Merge pull request #10 from INGEOTEC/develop

Version - 0.1.0

.github/workflows/pip.yaml

@@ -14,12 +14,12 @@ jobs:
         shell: bash -l {0}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-latest, windows-latest]
         python-version: ["3.9", "3.10", "3.11"]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python
-      uses: conda-incubator/setup-miniconda@v2
+      uses: conda-incubator/setup-miniconda@v3
       with:
         activate-environment: test
         auto-update-conda: true

.github/workflows/test.yaml

@@ -13,12 +13,12 @@ jobs:
         shell: bash -l {0}      
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-latest, windows-latest]
         python-version: ["3.9", "3.10", "3.11"]
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python
-      uses: conda-incubator/setup-miniconda@v2
+      uses: conda-incubator/setup-miniconda@v3
       with:
         activate-environment: test
         auto-update-conda: true

CompStats/__init__.py

@@ -11,7 +11,9 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-__version__ = '0.0.6'
+__version__ = '0.1.0'
 from CompStats.bootstrap import StatisticSamples
-from CompStats.measurements import CI, difference_p_value
+from CompStats.measurements import CI, SE, difference_p_value
 from CompStats.performance import performance, difference, all_differences, plot_performance, plot_difference
+from CompStats.performance import performance_multiple_metrics, difference_multiple, plot_performance_multiple, plot_difference_multiple
+from CompStats.performance import all_differences_multiple, plot_performance2, plot_difference2, plot_scatter_matrix

CompStats/bootstrap.py

@@ -46,10 +46,12 @@ class StatisticSamples:
     def __init__(self,
                  statistic: Callable[[np.ndarray], float]=np.mean,
                  num_samples: int=500,
-                 n_jobs: int=1):
+                 n_jobs: int=1,
+                 BiB: bool=True):
         self.statistic = statistic
         self.num_samples = num_samples
         self.n_jobs = n_jobs
+        self.BiB = BiB  # Guardar el parámetro BiB        
         self._samples = None
         self._calls = {}
         self._info = {}
@@ -67,7 +69,8 @@ def get_params(self):
         """Parameters"""
         return dict(statistic=self.statistic,
                     num_samples=self.num_samples,
-                    n_jobs=self.n_jobs)
+                    n_jobs=self.n_jobs,
+                    BiB=self.BiB)  # Añadir BiB a los parámetros
 
     def __sklearn_clone__(self):
         klass = self.__class__

CompStats/measurements.py

@@ -34,13 +34,38 @@ def CI(samples: np.ndarray, alpha=0.05):
     (0.6, 1.0)
     """
     if isinstance(samples, StatisticSamples):
-        return {k: CI(v) for k, v in samples.calls.items()}
+        return {k: CI(v, alpha=alpha) for k, v in samples.calls.items()}
     alpha = alpha / 2
     return (np.percentile(samples, alpha * 100, axis=0),
             np.percentile(samples, (1 - alpha) * 100, axis=0))
 
+
+def SE(samples: np.ndarray):
+    """Compute the Standard Error of a statistic using bootstrap.
+    
+    >>> from CompStats import StatisticSamples, SE
+    >>> from sklearn.metrics import accuracy_score
+    >>> import numpy as np    
+    >>> labels = np.r_[[0, 0, 0, 0, 0, 1, 1, 1, 1, 1]]
+    >>> pred   = np.r_[[0, 0, 1, 0, 0, 1, 1, 1, 0, 1]]
+    >>> bootstrap = StatisticSamples(statistic=accuracy_score)
+    >>> samples = bootstrap(labels, pred)
+    >>> SE(samples)
+    """
+    if isinstance(samples, StatisticSamples):
+        return {k: SE(v) for k, v in samples.calls.items()}
+    return np.std(samples, axis=0)
+
 
-def difference_p_value(statistic_samples: StatisticSamples):
+def difference_p_value(samples: np.ndarray, BiB: bool = True):
     """Compute the difference p-value"""
-    return {k: (v > 2 * np.mean(v)).mean()
-            for k, v in statistic_samples.calls.items()}
+    if isinstance(samples, StatisticSamples):
+        if samples.BiB:
+            return {k: (v > 2 * np.mean(v)).mean() for k, v in samples.calls.items()}
+        else:
+            return {k: (v < 2 * np.mean(v)).mean() for k, v in samples.calls.items()}
+    else:
+        if BiB:
+            return np.mean(samples > 2 * np.mean(samples, axis=0), axis=0)
+        else:
+            return np.mean(samples < 2 * np.mean(samples, axis=0), axis=0)