rgwfuncs 0.0.59__py3-none-any.whl → 0.0.60__py3-none-any.whl

rgwfuncs/df_lib.py

@@ -643,11 +643,7 @@ def top_n_unique_values(df: pd.DataFrame, n: int, columns: List[str]) -> None:
                 top_n_values = frequency.nlargest(n)
                 report[column] = {str(value): str(count)
                                   for value, count in top_n_values.items()}
-                print(
-                    f"Top {n} unique values for column '{column}':\n{
-                        json.dumps(
-                            report[column],
-                            indent=2)}\n")
+                print(f"Top {n} unique values for column '{column}':\n{json.dumps(report[column], indent=2)}\n")
             else:
                 print(f"Column '{column}' does not exist in the DataFrame.")
     else:
@@ -690,11 +686,7 @@ def bottom_n_unique_values(
                 report[column] = {
                     str(value): str(count) for value,
                     count in bottom_n_values.items()}
-                print(
-                    f"Bottom {n} unique values for column '{column}':\n{
-                        json.dumps(
-                            report[column],
-                            indent=2)}\n")
+                print(f"Bottom {n} unique values for column '{column}':\n{json.dumps(report[column],indent=2)}\n")
             else:
                 print(f"Column '{column}' does not exist in the DataFrame.")
     else:
@@ -753,8 +745,7 @@ def print_memory_usage(df: pd.DataFrame) -> None:
     - ValueError: If the DataFrame is `None`.
     """
     if df is not None:
-        memory_usage = df.memory_usage(deep=True).sum(
-        ) / (1024 * 1024)  # Convert bytes to MB
+        memory_usage = df.memory_usage(deep=True).sum() / (1024 * 1024)  # Convert bytes to MB
         print(f"Memory usage of DataFrame: {memory_usage:.2f} MB")
     else:
         raise ValueError("No DataFrame to print. Please provide a DataFrame.")
@@ -1234,9 +1225,7 @@ def append_ranged_classification_column(
             for r in range_list
         )
 
-        labels = [f"{pad_number(range_list[i],
-                                max_integer_length)} to {pad_number(range_list[i + 1],
-                                                                    max_integer_length)}" for i in range(len(range_list) - 1)]
+        labels = [f"{pad_number(range_list[i],max_integer_length)} to {pad_number(range_list[i + 1], max_integer_length)}" for i in range(len(range_list) - 1)]
 
     # Ensure the target column is numeric
     df[target_col] = pd.to_numeric(df[target_col], errors='coerce')
@@ -1379,8 +1368,7 @@ def rename_columns(df: pd.DataFrame,
         A new DataFrame with columns renamed.
     """
     if df is None:
-        raise ValueError(
-            "No DataFrame to rename columns. Please provide a valid DataFrame.")
+        raise ValueError("No DataFrame to rename columns. Please provide a valid DataFrame.")
 
     return df.rename(columns=rename_pairs)
 
@@ -1398,8 +1386,7 @@ def cascade_sort(df: pd.DataFrame, columns: List[str]) -> pd.DataFrame:
         A new DataFrame sorted by specified columns.
     """
     if df is None:
-        raise ValueError(
-            "No DataFrame to sort. Please provide a valid DataFrame.")
+        raise ValueError("No DataFrame to sort. Please provide a valid DataFrame.")
 
     col_names = []
     asc_order = []
@@ -1434,8 +1421,7 @@ def append_xgb_labels(df: pd.DataFrame, ratio_str: str) -> pd.DataFrame:
         A new DataFrame with XGB_TYPE labels appended.
     """
     if df is None:
-        raise ValueError(
-            "No DataFrame to add labels. Please provide a valid DataFrame.")
+        raise ValueError("No DataFrame to add labels. Please provide a valid DataFrame.")
 
     ratios = list(map(int, ratio_str.split(':')))
     total_ratio = sum(ratios)
@@ -1452,8 +1438,7 @@ def append_xgb_labels(df: pd.DataFrame, ratio_str: str) -> pd.DataFrame:
         labels = ['TRAIN'] * train_rows + ['VALIDATE'] * \
             validate_rows + ['TEST'] * test_rows
     else:
-        raise ValueError(
-            "Invalid ratio string format. Use 'TRAIN:TEST' or 'TRAIN:VALIDATE:TEST'.")
+        raise ValueError("Invalid ratio string format. Use 'TRAIN:TEST' or 'TRAIN:VALIDATE:TEST'.")
 
