julearn 0.3.5.dev80__tar.gz → 0.3.5.dev92__tar.gz

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: julearn
-Version: 0.3.5.dev80
+Version: 0.3.5.dev92
 Summary: Juelich Machine Learning Library
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Sami Hamdan <s.hamdan@fz-juelich.de>
 Maintainer-email: Sami Hamdan <s.hamdan@fz-juelich.de>

julearn-0.3.5.dev92/docs/changes/newsfragments/226.bugfix

@@ -0,0 +1 @@
+Fix parenthesis escaping in column names by `Synchon Mandal`_

julearn-0.3.5.dev92/docs/changes/newsfragments/226.feature

@@ -0,0 +1 @@
+Add a new global config option `"enable_auto_escape_parenthesis"` to escape parenthesis in column names by `Synchon Mandal`_

julearn-0.3.5.dev92/docs/changes/newsfragments/288.bugfix

@@ -0,0 +1 @@
+Fix a bug in which inspecting predictions will result in NaNs if y had a custom index by `Fede Raimondo`_

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/docs/configuration.rst

@@ -54,3 +54,7 @@ Here you can find the comprehensive list of flags that can be set:
        | If set to ``True``, the parameter will be set back to None.
      - | Column transformers will be applied in parallel, using more resources.
        | than expected.
+   * - ``enable_auto_escape_parenthesis``
+     - | This flag enables escaping parenthesis in column names.
+     - | If column names include parenthesis, then they will be treated as regular
+       | expression metacharacters and not regular characters.

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.5.dev80'
-__version_tuple__ = version_tuple = (0, 3, 5, 'dev80')
+__version__ = version = '0.3.5.dev92'
+__version_tuple__ = version_tuple = (0, 3, 5, 'dev92')
 
-__commit_id__ = commit_id = 'g835fe2f52'
+__commit_id__ = commit_id = 'g367066e38'

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/config.py

@@ -15,6 +15,7 @@ _global_config["disable_xtypes_check"] = False
 _global_config["disable_x_verbose"] = False
 _global_config["disable_xtypes_verbose"] = False
 _global_config["enable_parallel_column_transformers"] = False
+_global_config["enable_auto_escape_parenthesis"] = True
 
 
 def set_config(key: str, value: Any) -> None:

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/inspect/_cv.py

@@ -160,6 +160,7 @@ class FoldsInspector:
         predictions = predictions.sort_index()
         target_df = pd.DataFrame(self._y)
         target_df.columns = ["target"]
+        target_df.reset_index(inplace=True)
         predictions = target_df.join(predictions, how="left")
         return predictions
 

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/inspect/tests/test_cv.py

@@ -132,11 +132,18 @@ def test_get_predictions(get_cv_scores, df_typed_iris):
 
