classification.py b/tests/test_classification.py
index 4c1dbed0..94b0032e 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -117,12 +117,7 @@ def check(self):
         # Check that all classes are predicted
         assert len(self.prediction) == len(self.labels)
         # Check the proba for each classes are returned
-        assert self.predict_proab.shape[1] == len(self.labels)
-        for i in len(self.quantum_instance.classes_):
-            assert (
-                self.prediction[self.class_len * i : self.class_len * (i + 1)].all() == \
-                    self.quantum_instance.classes_[i]
-            )
+        assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 class TestQuanticSVM(TestClassicalSVM):
     """Tests the Quantum version of Quantic SVM.
@@ -189,7 +184,7 @@ def check(self):
         # Check the number of classes is consistent
         assert len(np.unique(self.prediction)) == len(np.unique(self.labels))
         # Check the proba for each classes are returned
-        assert self.predict_proab.shape[1] == len(self.labels)
+        assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 
 class TestQuanticVQC_MultiClass(MultiClassFVT):
@@ -221,9 +216,18 @@ def get_params(self):
         }
 
     def check(self):
-        assert (
-            self.prediction[: self.class_len].all() == self.quantum_instance.classes_[0]
-        )
-        assert (
-            self.prediction[self.class_len :].all() == self.quantum_instance.classes_[1]
-        )
+        for i in range(len(self.quantum_instance.classes_)):
+            assert (
+                np.all(self.prediction[self.class_len * i : self.class_len * (i + 1)]) == self.quantum_instance.classes_[i]
+            )
+
+class TestQuanticMDM_MultiClass(MultiClassFVT):
+    """Perform MDM on a simulated quantum computer
+    (multi-label classification)"""
+
+    def get_params(self):
+        # multi-inheritance pattern
+        return TestClassicalMDM.get_params(self)
+
+    def check(self):
+        TestClassicalMDM.check(self)
\ No newline at end of file

From cf89c8c8576630440f99313e95d44dfd281ab22b Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 15:42:37 +0100
Subject: [PATCH 04/20] fix conftest

---
 tests/conftest.py            | 5 ++---
 tests/test_classification.py | 2 --
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 8b439e8d..f54b54b0 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -98,10 +98,9 @@ def _get_dataset(n_samples, n_features, n_classes, type="bin"):
             labels = _get_labels(n_samples, n_classes)
         elif type == "bin_cov":
             samples_0 = make_covariances(
-                n_samples // n_classes, n_features, 0, return_params=False
+                    n_samples // n_classes, n_features, 0, return_params=False
             )
-            samples_1 = samples_0 * 2
-            samples = np.concatenate((samples_0, samples_1), axis=0)
+            samples = np.concatenate([samples_0 * (i + 1) for i in range(n_classes)], axis=0)
             labels = _get_labels(n_samples, n_classes)
         else:
             samples, labels = get_mne_sample()
diff --git a/tests/test_classification.py b/tests/test_classification.py
index 94b0032e..ae6126f6 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -142,7 +142,6 @@ class TestQuanticSVM_MultiClass(MultiClassFVT):
     (multi-label classification)"""
 
     def get_params(self):
-        # multi-inheritance pattern
         return TestQuanticSVM.get_params(self)
 
     def check(self):
@@ -226,7 +225,6 @@ class TestQuanticMDM_MultiClass(MultiClassFVT):
     (multi-label classification)"""
 
     def get_params(self):
-        # multi-inheritance pattern
         return TestClassicalMDM.get_params(self)
 
     def check(self):

From 2f0adfb95d83075f7a672162c8aeabca759dca55 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 20:48:08 +0100
Subject: [PATCH 05/20] fix MDM multiclass test

---
 tests/test_classification.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tests/test_classification.py b/tests/test_classification.py
index ae6126f6..174fa521 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -215,10 +215,11 @@ def get_params(self):
         }
 
     def check(self):
-        for i in range(len(self.quantum_instance.classes_)):
-            assert (
-                np.all(self.prediction[self.class_len * i : self.class_len * (i + 1)]) == self.quantum_instance.classes_[i]
-            )
+        assert len(self.prediction) == len(self.labels)
+        # Check the number of classes is consistent
+        assert len(np.unique(self.prediction)) == len(np.unique(self.labels))
+        # Check the proba for each classes are returned
+        assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 class TestQuanticMDM_MultiClass(MultiClassFVT):
     """Perform MDM on a simulated quantum computer

