Remove duplicate closure function

eis_toolkit/transformations/coda/alr.py

@@ -8,7 +8,7 @@
 from eis_toolkit.exceptions import InvalidColumnException, NumericValueSignException
 from eis_toolkit.utilities.aitchison_geometry import _closure
 from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space
-from eis_toolkit.utilities.miscellaneous import perform_closure, rename_columns_by_pattern
+from eis_toolkit.utilities.miscellaneous import rename_columns_by_pattern
 
 
 @beartype
@@ -24,7 +24,7 @@ def alr_transform(
     columns: Optional[Sequence[str]] = None,
     denominator_column: Optional[str] = None,
     keep_denominator_column: bool = False,
-    closure_target: Optional[Number] = None,
+    scale: Optional[Number] = None,
 ) -> pd.DataFrame:
     """
     Perform an additive logratio transformation on the data.
@@ -35,7 +35,8 @@ def alr_transform(
         denominator_column: The name of the column to be used as the denominator column.
         keep_denominator_column: Whether to include the denominator column in the result. If True, the returned
             dataframe retains its original shape.
-        closure_target: Target row sum for closure. If None, no closure is performed.
+        scale: The value to which each composition should be normalized. Eg., if the composition is expressed
+            as percentages, scale=100.
 
     Returns:
         A new dataframe containing the ALR transformed data.
@@ -65,8 +66,8 @@ def alr_transform(
     else:
         columns_to_transform = df.columns.to_list()
 
-    if closure_target is not None:
-        df = perform_closure(df, columns_to_transform, closure_target)
+    if scale is not None:
+        df = _closure(df, scale)
 
     check_in_simplex_sample_space(df)
 

eis_toolkit/transformations/coda/clr.py

@@ -9,7 +9,7 @@
 from eis_toolkit.exceptions import InvalidColumnException, NumericValueSignException
 from eis_toolkit.utilities.aitchison_geometry import _closure
 from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space
-from eis_toolkit.utilities.miscellaneous import perform_closure, rename_columns, rename_columns_by_pattern
+from eis_toolkit.utilities.miscellaneous import rename_columns, rename_columns_by_pattern
 
 
 @beartype
@@ -29,15 +29,16 @@ def _clr_transform(df: pd.DataFrame) -> pd.DataFrame:
 def clr_transform(
     df: pd.DataFrame,
     columns: Optional[Sequence[str]] = None,
-    closure_target: Optional[Number] = None,
+    scale: Optional[Number] = None,
 ) -> pd.DataFrame:
     """
     Perform a centered logratio transformation on the data.
 
     Args:
         df: A dataframe of compositional data.
         columns: The names of the columns to be transformed.
-        closure_target: Target row sum for closure. If None, no closure is performed.
+        scale: The value to which each composition should be normalized. Eg., if the composition is expressed
+            as percentages, scale=100.
 
     Returns:
         A new dataframe containing the CLR transformed data.
@@ -57,8 +58,8 @@ def clr_transform(
     else:
         columns_to_transform = df.columns.to_list()
 
-    if closure_target is not None:
-        df = perform_closure(df, columns_to_transform, closure_target)
+    if scale is not None:
+        df = _closure(df, scale)
 
     check_in_simplex_sample_space(df)
 

eis_toolkit/transformations/coda/ilr.py

@@ -7,10 +7,10 @@
 from scipy.stats import gmean
 
 from eis_toolkit.exceptions import InvalidColumnException, InvalidCompositionException, InvalidParameterValueException
+from eis_toolkit.utilities.aitchison_geometry import _closure
 from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space
 from eis_toolkit.utilities.checks.dataframe import check_columns_valid
 from eis_toolkit.utilities.checks.parameter import check_lists_overlap, check_numeric_value_sign
-from eis_toolkit.utilities.miscellaneous import perform_closure
 
 
 @beartype
@@ -70,7 +70,7 @@ def single_ilr_transform(
     df: pd.DataFrame,
     subcomposition_1: Sequence[str],
     subcomposition_2: Sequence[str],
-    closure_target: Optional[Number] = None,
+    scale: Optional[Number] = None,
 ) -> pd.Series:
     """
     Perform a single isometric logratio transformation on the provided subcompositions.
@@ -81,7 +81,8 @@ def single_ilr_transform(
         df: A dataframe of shape [N, D] of compositional data.
         subcomposition_1: Names of the columns in the numerator part of the ratio.
         subcomposition_2: Names of the columns in the denominator part of the ratio.
-        closure_target: Target row sum for closure. If None, no closure is performed.
+        scale: The value to which each composition should be normalized. Eg., if the composition is expressed
+            as percentages, scale=100.
 
