rgwfuncs 0.0.12__py3-none-any.whl → 0.0.14__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- rgwfuncs/df_lib.py +9 -10
 - {rgwfuncs-0.0.12.dist-info → rgwfuncs-0.0.14.dist-info}/METADATA +1 -1
 - rgwfuncs-0.0.14.dist-info/RECORD +8 -0
 - rgwfuncs-0.0.12.dist-info/RECORD +0 -8
 - {rgwfuncs-0.0.12.dist-info → rgwfuncs-0.0.14.dist-info}/LICENSE +0 -0
 - {rgwfuncs-0.0.12.dist-info → rgwfuncs-0.0.14.dist-info}/WHEEL +0 -0
 - {rgwfuncs-0.0.12.dist-info → rgwfuncs-0.0.14.dist-info}/entry_points.txt +0 -0
 - {rgwfuncs-0.0.12.dist-info → rgwfuncs-0.0.14.dist-info}/top_level.txt +0 -0
 
    
        rgwfuncs/df_lib.py
    CHANGED
    
    | 
         @@ -61,6 +61,7 @@ def docs(method_type_filter: Optional[str] = None) -> None: 
     | 
|
| 
       61 
61 
     | 
    
         
             
                                # Print the entire docstring for the matching function
         
     | 
| 
       62 
62 
     | 
    
         
             
                                print(f"\n{name}:\n{docstring}")
         
     | 
| 
       63 
63 
     | 
    
         | 
| 
      
 64 
     | 
    
         
            +
             
     | 
| 
       64 
65 
     | 
    
         
             
            def numeric_clean(df: pd.DataFrame, column_names: str, column_type: str, irregular_value_treatment: str) -> pd.DataFrame:
         
     | 
| 
       65 
66 
     | 
    
         
             
                """
         
     | 
| 
       66 
67 
     | 
    
         
             
                Cleans the numeric columns based on specified treatments.
         
     | 
| 
         @@ -1613,7 +1614,6 @@ def mask_against_dataframe_converse(df: pd.DataFrame, other_df: pd.DataFrame, co 
     | 
|
| 
       1613 
1614 
     | 
    
         | 
| 
       1614 
1615 
     | 
    
         
             
                return df[~df[column_name].isin(other_df[column_name])]
         
     | 
| 
       1615 
1616 
     | 
    
         | 
| 
       1616 
     | 
    
         
            -
             
     | 
| 
       1617 
1617 
     | 
    
         
             
            def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
         
     | 
| 
       1618 
1618 
     | 
    
         
             
                """
         
     | 
| 
       1619 
1619 
     | 
    
         
             
                Perform a union join, concatenating the two DataFrames and dropping duplicates.
         
     | 
| 
         @@ -1632,19 +1632,19 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame: 
     | 
|
| 
       1632 
1632 
     | 
    
         
             
                print("Initial df1 columns:", df1.columns)
         
     | 
| 
       1633 
1633 
     | 
    
         
             
                print("Initial df2 columns:", df2.columns)
         
     | 
| 
       1634 
1634 
     | 
    
         | 
| 
       1635 
     | 
    
         
            -
                # Standardize columns by adding missing columns filled with  
     | 
| 
      
 1635 
     | 
    
         
            +
                # Standardize columns by adding missing columns filled with empty strings
         
     | 
| 
       1636 
1636 
     | 
    
         
             
                for col in df2.columns:
         
     | 
| 
       1637 
1637 
     | 
    
         
             
                    if col not in df1:
         
     | 
| 
       1638 
     | 
    
         
            -
                        df1[col] =  
     | 
| 
      
 1638 
     | 
    
         
            +
                        df1[col] = ""
         
     | 
| 
       1639 
1639 
     | 
    
         | 
| 
       1640 
1640 
     | 
    
         
             
                for col in df1.columns:
         
     | 
| 
       1641 
1641 
     | 
    
         
             
                    if col not in df2:
         
     | 
| 
       1642 
     | 
    
         
            -
                        df2[col] =  
     | 
| 
      
 1642 
     | 
    
         
            +
                        df2[col] = ""
         
     | 
| 
       1643 
1643 
     | 
    
         | 
| 
       1644 
1644 
     | 
    
         
             
                print("Standardized df1 columns:", df1.columns)
         
     | 
| 
       1645 
1645 
     | 
    
         
             
                print("Standardized df2 columns:", df2.columns)
         
     | 
| 
       1646 
1646 
     | 
    
         | 
| 
       1647 
     | 
    
         
            -
                #  
     | 
| 
      
 1647 
     | 
    
         
            +
                # Ensure they have the same columns after standardizing
         
     | 
| 
       1648 
1648 
     | 
    
         
             
                if set(df1.columns) != set(df2.columns):
         
     | 
| 
       1649 
1649 
     | 
    
         
             
                    raise ValueError("Both DataFrames must have the same columns after standardizing columns")
         
     | 
| 
       1650 
1650 
     | 
    
         | 
| 
         @@ -1670,14 +1670,14 @@ def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame: 
     | 
|
| 
       1670 
1670 
     | 
    