From 1e05ad6880fb0a7e10d38e9e3e3dbf005dfa4abb Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 20:49:30 +0100
Subject: [PATCH 06/20] reactivate quantum pipeline with
 plot_classify_P300_bi.py

---
 examples/ERP/plot_classify_P300_bi.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/examples/ERP/plot_classify_P300_bi.py b/examples/ERP/plot_classify_P300_bi.py
index e2809c1b..a5ea971d 100644
--- a/examples/ERP/plot_classify_P300_bi.py
+++ b/examples/ERP/plot_classify_P300_bi.py
@@ -67,7 +67,7 @@
 
 # reduce the number of subjects, the Quantum pipeline takes a lot of time
 # if executed on the entire dataset
-n_subjects = 5
+n_subjects = 2
 for dataset in datasets:
     dataset.subject_list = dataset.subject_list[0:n_subjects]
 
@@ -78,7 +78,7 @@
 # A Riemannian Quantum pipeline provided by pyRiemann-qiskit
 # You can choose between classical SVM and Quantum SVM.
 pipelines["RG+QuantumSVM"] = QuantumClassifierWithDefaultRiemannianPipeline(
-    shots=None,  # 'None' forces classic SVM
+    shots=512,  # 'None' forces classic SVM
     nfilter=2,  # default 2
     # default n_components=10, a higher value renders better performance with
     # the non-qunatum SVM version used in qiskit

From 5b5644741c5637ed9010bd98ba4b77f18130c0fc Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 21:02:14 +0100
Subject: [PATCH 07/20] fix labels for multiclass

---
 pyriemann_qiskit/classification.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 872f8267..bf022a0a 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -454,7 +454,7 @@ def predict(self, X):
         """
         if(isinstance(self._classifier, QSVC)):
             probs = self.predict_proba(X)
-            labels = [1 if prob[0] < prob[1] else 0 for prob in probs]
+            labels = [np.argmax(prob) for prob in probs]
         else:
             labels = self._predict(X)
         self._log("Prediction finished.")

From 901edfa757ae84a079aeda77ddfd1858b05a3f8a Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 6 Dec 2023 20:05:33 +0000
Subject: [PATCH 08/20] [pre-commit.ci] auto fixes from pre-commit.com hooks

---
 pyriemann_qiskit/classification.py | 30 +++++++++++++++---------------
 tests/conftest.py                  |  6 ++++--
 tests/test_classification.py       |  6 +++++-
 3 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index bf022a0a..577b950d 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -237,7 +237,7 @@ def _predict(self, X):
         result = self._classifier.predict(X)
         self._log("Prediction finished.")
         return result
-    
+
     def predict_proba(self, X):
         """Return the probabilities associated with predictions.
 
@@ -258,12 +258,17 @@ def predict_proba(self, X):
             prob[n, i] == 1 if the nth sample is assigned to class `i`;
         """
 
-        if(not hasattr(self._classifier, "predict_proba")):
+        if not hasattr(self._classifier, "predict_proba"):
             # Classifier has no predict_proba
             # Use the result from predict and apply a softmax
             proba = self._classifier.predict(X)
             proba = [
-                np.array([1 if c == self.classes_[i] else 0 for i in range(len(self.classes_))])
+                np.array(
+                    [
+                        1 if c == self.classes_[i] else 0
+                        for i in range(len(self.classes_))
+                    ]
+                )
                 for c in proba
             ]
             proba = softmax(proba, axis=0)
@@ -388,9 +393,7 @@ def _init_algo(self, n_features):
                 self._log("[Warning] `gamma` is not supported by PegasosQSVC")
                 num_steps = 1000 if self.max_iter is None else self.max_iter
                 classifier = PegasosQSVC(
-                    quantum_kernel=quantum_kernel,
-                    C=self.C,
-                    num_steps=num_steps
+                    quantum_kernel=quantum_kernel, C=self.C, num_steps=num_steps
                 )
             else:
                 max_iter = -1 if self.max_iter is None else self.max_iter
@@ -399,16 +402,13 @@ def _init_algo(self, n_features):
                     gamma=self.gamma,
                     C=self.C,
                     max_iter=max_iter,
-                    probability=True
+                    probability=True,
                 )
         else:
             max_iter = -1 if self.max_iter is None else self.max_iter
             classifier = SVC(
-                    gamma=self.gamma,
-                    C=self.C,
-                    max_iter=max_iter,
-                    probability=True
-                )
+                gamma=self.gamma, C=self.C, max_iter=max_iter, probability=True
+            )
         return classifier
 
     def predict_proba(self, X):
@@ -432,8 +432,8 @@ def predict_proba(self, X):
         """
 
         proba = super().predict_proba(X)
-        if(isinstance(self._classifier, QSVC)):
-            # apply additional softmax 
+        if isinstance(self._classifier, QSVC):
+            # apply additional softmax
             proba = softmax(proba)
 
         return np.array(proba)
@@ -452,7 +452,7 @@ def predict(self, X):
         pred : array, shape (n_samples,)
             Class labels for samples in X.
         """
-        if(isinstance(self._classifier, QSVC)):
+        if isinstance(self._classifier, QSVC):
             probs = self.predict_proba(X)
             labels = [np.argmax(prob) for prob in probs]
         else:
diff --git a/tests/conftest.py b/tests/conftest.py
index f54b54b0..333f39a2 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -98,9 +98,11 @@ def _get_dataset(n_samples, n_features, n_classes, type="bin"):
             labels = _get_labels(n_samples, n_classes)
         elif type == "bin_cov":
             samples_0 = make_covariances(
-                    n_samples // n_classes, n_features, 0, return_params=False
+                n_samples // n_classes, n_features, 0, return_params=False
+            )
+            samples = np.concatenate(
+                [samples_0 * (i + 1) for i in range(n_classes)], axis=0
             )
-            samples = np.concatenate([samples_0 * (i + 1) for i in range(n_classes)], axis=0)
             labels = _get_labels(n_samples, n_classes)
         else:
             samples, labels = get_mne_sample()
diff --git a/tests/test_classification.py b/tests/test_classification.py
index 174fa521..ed28e3b3 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -119,6 +119,7 @@ def check(self):
         # Check the proba for each classes are returned
         assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
+
 class TestQuanticSVM(TestClassicalSVM):
     """Tests the Quantum version of Quantic SVM.
     It is executed on a simulated quantum computer.
@@ -137,6 +138,7 @@ def get_params(self):
             "type": "bin",
         }
 
+
 class TestQuanticSVM_MultiClass(MultiClassFVT):
     """Perform SVM on a simulated quantum computer
     (multi-label classification)"""
@@ -147,6 +149,7 @@ def get_params(self):
     def check(self):
         TestQuanticSVM.check(self)
 
+
 class TestQuanticPegasosSVM(TestClassicalSVM):
     """Same as TestQuanticSVM, except it uses
     PegasosQSVC instead of QSVC implementation.
@@ -221,6 +224,7 @@ def check(self):
         # Check the proba for each classes are returned
         assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
+
 class TestQuanticMDM_MultiClass(MultiClassFVT):
     """Perform MDM on a simulated quantum computer
     (multi-label classification)"""
@@ -229,4 +233,4 @@ def get_params(self):
         return TestClassicalMDM.get_params(self)
 
     def check(self):
-        TestClassicalMDM.check(self)
\ No newline at end of file
+        TestClassicalMDM.check(self)

From 7ab17bc6cab3e6ffb393e66ddae2096c68bf629c Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Wed, 6 Dec 2023 21:30:22 +0100
Subject: [PATCH 09/20] remove feature_entanglement from plot_compare_dim

---
 examples/MI/plot_compare_dim_red.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/examples/MI/plot_compare_dim_red.py b/examples/MI/plot_compare_dim_red.py
index a47b349b..55bf6295 100644
--- a/examples/MI/plot_compare_dim_red.py
+++ b/examples/MI/plot_compare_dim_red.py
@@ -39,10 +39,6 @@
     # Determine the number of "run" on the quantum machine (simulated or real)
     # the higher is this number, the lower the variability.
     "shots": [1024],  # [512, 1024, 2048]
-    # This defines how we entangle the data into a quantum state
-    # the more complex is the kernel, the more outcomes we can expect from
-    # a quantum vs classical classifier.
-    "feature_entanglement": ["linear"],  # ['linear', 'sca', 'full'],
     # This parameter change the depth of the circuit when entangling data.
     # There is a trade-off between accuracy and noise when the depth of the
     # circuit increases.