     Returns:
         A series of length N containing the transforms.
@@ -103,10 +104,8 @@ def single_ilr_transform(
     if check_lists_overlap(subcomposition_1, subcomposition_2):
         raise InvalidCompositionException("The subcompositions overlap.")
 
-    if closure_target is not None:
-        columns = subcomposition_1 + subcomposition_2
-        df = perform_closure(df, columns, closure_target)
-        df = df[columns]
+    if scale is not None:
+        df = _closure(df, scale)
 
     check_in_simplex_sample_space(df)
 

eis_toolkit/transformations/coda/plr.py

@@ -7,9 +7,10 @@
 from scipy.stats import gmean
 
 from eis_toolkit.exceptions import InvalidColumnException, InvalidParameterValueException
+from eis_toolkit.utilities.aitchison_geometry import _closure
 from eis_toolkit.utilities.checks.compositional import check_in_simplex_sample_space
 from eis_toolkit.utilities.checks.parameter import check_numeric_value_sign
-from eis_toolkit.utilities.miscellaneous import perform_closure, rename_columns_by_pattern
+from eis_toolkit.utilities.miscellaneous import rename_columns_by_pattern
 
 
 @beartype
@@ -53,7 +54,7 @@ def _single_plr_transform_by_index(df: pd.DataFrame, column_ind: int) -> pd.Seri
 
 
 @beartype
-def single_plr_transform(df: pd.DataFrame, column: str, closure_target: Optional[Number] = None) -> pd.Series:
+def single_plr_transform(df: pd.DataFrame, column: str, scale: Optional[Number] = None) -> pd.Series:
     """
     Perform a pivot logratio transformation on the selected column.
 
@@ -65,7 +66,8 @@ def single_plr_transform(df: pd.DataFrame, column: str, closure_target: Optional
     Args:
         df: A dataframe of shape [N, D] of compositional data.
         column: The name of the numerator column to use for the transformation.
-        closure_target: Target row sum for closure. If None, no closure is performed.
+        scale: The value to which each composition should be normalized. Eg., if the composition is expressed
+            as percentages, scale=100.
     Returns:
         A series of length N containing the transforms.
 
@@ -84,17 +86,15 @@ def single_plr_transform(df: pd.DataFrame, column: str, closure_target: Optional
     if idx == len(df.columns) - 1:
         raise InvalidColumnException("Can't select last column as numerator.")
 
-    if closure_target is not None:
-        # Perform closure on columns starting from numerator "to the right"
-        columns = df.columns[idx:].to_list()
-        df = perform_closure(df, columns, closure_target)
+    # Keep columns from idx to the right
+    df = df.iloc[:, idx:]
 
-        check_in_simplex_sample_space(df[columns])
+    if scale is not None:
+        df = _closure(df, scale)
 
-    else:
-        check_in_simplex_sample_space(df)
+    check_in_simplex_sample_space(df)
 
-    return _single_plr_transform_by_index(df, idx)
+    return _single_plr_transform_by_index(df, 0)
 
 
 @beartype
@@ -112,15 +112,16 @@ def _plr_transform(df: pd.DataFrame) -> pd.DataFrame:
 
 @beartype
 def plr_transform(
-    df: pd.DataFrame, columns: Optional[Sequence[str]] = None, closure_target: Optional[Number] = None
+    df: pd.DataFrame, columns: Optional[Sequence[str]] = None, scale: Optional[Number] = None
 ) -> pd.DataFrame:
     """
     Perform a pivot logratio transformation on the dataframe, returning the full set of transforms.
 
     Args:
         df: A dataframe of shape [N, D] of compositional data.
         columns: The names of the columns to use for the transformation.
-        closure_target: Target row sum for closure. If None, no closure is performed.
+        scale: The value to which each composition should be normalized. Eg., if the composition is expressed
+            as percentages, scale=100.
 