     X = df_typed_iris.iloc[:, :4]
     y = df_typed_iris["species"]
+    # Add another kind of index to y
+    y.index = [f"sample-{i:03d}" for i in range(100, len(y) + 100)]
+    y.index.name = "sample_id"
     cv, df_scores = get_cv_scores
     inspector = FoldsInspector(df_scores, cv=cv, X=X, y=y)
     print(df_scores)
     expected_df = pd.DataFrame(
-        {"target": y.values, "repeat0_p0": X.index.values}
+        {
+            "sample_id": y.index.values,
+            "target": y.values,
+            "repeat0_p0": X.index.values,
+        }
     )
     assert_frame_equal(inspector.predict(), expected_df)
     assert_frame_equal(inspector.predict_proba(), expected_df)
@@ -233,7 +240,9 @@ def test_overlapping_cv_predictions(klass, params, cv_params, df_grouped_iris):
     mock_model = MockModelReturnsIndex
     X = df_grouped_iris.iloc[:, :4]
     y = df_grouped_iris["species"]
-
+    # Add another kind of index to y
+    y.index = [f"sample-{i:03d}" for i in range(100, len(y) + 100)]
+    y.index.name = "sample_id"
     groups = None
     if "groups" in params:
         groups = df_grouped_iris["group"]
@@ -253,6 +262,7 @@ def test_overlapping_cv_predictions(klass, params, cv_params, df_grouped_iris):
     inspector = FoldsInspector(df_scores, cv=cv, X=X, y=y, groups=groups)
     print(df_scores)
     expected_dict = {}
+    expected_dict["sample_id"] = y.index.values
     expected_dict["target"] = y.values
     for i, (_, test) in enumerate(cv.split(X, y, groups=groups)):
         expected_dict[f"fold{i}_p0"] = np.array(
@@ -305,7 +315,9 @@ def test_nonoverlapping_cv_predictions(
     mock_model = MockModelReturnsIndex
     X = df_grouped_iris.iloc[:, :4]
     y = df_grouped_iris["species"]
-
+    # Add another kind of index to y
+    y.index = [f"sample-{i:03d}" for i in range(100, len(y) + 100)]
+    y.index.name = "sample_id"
     groups = None
     if "groups" in params:
         groups = df_grouped_iris["group"]
@@ -325,6 +337,7 @@ def test_nonoverlapping_cv_predictions(
     inspector = FoldsInspector(df_scores, cv=cv, X=X, y=y, groups=groups)
     print(df_scores)
     expected_dict = {}
+    expected_dict["sample_id"] = y.index.values
     expected_dict["target"] = y.values
     n_repeats = getattr(cv, "n_repeats", 1)
     for i in range(n_repeats):
@@ -378,7 +391,9 @@ def test_nonoverlapping_continuous_cv_predictions(
     mock_model = MockModelReturnsIndex
     X = df_regression.iloc[:, :-1]
     y = df_regression["target"]
-
+    # Add another kind of index to y
+    y.index = [f"sample-{i:03d}" for i in range(100, len(y) + 100)]
+    y.index.name = "sample_id"
     groups = None
     if "groups" in params:
         groups = df_regression["group"]
@@ -399,6 +414,7 @@ def test_nonoverlapping_continuous_cv_predictions(
     inspector = FoldsInspector(df_scores, cv=cv, X=X, y=y, groups=groups)
     print(df_scores)
     expected_dict = {}
+    expected_dict["sample_id"] = y.index.values
     expected_dict["target"] = y.values
     n_repeats = getattr(cv, "n_repeats", 1)
     for i in range(n_repeats):

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/prepare.py

@@ -175,6 +175,7 @@ def _pick_columns(
     if not isinstance(regexes, list):
         regexes = [regexes]
 
+    parens = ["(", ")"]
     picks = []
     for exp in regexes:
         if not _is_regex(exp):
@@ -184,7 +185,18 @@ def _pick_columns(
             cols = [
                 col
                 for col in columns
-                if any([re.fullmatch(exp, col)]) and col not in picks
+                if any(
+                    [
+                        re.fullmatch(
+                            re.escape(exp)
+                            if get_config("enable_auto_escape_parenthesis")
+                            and any(char in exp for char in parens)
+                            else exp,
+                            col,
+                        )
+                    ]
+                )
+                and col not in picks
             ]
             if len(cols) > 0:
                 picks.extend(cols)
@@ -199,7 +211,16 @@ def _pick_columns(
             )
         unmatched = []
         for exp in regexes:
-            if not any(re.fullmatch(exp, col) for col in columns):
+            if not any(
+                re.fullmatch(
+                    re.escape(exp)
+                    if get_config("enable_auto_escape_parenthesis")
+                    and any(char in exp for char in parens)
+                    else exp,
+                    col,
+                )
+                for col in columns
+            ):
                 unmatched.append(exp)
         if len(unmatched) > 0:
             raise ValueError(
@@ -476,16 +497,43 @@ def _check_x_types(
             )
         missing_columns = []
         defined_columns = []
-        for _, columns in X_types.items():
+        parens = ["(", ")"]
+        for columns in X_types.values():
+            if not get_config("enable_auto_escape_parenthesis"):
+                if any(char in col for char in parens for col in columns):
+                    warn_with_log(
+                        f"{parens} found in column names, "
+                        "recommended to use "
+                        '`julearn.config.set_config("enable_auto_escape_'
+                        'parenthesis", True)`'
+                    )
             t_columns = [
                 col
                 for col in X
-                if any(re.fullmatch(exp, col) for exp in columns)
+                if any(
+                    re.fullmatch(
+                        re.escape(exp)
+                        if get_config("enable_auto_escape_parenthesis")
+                        and any(char in exp for char in parens)
+                        else exp,
+                        col,
+                    )
+                    for exp in columns
+                )
             ]
             t_missing = [
                 exp
                 for exp in columns
-                if not any(re.fullmatch(exp, col) for col in X)
+                if not any(
+                    re.fullmatch(
+                        re.escape(exp)
+                        if get_config("enable_auto_escape_parenthesis")
+                        and any(char in exp for char in parens)
+                        else exp,
+                        col,
+                    )
+                    for col in X
+                )
             ]
             defined_columns.extend(t_columns)
             missing_columns.extend(t_missing)