From 02655f207721460e225fd42bc6bc04a2a9640c54 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 09:10:21 +0100
Subject: [PATCH 10/20] missing cast to np.array

---
 pyriemann_qiskit/classification.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 577b950d..17986e01 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -150,7 +150,7 @@ def _map_indices_to_classes(self, y):
         n_classes = len(self.classes_)
         for idx in range(n_classes):
             y_copy[y == idx] = self.classes_[idx]
-        return y_copy
+        return np.array(y_copy)
 
     def fit(self, X, y):
         """Uses a quantum backend and fits the training data.
@@ -261,6 +261,8 @@ def predict_proba(self, X):
         if not hasattr(self._classifier, "predict_proba"):
             # Classifier has no predict_proba
             # Use the result from predict and apply a softmax
+            self._log("No predict_proba method available.\
+                       Computing softmax probabilities...")
             proba = self._classifier.predict(X)
             proba = [
                 np.array(

From f90aa689d61ec852179ede1d8cf4be45ee49122f Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 8 Dec 2023 08:11:08 +0000
Subject: [PATCH 11/20] [pre-commit.ci] auto fixes from pre-commit.com hooks

---
 pyriemann_qiskit/classification.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 17986e01..eeabc775 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -261,8 +261,10 @@ def predict_proba(self, X):
         if not hasattr(self._classifier, "predict_proba"):
             # Classifier has no predict_proba
             # Use the result from predict and apply a softmax
-            self._log("No predict_proba method available.\
-                       Computing softmax probabilities...")
+            self._log(
+                "No predict_proba method available.\
+                       Computing softmax probabilities..."
+            )
             proba = self._classifier.predict(X)
             proba = [
                 np.array(

From f9ad84ed44f627ce6b006bf5afb9b0c395ecca7f Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 15:48:34 +0100
Subject: [PATCH 12/20] - fix financial example (inverted classifier rf and
 erp) - only apply softmax on predict (remove useless overriden method
 predict_proba inside QSVM).

---
 .../other_datasets/plot_financial_data.py     |  4 +--
 pyriemann_qiskit/classification.py            | 29 +------------------
 2 files changed, 3 insertions(+), 30 deletions(-)

diff --git a/examples/other_datasets/plot_financial_data.py b/examples/other_datasets/plot_financial_data.py
index 2c539cf7..b45b0f87 100644
--- a/examples/other_datasets/plot_financial_data.py
+++ b/examples/other_datasets/plot_financial_data.py
@@ -443,7 +443,7 @@ def transform(self, X):
 
 
 class ERP_CollusionClassifier(ClassifierMixin):
-    def __init__(self, row_clf, erp_clf, threshold=0.5):
+    def __init__(self, erp_clf, row_clf, threshold=0.5):
         self.row_clf = row_clf
         self.erp_clf = erp_clf
         self.threshold = threshold
@@ -453,7 +453,7 @@ def fit(self, X, y):
         return self
 
     def predict(self, X):
-        y_pred = self.row_clf.predict(X)
+        y_pred = self.row_clf.predict(X).astype(float)
         collusion_prob = self.erp_clf.predict_proba(X)
         y_pred[y_pred == 1] = collusion_prob[y_pred == 1, 1].transpose()
         y_pred[y_pred >= self.threshold] = 1
diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index eeabc775..93d58a8e 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -415,33 +415,6 @@ def _init_algo(self, n_features):
             )
         return classifier
 
-    def predict_proba(self, X):
-        """Return the probabilities associated with predictions.
-
-        This method is implemented for compatibility purpose
-        as SVM prediction probabilities are not available.
-        This method assigns a boolean value to each trial which
-        depends on whether the label was assigned to class 0 or 1
-
-        Parameters
-        ----------
-        X : ndarray, shape (n_samples, n_features)
-            Input vector, where `n_samples` is the number of samples and
-            `n_features` is the number of features.
-
-        Returns
-        -------
-        prob : ndarray, shape (n_samples, n_classes)
-            prob[n, i] == 1 if the nth sample is assigned to class `i`;
-        """
-
-        proba = super().predict_proba(X)
-        if isinstance(self._classifier, QSVC):
-            # apply additional softmax
-            proba = softmax(proba)
-
-        return np.array(proba)
-
     def predict(self, X):
         """Calculates the predictions.
 
@@ -457,7 +430,7 @@ def predict(self, X):
             Class labels for samples in X.
         """
         if isinstance(self._classifier, QSVC):
-            probs = self.predict_proba(X)
+            probs = softmax(self.predict_proba(X))
             labels = [np.argmax(prob) for prob in probs]
         else:
             labels = self._predict(X)

From d29991404863b387df4eccfe289f2f9e1d135f19 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 18:07:59 +0100
Subject: [PATCH 13/20] fix _map_indices_to_classes

---
 pyriemann_qiskit/classification.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 93d58a8e..52f69f84 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -146,10 +146,10 @@ def _map_classes_to_indices(self, y):
         return y_copy
 
     def _map_indices_to_classes(self, y):
-        y_copy = y.copy()
+        y_copy = np.array(y.copy())
         n_classes = len(self.classes_)
         for idx in range(n_classes):
-            y_copy[y == idx] = self.classes_[idx]
+            y_copy[np.array(y).transpose() == idx] = self.classes_[idx]     
         return np.array(y_copy)
 
     def fit(self, X, y):

From cb76985caa1b2379b2dde069fab00bd8aac23964 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 8 Dec 2023 17:18:39 +0000
Subject: [PATCH 14/20] [pre-commit.ci] auto fixes from pre-commit.com hooks

---
 pyriemann_qiskit/classification.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 52f69f84..0879bb5e 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -149,7 +149,7 @@ def _map_indices_to_classes(self, y):
         y_copy = np.array(y.copy())
         n_classes = len(self.classes_)
         for idx in range(n_classes):
-            y_copy[np.array(y).transpose() == idx] = self.classes_[idx]     
+            y_copy[np.array(y).transpose() == idx] = self.classes_[idx]
         return np.array(y_copy)
 
     def fit(self, X, y):

From 48099fc81564e6b718cd19dceb7289ce7ea590b0 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 18:22:46 +0100
Subject: [PATCH 15/20] Anton's suggestion

---
 README.md                     | 11 +++--------
 pyriemann_qiskit/pipelines.py |  4 ++++
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 3eea2ca4..17e41d0d 100644
--- a/README.md
+++ b/README.md
@@ -96,7 +96,7 @@ This library is part of the [Qiskit Ecosystem](https://qiskit.org/ecosystem)
 _We recommend the use of [Anaconda](https://www.anaconda.com/) to manage python
 environements._
 
-`pyRiemann-qiskit` currently supports Windows, Mac and Linux OS with Python 3.9 - 3.11.
+`pyRiemann-qiskit` currently supports Windows, Mac and Linux OS with **Python 3.9 - 3.11**.
 
 You can install `pyRiemann-qiskit` release from PyPI:
 
@@ -105,13 +105,8 @@ pip install pyriemann-qiskit
 ```
 
 The development version can be installed by cloning this repository and installing the
-package on your local machine using the `setup.py` script:
-
-```
-python setup.py develop
-```
-
-Or directly pip:
+package on your local machine using the `setup.py` script.
+We recommand to do it using `pip`:
 
 ```
 pip install .
diff --git a/pyriemann_qiskit/pipelines.py b/pyriemann_qiskit/pipelines.py
index b6db7f4a..c39d778a 100644
--- a/pyriemann_qiskit/pipelines.py
+++ b/pyriemann_qiskit/pipelines.py
@@ -257,6 +257,10 @@ def _create_pipe(self):
         is_vqc = self.spsa_trials and self.two_local_reps
         is_quantum = self.shots is not None
 
+        # Different feature maps can be used.
+        # Currently the best results are produced by the x_feature_map.
+        # This can change in the future as the code for the different feature maps
+        # is updated in the new versions of Qiskit.
         feature_map = gen_x_feature_map(self.feature_reps)
 
         if is_vqc:

From 8828048d068440c01112b61cead8a0e71e2deca8 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 8 Dec 2023 17:23:09 +0000
Subject: [PATCH 16/20] [pre-commit.ci] auto fixes from pre-commit.com hooks

---
 README.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 17e41d0d..785e2728 100644
--- a/README.md
+++ b/README.md
@@ -96,7 +96,8 @@ This library is part of the [Qiskit Ecosystem](https://qiskit.org/ecosystem)
 _We recommend the use of [Anaconda](https://www.anaconda.com/) to manage python
 environements._
 
-`pyRiemann-qiskit` currently supports Windows, Mac and Linux OS with **Python 3.9 - 3.11**.
+`pyRiemann-qiskit` currently supports Windows, Mac and Linux OS with **Python 3.9 -
+3.11**.
 