     Returns:
         A dataframe of shape [N, D-1] containing the set of PLR transformed data.
@@ -137,8 +138,8 @@ def plr_transform(
             raise InvalidColumnException(f"The following columns were not found in the dataframe: {invalid_columns}.")
         df = df[columns]
 
-    if closure_target is not None:
-        df = perform_closure(df, closure_target=1)
+    if scale is not None:
+        df = _closure(df, scale)
 
     check_in_simplex_sample_space(df)
 

eis_toolkit/utilities/miscellaneous.py

@@ -375,29 +375,3 @@ def toggle_gdal_exceptions():
     finally:
         if not already_has_exceptions_enabled:
             gdal.DontUseExceptions()
-
-
-@beartype
-def perform_closure(
-    df: pd.DataFrame, columns: Optional[Sequence[str]] = None, closure_target: Number = 1
-) -> pd.DataFrame:
-    """
-    Peform closure on selected columns of a DataFrame.
-
-    Values in the specified columns of each row are scaled so that they sum to 'closure_target'.
-
-    Args:
-        df: Input DataFrame.
-        columns: Names of the columns on which to perform closure. If not provided, all columns are used.
-        closure_target: Row sum of the selected columns after performing closure. Defaults to 1.
-
-    Returns:
-        A DataFrame where on each row the values in the selected columns sum to the closure target.
-    """
-    if columns is None:
-        columns = df.columns
-
-    row_sums = df[columns].sum(axis=1)
-    df[columns] = df[columns].div(row_sums, axis=0).mul(closure_target)
-
-    return df

tests/transformations/coda/ilr_test.py

@@ -15,10 +15,10 @@ def test_calculate_scaling_factor():
 
 def test_single_ilr_transform_with_single_composition():
     """Test the core functionality of a single ILR transform with a single row of data."""
-    arr = np.array([80, 15, 5])
+    arr = np.array([80, 15, 5]).astype(np.float64)
     df = pd.DataFrame(arr[None], columns=["a", "b", "c"])
 
-    result = single_ilr_transform(df, ["a"], ["b"])
+    result = single_ilr_transform(df, ["a"], ["b"], scale=100)
     assert result[0] == pytest.approx(1.18, abs=1e-2)
 
     result = single_ilr_transform(df, ["a", "b"], ["c"])
@@ -27,10 +27,10 @@ def test_single_ilr_transform_with_single_composition():
 
 def test_single_ilr_transform():
     """Test the core functionality of a single ILR transform."""
-    arr = np.array([[80, 15, 5], [75, 18, 7]])
+    arr = np.array([[80, 15, 5], [75, 18, 7]]).astype(dtype=np.float64)
     df = pd.DataFrame(arr, columns=["a", "b", "c"])
 
-    result = single_ilr_transform(df, ["a"], ["b"])
+    result = single_ilr_transform(df, ["a"], ["b"], scale=100)
     assert result[1] == pytest.approx(1.01, abs=1e-2)
 
     result = single_ilr_transform(df, ["a", "b"], ["c"])

tests/transformations/coda/plr_test.py

@@ -17,7 +17,7 @@ def test_single_plr_transform_with_single_composition():
     result = _single_plr_transform_by_index(df, 0)
     assert result[0] == pytest.approx(1.82, abs=1e-2)
 
-    result = single_plr_transform(df, "b", closure_target=100)
+    result = single_plr_transform(df, "b", scale=100)
     assert result[0] == pytest.approx(0.78, abs=1e-2)
 
     result = _single_plr_transform_by_index(df, 1)

tests/utilities/miscellaneous_test.py

@@ -4,7 +4,6 @@
 
 from eis_toolkit.exceptions import InvalidColumnIndexException
 from eis_toolkit.utilities.miscellaneous import (
-    perform_closure,
     rename_columns,
     rename_columns_by_pattern,
     replace_values,
@@ -72,11 +71,3 @@ def test_rename_columns_with_too_few_columns():
     target_df = pd.DataFrame({"a": [1, 2], "b": [3, 4], "col3": [5, 6]})
     renamed_df = rename_columns(df, colnames=colnames)
     pd.testing.assert_frame_equal(renamed_df, target_df)
-
-
-def test_perform_closure():
-    """Test that performing closure on a DataFrame works as expected."""
-    df = pd.DataFrame({"col1": [1, 2, 1], "col2": [4, 8, 1], "col3": [3, 1, 6]})
-    closured_df = perform_closure(df, columns=["col1", "col2"], closure_target=100)
-    expected_df = pd.DataFrame({"col1": [20.0, 20.0, 50.0], "col2": [80.0, 80.0, 50.0], "col3": [3, 1, 6]})
-    pd.testing.assert_frame_equal(closured_df, expected_df)