rgwfuncs 0.0.11__py3-none-any.whl → 0.0.13__py3-none-any.whl

rgwfuncs/df_lib.py

@@ -61,6 +61,7 @@ def docs(method_type_filter: Optional[str] = None) -> None:
                     # Print the entire docstring for the matching function
                     print(f"\n{name}:\n{docstring}")
 
+
 def numeric_clean(df: pd.DataFrame, column_names: str, column_type: str, irregular_value_treatment: str) -> pd.DataFrame:
     """
     Cleans the numeric columns based on specified treatments.
@@ -1628,28 +1629,29 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     Raises:
         ValueError: If the DataFrames do not have the same columns.
     """
-    if set(df1.columns) != set(df2.columns):
-        raise ValueError("Both DataFrames must have the same columns for a union join")
-
     # Inspect initial columns
-    print("Initial df1 columns:", df1.columns)
-    print("Initial df2 columns:", df2.columns)
+    # print("Initial df1 columns:", df1.columns)
+    # print("Initial df2 columns:", df2.columns)
 
-    # Drop all-NA columns, if any
-    df1_clean = df1.dropna(axis=1, how='all')
-    df2_clean = df2.dropna(axis=1, how='all')
+    # Standardize columns by adding missing columns filled with NaN
+    for col in df2.columns:
+        if col not in df1:
+            df1[col] = pd.NA
 
-    # Inspect resulting columns after dropping all-NA columns
-    print("Cleaned df1 columns:", df1_clean.columns)
-    print("Cleaned df2 columns:", df2_clean.columns)
+    for col in df1.columns:
+        if col not in df2:
+            df2[col] = pd.NA
 
-    # Ensure they still have the same columns after dropping all-NA columns
-    if set(df1_clean.columns) != set(df2_clean.columns):
-        raise ValueError("Both DataFrames must have the same columns after dropping all-NA columns")
+    # print("Standardized df1 columns:", df1.columns)
+    # print("Standardized df2 columns:", df2.columns)
 
-    result_df = pd.concat([df1_clean, df2_clean], ignore_index=True).drop_duplicates()
-    return result_df
+    # Check if columns match now
+    if set(df1.columns) != set(df2.columns):
+        raise ValueError("Both DataFrames must have the same columns after standardizing columns")
 
+    # Concatenate and drop duplicates
+    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:
@@ -1666,18 +1668,28 @@ def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
     Raises:
         ValueError: If the DataFrames do not have the same columns.
     """
-    if set(df1.columns) != set(df2.columns):
-        raise ValueError("Both DataFrames must have the same columns for a bag union join")
+    # Inspect initial columns
+    # print("Initial df1 columns:", df1.columns)
+    # print("Initial df2 columns:", df2.columns)
+
+    # Standardize columns by adding missing columns filled with NaN
+    for col in df2.columns:
+        if col not in df1:
+            df1[col] = pd.NA
 
-    # Drop all-NA columns, if any
-    df1_clean = df1.dropna(axis=1, how='all')
-    df2_clean = df2.dropna(axis=1, how='all')
+    for col in df1.columns:
+        if col not in df2:
+            df2[col] = pd.NA
 
-    # Ensure they still have the same columns after dropping all-NA columns
-    if set(df1_clean.columns) != set(df2_clean.columns):
-        raise ValueError("Both DataFrames must have the same columns after dropping all-NA columns")
+    # print("Standardized df1 columns:", df1.columns)
+    # print("Standardized df2 columns:", df2.columns)
+
+    # 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")
 
-    result_df = pd.concat([df1_clean, df2_clean], ignore_index=True)
+    # Concatenate without dropping duplicates
+    result_df = pd.concat([df1, df2], ignore_index=True)
     return result_df
 
 
@@ -1712,6 +1724,7 @@ def right_join(df1: pd.DataFrame, df2: pd.DataFrame, left_on: str, right_on: str
     """
     return df1.merge(df2, how='right', left_on=left_on, right_on=right_on)
 
+
 def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataFrame) -> None:
     """
     Processes and saves a DataFrame to an SQLite database, adding a timestamp column
@@ -1766,5 +1779,3 @@ def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataF
             conn.execute(f"DROP TABLE IF EXISTS {tablename}")
             # Rename the new table to the old table name
             conn.execute(f"ALTER TABLE {new_table_name} RENAME TO {tablename}")
-
-

{rgwfuncs-0.0.11.dist-info → rgwfuncs-0.0.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.11
+Version: 0.0.13
 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.dist-info/RECORD

@@ -0,0 +1,8 @@
+rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
+rgwfuncs/df_lib.py,sha256=2JU1Z0wjBrpcmLuJgY6-Bi1OFXHyNk1XeRGESkDI934,64077
+rgwfuncs-0.0.13.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
+rgwfuncs-0.0.13.dist-info/METADATA,sha256=TZoSn8ANcHG2IOAW1SwNbu3ZnPKxdWbKzoCAXLTB06w,32059
+rgwfuncs-0.0.13.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+rgwfuncs-0.0.13.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.13.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.13.dist-info/RECORD,,

rgwfuncs-0.0.11.dist-info/RECORD

@@ -1,8 +0,0 @@
-rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
-rgwfuncs/df_lib.py,sha256=N5XCe9LYMIVjh0pg2Xc1i3Md--mdNJyJ5t7NpO9x4-s,63973
-rgwfuncs-0.0.11.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
-rgwfuncs-0.0.11.dist-info/METADATA,sha256=mqOIwsthIDAdpgtcFt35vW_xc99f2xtu5O_k4_Y-wQY,32059
-rgwfuncs-0.0.11.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-rgwfuncs-0.0.11.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.11.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.11.dist-info/RECORD,,