rgwfuncs 0.0.21__tar.gz → 0.0.23__tar.gz

{rgwfuncs-0.0.21/src/rgwfuncs.egg-info → rgwfuncs-0.0.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.21
+Version: 0.0.23
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

{rgwfuncs-0.0.21 → rgwfuncs-0.0.23}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rgwfuncs"
-version = "0.0.21"
+version = "0.0.23"
 authors = [
   { name = "Ryan Gerard Wilson", email = "ryangerardwilson@gmail.com" },
 ]

{rgwfuncs-0.0.21 → rgwfuncs-0.0.23}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = rgwfuncs
-version = 0.0.21
+version = 0.0.23
 author = Ryan Gerard Wilson
 author_email = ryangerardwilson@gmail.com
 description = A functional programming paradigm for mathematical modelling and data science

{rgwfuncs-0.0.21 → rgwfuncs-0.0.23}/src/rgwfuncs/df_lib.py

@@ -1672,7 +1672,6 @@ def print_n_frequency_cascading(
     report = generate_cascade_report(df, columns, n, order_by)
     print(json.dumps(report, indent=2))
 
-
 def print_n_frequency_linear(df: pd.DataFrame, n: int, columns: list, order_by: str = "FREQ_DESC") -> None:
     """
     Print the linear frequency of top n values for specified columns.
@@ -1709,27 +1708,36 @@ def print_n_frequency_linear(df: pd.DataFrame, n: int, columns: list, order_by:
 
         return report
 
+    def try_parse_numeric(val):
+        """Attempt to parse a value as an integer or float."""
+        try:
+            return int(val)
+        except ValueError:
+            try:
+                return float(val)
+            except ValueError:
+                return val
+
     def sort_frequency(frequency, order_by):
-        if order_by == "ASC":
-            return dict(sorted(frequency.items(), key=lambda item: item[0]))
-        elif order_by == "DESC":
-            return dict(
-                sorted(
-                    frequency.items(),
-                    key=lambda item: item[0],
-                    reverse=True))
-        elif order_by == "FREQ_ASC":
-            return dict(sorted(frequency.items(), key=lambda item: item[1]))
-        elif order_by == "BY_KEYS_ASC":
-            return dict(sorted(frequency.items()))
-        elif order_by == "BY_KEYS_DESC":
-            return dict(sorted(frequency.items(), reverse=True))
-        else:  # Default to "FREQ_DESC"
-            return dict(
-                sorted(
-                    frequency.items(),
-                    key=lambda item: item[1],
-                    reverse=True))
+        keys = frequency.keys()
+
+        # Convert keys to numerical values where possible, leaving `NaN` as a special string
+        parsed_keys = [(try_parse_numeric(key), key) for key in keys]
+
+        if order_by in {"BY_KEYS_ASC", "BY_KEYS_DESC"}:
+            reverse = order_by == "BY_KEYS_DESC"
+            sorted_items = sorted(frequency.items(), key=lambda item: try_parse_numeric(item[0]), reverse=reverse)
+        else:
+            if order_by == "ASC":
+                sorted_items = sorted(frequency.items(), key=lambda item: item[0])
+            elif order_by == "DESC":
+                sorted_items = sorted(frequency.items(), key=lambda item: item[0], reverse=True)
+            elif order_by == "FREQ_ASC":
+                sorted_items = sorted(frequency.items(), key=lambda item: item[1])
+            else:  # Default to "FREQ_DESC"
+                sorted_items = sorted(frequency.items(), key=lambda item: item[1], reverse=True)
+
+        return dict(sorted_items)
 
     report = generate_linear_report(df, columns, n, order_by)
     print(json.dumps(report, indent=2))

{rgwfuncs-0.0.21 → rgwfuncs-0.0.23/src/rgwfuncs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.21
+Version: 0.0.23
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson