Merge branch 'main' into update_test.ipynb

Signed-off-by: Jim-smith <jim-smith@users.noreply.github.com>

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ repos:
 
   # Standard hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: check-merge-conflict
       - id: end-of-file-fixer
@@ -26,7 +26,7 @@ repos:
 
   # Check for spelling
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.5
+    rev: v2.2.6
     hooks:
       - id: codespell
         args: ["-L", "tre"]
@@ -39,7 +39,7 @@ repos:
 
   # Upgrade old Python syntax
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.13.0
+    rev: v3.15.0
     hooks:
       - id: pyupgrade
         args: [--py310-plus]

acro/acro_tables.py

@@ -70,6 +70,9 @@ def crosstab(  # pylint: disable=too-many-arguments,too-many-locals
         default, computes a frequency table of the factors unless an array of
         values and an aggregation function are passed.
 
+        To provide consistent behaviour with different aggregation functions,
+        'empty' rows or columns -i.e. that  are all NaN or 0 (count,sum) are removed.
+
         Parameters
         ----------
         index : array-like, Series, or list of arrays/Series
@@ -133,6 +136,28 @@ def crosstab(  # pylint: disable=too-many-arguments,too-many-locals
             dropna,
             normalize,
         )
+        # delete empty rows and columns from table
+        deleted_rows = []
+        deleted_cols = []
+        # define empty columns and rows using boolean masks
+        empty_cols_mask = table.sum(axis=0) == 0
+        empty_rows_mask = table.sum(axis=1) == 0
+
+        deleted_cols = list(table.columns[empty_cols_mask])
+        table = table.loc[:, ~empty_cols_mask]
+        deleted_rows = list(table.index[empty_rows_mask])
+        table = table.loc[~empty_rows_mask, :]
+
+        # create a message with the deleted column's names
+        comments = []
+        if deleted_cols:
+            msg_cols = ", ".join(str(col) for col in deleted_cols)
+            comments.append(f"Empty columns: {msg_cols} were deleted.")
+        if deleted_rows:
+            msg_rows = ", ".join(str(row) for row in deleted_rows)
+            comments.append(f"Empty rows: {msg_rows} were deleted.")
+        if comments:
+            logger.info(" ".join(comments))
 
         masks = create_crosstab_masks(
             index,
@@ -195,6 +220,7 @@ def crosstab(  # pylint: disable=too-many-arguments,too-many-locals
             summary=summary,
             outcome=outcome,
             output=[table],
+            comments=comments,
         )
         return table
 
@@ -548,10 +574,14 @@ def create_crosstab_masks(  # pylint: disable=too-many-arguments,too-many-locals
             normalize=normalize,
         )
 
+        # drop empty columns and rows
         if dropna or margins:
-            for col in t_values.columns:
-                if t_values[col].sum() == 0:
-                    t_values = t_values.drop(col, axis=1)
+            empty_cols_mask = t_values.sum(axis=0) == 0
+            empty_rows_mask = t_values.sum(axis=1) == 0
+
+            t_values = t_values.loc[:, ~empty_cols_mask]
+            t_values = t_values.loc[~empty_rows_mask, :]
+
         t_values = t_values < THRESHOLD
         masks["threshold"] = t_values
         # check for negative values -- currently unsupported

docs/ACRO_For_Researchers.md

@@ -89,7 +89,7 @@ The finalise function will:
 
 ## Frequently Asked Questions
 ### What if I want to run my code many times before I decide exactly what to send for approval?
-ACRO naturally suppors this way of working. It will not produce the output folder until you are satisfied and add acro.finalise() to the end of your script.
+ACRO naturally supports this way of working. It will not produce the output folder until you are satisfied and add acro.finalise() to the end of your script.
 ### Why is my data exported as unformatted .csv files?
 The outputs are saved in row format (as csv files) for the output checkers to check and make decisions. Although, you can change the format, if you like, the csv files should be there for the checking.
 ### Why is ACRO Python-based ‘under-the-hood’?