rgwfuncs 0.0.13__tar.gz → 0.0.15__tar.gz

{rgwfuncs-0.0.13/src/rgwfuncs.egg-info → rgwfuncs-0.0.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.13
+Version: 0.0.15
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

{rgwfuncs-0.0.13 → rgwfuncs-0.0.15}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rgwfuncs"
-version = "0.0.13"
+version = "0.0.15"
 authors = [
   { name = "Ryan Gerard Wilson", email = "ryangerardwilson@gmail.com" },
 ]

{rgwfuncs-0.0.13 → rgwfuncs-0.0.15}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = rgwfuncs
-version = 0.0.13
+version = 0.0.15
 author = Ryan Gerard Wilson
 author_email = ryangerardwilson@gmail.com
 description = A functional programming paradigm for mathematical modelling and data science

{rgwfuncs-0.0.13 → rgwfuncs-0.0.15}/src/rgwfuncs/df_lib.py

@@ -1614,7 +1614,6 @@ def mask_against_dataframe_converse(df: pd.DataFrame, other_df: pd.DataFrame, co
 
     return df[~df[column_name].isin(other_df[column_name])]
 
-
 def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     """
     Perform a union join, concatenating the two DataFrames and dropping duplicates.
@@ -1633,19 +1632,19 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     # print("Initial df1 columns:", df1.columns)
     # print("Initial df2 columns:", df2.columns)
 
-    # Standardize columns by adding missing columns filled with NaN
+    # Standardize columns by adding missing columns filled with empty strings
     for col in df2.columns:
         if col not in df1:
-            df1[col] = pd.NA
+            df1[col] = ""
 
     for col in df1.columns:
         if col not in df2:
-            df2[col] = pd.NA
+            df2[col] = ""
 
     # print("Standardized df1 columns:", df1.columns)
     # print("Standardized df2 columns:", df2.columns)
 
-    # Check if columns match now
+    # Ensure they have the same columns after standardizing
     if set(df1.columns) != set(df2.columns):
         raise ValueError("Both DataFrames must have the same columns after standardizing columns")
 
@@ -1653,7 +1652,6 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     result_df = pd.concat([df1, df2], ignore_index=True).drop_duplicates()
     return result_df
 
-
 def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     """
     Perform a bag union join, concatenating the two DataFrames without dropping duplicates.
@@ -1672,14 +1670,14 @@ def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     # print("Initial df1 columns:", df1.columns)
     # print("Initial df2 columns:", df2.columns)
 
-    # Standardize columns by adding missing columns filled with NaN
+    # Standardize columns by adding missing columns filled with empty strings
     for col in df2.columns:
         if col not in df1:
-            df1[col] = pd.NA
+            df1[col] = ""
 
     for col in df1.columns:
         if col not in df2:
-            df2[col] = pd.NA
+            df2[col] = ""
 
     # print("Standardized df1 columns:", df1.columns)
     # print("Standardized df2 columns:", df2.columns)

{rgwfuncs-0.0.13 → rgwfuncs-0.0.15/src/rgwfuncs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.13
+Version: 0.0.15
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson