0.24.30

Author: bartzbeielstein

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotpython"
-version = "0.24.29"
+version = "0.24.30"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotpython/utils/compare.py

@@ -86,7 +86,7 @@ def check_identical_columns_and_rows(df, remove=False, verbosity=1) -> tuple:
     identical_columns = []
     for i in range(len(df.columns)):
         for j in range(i + 1, len(df.columns)):
-            if df.iloc[:, i].equals(df.iloc[:, j]):
+            if df.iloc[:, i].equals(df.iloc[:, j]):  # Ensure entire columns are compared
                 identical_columns.append((df.columns[i], df.columns[j]))
 
     if identical_columns and verbosity > 0:
@@ -101,7 +101,7 @@ def check_identical_columns_and_rows(df, remove=False, verbosity=1) -> tuple:
     identical_rows = []
     for i in range(len(df.index)):
         for j in range(i + 1, len(df.index)):
-            if df.iloc[i, :].equals(df.iloc[j, :]):
+            if df.iloc[i, :].equals(df.iloc[j, :]):  # Ensure entire rows are compared
                 identical_rows.append((df.index[i], df.index[j]))
 
     if identical_rows and verbosity > 0:

test/test_check_identical_columns_and_rows.py

@@ -3,6 +3,7 @@
 from spotpython.utils.compare import check_identical_columns_and_rows, check_identical_columns_and_rows_with_tol
 
 def test_check_exact_identical_columns_and_rows_remove_true():
+    # Test DataFrame with exact duplicate columns
     df1 = pd.DataFrame({
         "A": [1, 2, 3],
         "B": [1, 2, 3],
@@ -15,6 +16,7 @@ def test_check_exact_identical_columns_and_rows_remove_true():
     assert identical_rows == [], "Incorrectly identified duplicate rows where none exist"
 
 def test_check_exact_identical_columns_and_rows_remove_false():
+    # Test DataFrame checks presence of duplicates without removing
     df1 = pd.DataFrame({
         "A": [1, 2, 3],
         "B": [1, 2, 3],
@@ -27,6 +29,7 @@ def test_check_exact_identical_columns_and_rows_remove_false():
     assert identical_rows == [], "Incorrectly found duplicate rows"
 
 def test_check_identical_columns_and_rows_with_tol_remove_true():
+    # Test DataFrame with near-duplicate tolerance checks for columns
     df1 = pd.DataFrame({
         "A": [1.00, 2.01, 3.00],
         "B": [1.01, 2.00, 3.01],
@@ -39,6 +42,7 @@ def test_check_identical_columns_and_rows_with_tol_remove_true():
     assert identical_rows == [], "Incorrectly found duplicate rows"
 
 def test_check_identical_columns_and_rows_with_tol_remove_false():
+    # Test DataFrame with tolerance execution, no removal
     df1 = pd.DataFrame({
         "A": [1.00, 2.01, 3.00],
         "B": [1.01, 2.00, 3.01],
@@ -51,6 +55,7 @@ def test_check_identical_columns_and_rows_with_tol_remove_false():
     assert identical_rows == [], "Incorrectly found duplicate rows"
 
 def test_with_no_duplicates():
+    # Tests scenarios where there are no duplicate columns or rows present
     df = pd.DataFrame({
         "X": [1, 2, 3],
         "Y": [4, 5, 6],