Merge branch 'dev' into Unit_test_FDA

Author: DakhliFirasQM

.vscode/settings.json

@@ -0,0 +1,42 @@
+{
+    "python.pythonPath": "./workspace_venv/bin/python3",
+    "editor.rulers": [
+        100
+    ],
+    "python.formatting.provider": "black",
+    "python.formatting.blackArgs": [
+        "--line-length=99"
+    ],
+    "isort.args": [
+        "--profile",
+        "black"
+    ],
+    "[python]": {
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "python.linting.flake8Enabled": true,
+    "python.linting.flake8Args": [
+        "--max-line-length=99",
+        "--ignore=E402,F841,F401,E302,E305",
+    ],
+    "files.watcherExclude": {
+        "**/.git/objects/**": true,
+        "**/.git/subtree-cache/**": true,
+        "**/notebooks/*/**": true,
+        "**/node_modules/*/**": true
+    },
+    "terminal.integrated.inheritEnv": false,
+    "python.linting.lintOnSave": false,
+    "python.languageServer": "Pylance",
+    "editor.formatOnSave": true,
+    "terminal.integrated.scrollback": 10000,
+    "python.linting.pylintEnabled": false,
+    "python.linting.enabled": true,
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true
+}

qolmat/benchmark/missing_patterns.py

@@ -44,7 +44,8 @@ def get_sizes_max(values_isna: pd.Series) -> pd.Series:
 
 class _HoleGenerator:
     """
-    This class implements a method to get indices of observed and missing values.
+    This abstract class implements the generic method to generate masks according to law of missing
+    values.
 
     Parameters
     ----------
@@ -191,9 +192,8 @@ def generate_mask(self, X: pd.DataFrame) -> pd.DataFrame:
 
 
 class _SamplerHoleGenerator(_HoleGenerator):
-    """
-    This abstract class implements a generic way to generate holes in a dataframe
-    by sampling 1D hole size distributions.
+    """This abstract class implements a generic way to generate holes in a dataframe by sampling 1D
+    hole size distributions.
 
     Parameters
     ----------
@@ -401,7 +401,7 @@ def compute_distribution_holes(self, states):
         series_id = (states.diff() != 0).cumsum()
         series_id = series_id[states]
         distribution_holes = series_id.value_counts().value_counts()
-        # distribution_holes /= distribution_holes.sum()
+
         return distribution_holes
 
     def fit(self, X: pd.DataFrame) -> EmpiricalHoleGenerator:
@@ -430,7 +430,7 @@ def fit(self, X: pd.DataFrame) -> EmpiricalHoleGenerator:
                 distributions_holes = states.groupby(self.ngroups).apply(
                     self.compute_distribution_holes
                 )
-                distributions_holes = distributions_holes.groupby(level=0).sum()
+                distributions_holes = distributions_holes.groupby(level=1).sum()
                 self.dict_distributions_holes[column] = distributions_holes
 
     def sample_sizes(self, column, n_masked):