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn/tests/test_prepare.py

@@ -158,6 +158,32 @@ def test_prepare_input_data() -> None:
     _check_df_input(prepared, X=X, y=y, groups=groups, df=df)
 
 
+def test_prepare_input_data_with_parens_in_col_names() -> None:
+    """Test prepare input data (dataframe) with parenthesis in column names."""
+    X = [
+        "AgeAtScan",
+        "Sex-0.0",
+        "Feature_0.0",
+        "Feature_1.1",
+        "Feature_2.2",
+        "Feature_3_4_5_7",
+        "Scanner_(X)_pos_head",
+        "Scanner_(Y)_pos_head",
+        "Scanner_(Z)_pos_head",
+        "Scanner_pos_Table",
+        "Intensity_scaling",
+        "Date_of_evaluation",
+    ]
+    y = "target"
+    X_types = {"continuous": X}
+    df = pd.DataFrame(np.random.randn(100, len(X)), columns=X)
+    df[y] = np.random.randint(0, 2, size=100)
+    df_X, _, _, _ = prepare_input_data(
+        X=X, y=y, df=df, pos_labels=None, groups=None, X_types=X_types
+    )
+    assert df_X.columns.size == len(X)
+
+
 def test_prepare_input_data_erors() -> None:
     """Test prepare input data (dataframe) errors."""
     data = np.random.rand(4, 10)
@@ -794,3 +820,26 @@ def test__check_x_types_regexp() -> None:
         warnings.simplefilter("error")
         checked_X_types = _check_x_types(X=X, X_types=X_types)
         assert X_types == checked_X_types
+
+
+def test__check_x_types_regexp_parenthesis_escape() -> None:
+    """Test checking for valid X types using regexp with parenthesis escape."""
+    X = [
+        "a",
+        "b",
+        "a_(c)_b",
+        "a_b_(c)_d",
+        "a-b_c_(d)_e",
+        "a-b_c_(d)_e-f",
+        "g",
+    ]
+    X_types = {"continuous": X}
+    # Disable escaping and expect error
+    set_config("enable_auto_escape_parenthesis", False)
+    with pytest.raises(ValueError, match=r"defined in X_types but not in X"):
+        with pytest.raises(RuntimeWarning, match=r"recommended to use"):
+            checked_X_types = _check_x_types(X=X, X_types=X_types)
+    # Enable escaping and no error
+    set_config("enable_auto_escape_parenthesis", True)
+    checked_X_types = _check_x_types(X=X, X_types=X_types)
+    assert X_types == checked_X_types

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: julearn
-Version: 0.3.5.dev80
+Version: 0.3.5.dev92
 Summary: Juelich Machine Learning Library
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Sami Hamdan <s.hamdan@fz-juelich.de>
 Maintainer-email: Sami Hamdan <s.hamdan@fz-juelich.de>

{julearn-0.3.5.dev80 → julearn-0.3.5.dev92}/julearn.egg-info/SOURCES.txt

@@ -55,6 +55,8 @@ docs/api/utils.rst
 docs/api/viz.rst
 docs/changes/contributors.inc
 docs/changes/newsfragments/.gitignore
+docs/changes/newsfragments/226.bugfix
+docs/changes/newsfragments/226.feature
 docs/changes/newsfragments/254.bugfix
 docs/changes/newsfragments/254.change
 docs/changes/newsfragments/277.enh
@@ -65,6 +67,7 @@ docs/changes/newsfragments/283.doc
 docs/changes/newsfragments/284.misc
 docs/changes/newsfragments/285.bugfix
 docs/changes/newsfragments/286.bugfix
+docs/changes/newsfragments/288.bugfix
 docs/images/corrected_ttest.png
 docs/images/final_estimator.png
 docs/images/iris_X.png