 You can install `pyRiemann-qiskit` release from PyPI:
 
@@ -105,8 +106,8 @@ pip install pyriemann-qiskit
 ```
 
 The development version can be installed by cloning this repository and installing the
-package on your local machine using the `setup.py` script.
-We recommand to do it using `pip`:
+package on your local machine using the `setup.py` script. We recommand to do it using
+`pip`:
 
 ```
 pip install .

From b3e61e5f76f73410bbecbc5c7f441dfaae0d9d4f Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 18:55:54 +0100
Subject: [PATCH 17/20] various typo

---
 examples/MI/plot_compare_dim_red.py |  2 +-
 pyriemann_qiskit/classification.py  |  4 ++--
 pyriemann_qiskit/pipelines.py       |  4 ++--
 tests/test_classification.py        | 10 +++++-----
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/examples/MI/plot_compare_dim_red.py b/examples/MI/plot_compare_dim_red.py
index 55bf6295..48febbb9 100644
--- a/examples/MI/plot_compare_dim_red.py
+++ b/examples/MI/plot_compare_dim_red.py
@@ -39,7 +39,7 @@
     # Determine the number of "run" on the quantum machine (simulated or real)
     # the higher is this number, the lower the variability.
     "shots": [1024],  # [512, 1024, 2048]
-    # This parameter change the depth of the circuit when entangling data.
+    # This parameter changes the depth of the circuit when entangling data.
     # There is a trade-off between accuracy and noise when the depth of the
     # circuit increases.
     "feature_reps": [2],  # [2, 3, 4]
diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 0879bb5e..39250e3c 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -243,7 +243,7 @@ def predict_proba(self, X):
 
         The default behavior is to return the nested classifier probabilities.
         In case where no `predict_proba` method is available inside the classifier,
-        the method the predicted label number (0 or 1 for examples) and applies a
+        the method predicts the label number (0 or 1 for examples) and applies a
         softmax in top of it.
 
         Parameters
@@ -300,7 +300,7 @@ class QuanticSVM(QuanticClassifierBase):
         Fix: copy estimator not keeping base class parameters.
     .. versionchanged:: 0.2.0
         Add seed parameter
-        SVC and QSVC now compute probability (may impact time performance)
+        SVC and QSVC now compute probability (may impact performance)
         Predict is now using predict_proba with a softmax, when using QSVC.
 
     Parameters
diff --git a/pyriemann_qiskit/pipelines.py b/pyriemann_qiskit/pipelines.py
index c39d778a..004082cd 100644
--- a/pyriemann_qiskit/pipelines.py
+++ b/pyriemann_qiskit/pipelines.py
@@ -177,7 +177,7 @@ class QuantumClassifierWithDefaultRiemannianPipeline(BasePipeline):
         Number of repetitions of each circuit, for sampling.
         If None, classical computation will be performed.
     feature_reps : int (default: 2)
-        The number of repeated circuits for the ZZFeatureMap,
+        The number of repeated circuits for the FeatureMap,
         greater or equal to 1.
     spsa_trials : int (default: None)
         Maximum number of iterations to perform using SPSA optimizer.
@@ -202,7 +202,7 @@ class QuantumClassifierWithDefaultRiemannianPipeline(BasePipeline):
     -----
     .. versionadded:: 0.0.1
     .. versionchanged:: 0.2.0
-        Change feature map from ZZFeatureMap to XFeatureMap.
+        Changed feature map from ZZFeatureMap to XFeatureMap.
         Therefore remove unused parameter `feature_entanglement`.
 
     See Also
diff --git a/tests/test_classification.py b/tests/test_classification.py
index ed28e3b3..3fe8dcc3 100644
--- a/tests/test_classification.py
+++ b/tests/test_classification.py
@@ -116,7 +116,7 @@ def get_params(self):
     def check(self):
         # Check that all classes are predicted
         assert len(self.prediction) == len(self.labels)
-        # Check the proba for each classes are returned
+        # Check if the proba for each classes are returned
         assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 
@@ -183,9 +183,9 @@ def check(self):
         # Considering the inputs, this probably make no sense to test accuracy.
         # Instead, we could consider this test as a canary test
         assert len(self.prediction) == len(self.labels)
-        # Check the number of classes is consistent
+        # Check if the number of classes is consistent
         assert len(np.unique(self.prediction)) == len(np.unique(self.labels))
-        # Check the proba for each classes are returned
+        # Check if the proba for each classes are returned
         assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 
@@ -219,9 +219,9 @@ def get_params(self):
 