         
             
                print("Initial df1 columns:", df1.columns)
         
     | 
| 
       1671 
1671 
     | 
    
         
             
                print("Initial df2 columns:", df2.columns)
         
     | 
| 
       1672 
1672 
     | 
    
         | 
| 
       1673 
     | 
    
         
            -
                # Standardize columns by adding missing columns filled with  
     | 
| 
      
 1673 
     | 
    
         
            +
                # Standardize columns by adding missing columns filled with empty strings
         
     | 
| 
       1674 
1674 
     | 
    
         
             
                for col in df2.columns:
         
     | 
| 
       1675 
1675 
     | 
    
         
             
                    if col not in df1:
         
     | 
| 
       1676 
     | 
    
         
            -
                        df1[col] =  
     | 
| 
      
 1676 
     | 
    
         
            +
                        df1[col] = ""
         
     | 
| 
       1677 
1677 
     | 
    
         | 
| 
       1678 
1678 
     | 
    
         
             
                for col in df1.columns:
         
     | 
| 
       1679 
1679 
     | 
    
         
             
                    if col not in df2:
         
     | 
| 
       1680 
     | 
    
         
            -
                        df2[col] =  
     | 
| 
      
 1680 
     | 
    
         
            +
                        df2[col] = ""
         
     | 
| 
       1681 
1681 
     | 
    
         | 
| 
       1682 
1682 
     | 
    
         
             
                print("Standardized df1 columns:", df1.columns)
         
     | 
| 
       1683 
1683 
     | 
    
         
             
                print("Standardized df2 columns:", df2.columns)
         
     | 
| 
         @@ -1722,6 +1722,7 @@ def right_join(df1: pd.DataFrame, df2: pd.DataFrame, left_on: str, right_on: str 
     | 
|
| 
       1722 
1722 
     | 
    
         
             
                """
         
     | 
| 
       1723 
1723 
     | 
    
         
             
                return df1.merge(df2, how='right', left_on=left_on, right_on=right_on)
         
     | 
| 
       1724 
1724 
     | 
    
         | 
| 
      
 1725 
     | 
    
         
            +
             
     | 
| 
       1725 
1726 
     | 
    
         
             
            def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataFrame) -> None:
         
     | 
| 
       1726 
1727 
     | 
    
         
             
                """
         
     | 
| 
       1727 
1728 
     | 
    
         
             
                Processes and saves a DataFrame to an SQLite database, adding a timestamp column
         
     | 
| 
         @@ -1776,5 +1777,3 @@ def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataF 
     | 
|
| 
       1776 
1777 
     | 
    
         
             
                        conn.execute(f"DROP TABLE IF EXISTS {tablename}")
         
     | 
| 
       1777 
1778 
     | 
    
         
             
                        # Rename the new table to the old table name
         
     | 
| 
       1778 
1779 
     | 
    
         
             
                        conn.execute(f"ALTER TABLE {new_table_name} RENAME TO {tablename}")
         
     | 
| 
       1779 
     | 
    
         
            -
             
     | 
| 
       1780 
     | 
    
         
            -
             
     | 
| 
         @@ -0,0 +1,8 @@ 
     | 
|
| 
      
 1 
     | 
    
         
            +
            rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
         
     | 
| 
      
 2 
     | 
    
         
            +
            rgwfuncs/df_lib.py,sha256=GlFATJvcvLxQK-twfmcBIMJk_1-cq4HCuiODqyoZN78,64094
         
     | 
| 
      
 3 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
         
     | 
| 
      
 4 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/METADATA,sha256=QSQo_msYCNSoln73NBfxfgvudh4LmTwVwzvM2JHc114,32059
         
     | 
| 
      
 5 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
         
     | 
| 
      
 6 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
         
     | 
| 
      
 7 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
         
     | 
| 
      
 8 
     | 
    
         
            +
            rgwfuncs-0.0.14.dist-info/RECORD,,
         
     | 
    
        rgwfuncs-0.0.12.dist-info/RECORD
    DELETED
    
    | 
         @@ -1,8 +0,0 @@ 
     | 
|
| 
       1 
     | 
    
         
            -
            rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
         
     | 
| 
       2 
     | 
    
         
            -
            rgwfuncs/df_lib.py,sha256=mIOEvnqpkkHW2Az23_09Xt61nltTtG6uNW0b81aW5Mg,64060
         
     | 
| 
       3 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
         
     | 
| 
       4 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/METADATA,sha256=rgeOUbLIXmgb-JuqmAcdF2G2vBS7iWCdsop74rfuTfc,32059
         
     | 
| 
       5 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
         
     | 
| 
       6 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
         
     | 
| 
       7 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
         
     | 
| 
       8 
     | 
    
         
            -
            rgwfuncs-0.0.12.dist-info/RECORD,,
         
     | 
| 
         
            File without changes
         
     | 
| 
         
            File without changes
         
     | 
| 
         
            File without changes
         
     | 
| 
         
            File without changes
         
     |