     def check(self):
         assert len(self.prediction) == len(self.labels)
-        # Check the number of classes is consistent
+        # Check if the number of classes is consistent
         assert len(np.unique(self.prediction)) == len(np.unique(self.labels))
-        # Check the proba for each classes are returned
+        # Check if the proba for each classes are returned
         assert self.predict_proab.shape[1] == len(np.unique(self.labels))
 
 

From 3c421bac7b845a313c0051b0954d6606c0a12702 Mon Sep 17 00:00:00 2001
From: Gregoire Cattan <gregoire.cattan@ibm.com>
Date: Fri, 8 Dec 2023 21:23:35 +0100
Subject: [PATCH 18/20] - Run multiclass classification example: Ok - fix
 titles

---
 examples/MI/multiclass_classification.py | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/examples/MI/multiclass_classification.py b/examples/MI/multiclass_classification.py
index 61291f5f..ef77f972 100644
--- a/examples/MI/multiclass_classification.py
+++ b/examples/MI/multiclass_classification.py
@@ -99,13 +99,21 @@
     # A confusion matrix is reported for each classifier. A perfectly performing
     # classifier will have only its diagonal filled and the rest will be zeros.
     names = ["aud left", "aud right", "vis left", "vis right"]
-    title = (
-        ("VQC (" if idx == 0 else "Quantum SVM (" if idx == 1 else "Classical SVM (")
-        if idx == 2
-        else "Quantum MDM ("
-        if idx == 3
-        else "R-MDM (" + acc_str + ")"
-    )
+    if idx == 0:
+        title="VQC"
+    elif idx == 1:
+        title="Q-SVM"
+    elif idx == 2:
+        title="SVM"
+    elif idx == 3:
+        title="Q-MDM"
+    else:
+        title="MDM"
+
+    title = f"{title} (" + acc_str + ")"
+
+    print(title)
+
     axe = axes[idx]
     cm = confusion_matrix(y_pred, y_test)
     disp = ConfusionMatrixDisplay(cm, display_labels=names)

From 2df3cdf86a7d1abd70b6df9189b1ac0919357991 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 8 Dec 2023 20:24:41 +0000
Subject: [PATCH 19/20] [pre-commit.ci] auto fixes from pre-commit.com hooks

---
 examples/MI/multiclass_classification.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/examples/MI/multiclass_classification.py b/examples/MI/multiclass_classification.py
index ef77f972..19e7fc75 100644
--- a/examples/MI/multiclass_classification.py
+++ b/examples/MI/multiclass_classification.py
@@ -100,15 +100,15 @@
     # classifier will have only its diagonal filled and the rest will be zeros.
     names = ["aud left", "aud right", "vis left", "vis right"]
     if idx == 0:
-        title="VQC"
+        title = "VQC"
     elif idx == 1:
-        title="Q-SVM"
+        title = "Q-SVM"
     elif idx == 2:
-        title="SVM"
+        title = "SVM"
     elif idx == 3:
-        title="Q-MDM"
+        title = "Q-MDM"
     else:
-        title="MDM"
+        title = "MDM"
 
     title = f"{title} (" + acc_str + ")"
 

From 7c6d6fb14bab9eb9512dc05170ed9b08b7180194 Mon Sep 17 00:00:00 2001
From: qbarthelemy <q.barthelemy@gmail.com>
Date: Fri, 8 Dec 2023 22:21:04 +0100
Subject: [PATCH 20/20] minor correction

---
 pyriemann_qiskit/classification.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyriemann_qiskit/classification.py b/pyriemann_qiskit/classification.py
index 39250e3c..823dfac4 100644
--- a/pyriemann_qiskit/classification.py
+++ b/pyriemann_qiskit/classification.py
@@ -255,7 +255,7 @@ def predict_proba(self, X):
         Returns
         -------
         prob : ndarray, shape (n_samples, n_classes)
-            prob[n, i] == 1 if the nth sample is assigned to class `i`;
+            prob[n, i] == 1 if the nth sample is assigned to class `i`.
         """
 
         if not hasattr(self._classifier, "predict_proba"):