     df_with_labels = df.copy()
     df_with_labels['XGB_TYPE'] = labels
@@ -1483,8 +1468,7 @@ def append_xgb_regression_predictions(
         DataFrame with predictions appended.
     """
     if df is None or 'XGB_TYPE' not in df.columns:
-        raise ValueError(
-            "DataFrame is not initialized or 'XGB_TYPE' column is missing.")
+        raise ValueError("DataFrame is not initialized or 'XGB_TYPE' column is missing.")
 
     features = feature_cols.replace(' ', '').split(',')
 
@@ -1558,8 +1542,7 @@ def append_xgb_logistic_regression_predictions(
         DataFrame with predictions appended.
     """
     if df is None or 'XGB_TYPE' not in df.columns:
-        raise ValueError(
-            "DataFrame is not initialized or 'XGB_TYPE' column is missing.")
+        raise ValueError("DataFrame is not initialized or 'XGB_TYPE' column is missing.")
 
     features = feature_cols.replace(' ', '').split(',')
 
@@ -1603,8 +1586,7 @@ def append_xgb_logistic_regression_predictions(
     if model_path:
         model.save_model(model_path)
 
-    columns_order = [col for col in df.columns if col not in [
-        'XGB_TYPE', target_col, pred_col]] + ['XGB_TYPE', target_col, pred_col]
+    columns_order = [col for col in df.columns if col not in ['XGB_TYPE', target_col, pred_col]] + ['XGB_TYPE', target_col, pred_col]
     df = df[columns_order]
 
     return df
@@ -1852,8 +1834,7 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
         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")
+        raise ValueError("Both DataFrames must have the same columns for a union join")
 
     result_df = pd.concat([df1, df2], ignore_index=True).drop_duplicates()
     return result_df
@@ -1874,8 +1855,7 @@ def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
         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")
+        raise ValueError("Both DataFrames must have the same columns for a bag union join")
 
     result_df = pd.concat([df1, df2], ignore_index=True)
     return result_df
@@ -2024,12 +2004,7 @@ def sync_dataframe_to_sqlite_database(
         cursor.execute(f"PRAGMA table_info({new_table_name})")
         if cursor.fetchall() == []:  # Table does not exist
             # Create a table using the DataFrame's column names and types
-            columns_with_types = ', '.join(
-                f'"{col}" {
-                    map_dtype(dtype)}' for col,
-                dtype in zip(
-                    df.columns,
-                    df.dtypes))
+            columns_with_types = ', '.join(f'"{col}" {map_dtype(dtype)}' for col,dtype in zip(df.columns,df.dtypes))
             create_table_query = f'CREATE TABLE "{new_table_name}" ({columns_with_types})'
             conn.execute(create_table_query)
 

{rgwfuncs-0.0.59.dist-info → rgwfuncs-0.0.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.59
+Version: 0.0.60
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson

{rgwfuncs-0.0.59.dist-info → rgwfuncs-0.0.60.dist-info}/RECORD

@@ -1,12 +1,12 @@
 rgwfuncs/__init__.py,sha256=-rcdj4_9zq82h0Tl00S9GvEqDYh7yhPCNhnhBs3mZCg,1676
 rgwfuncs/algebra_lib.py,sha256=rKFITfpWfgdBswnbMUuS41XgndEt-jUVz2ObO_ik7eM,42234
-rgwfuncs/df_lib.py,sha256=EJRGHlYIol5UshuGO6m8MoYNjZMmPSU7W-sh1SDclfw,68947
+rgwfuncs/df_lib.py,sha256=XhqHYcrXGEOOqB4Z0Y-ASViy6_R_Df5f7ZGh66RIP6w,68420
 rgwfuncs/docs_lib.py,sha256=y3wSAOPO3qsA4HZ7xAtW8HimM8w-c8hjcEzMRLJ96ao,1960
 rgwfuncs/interactive_shell_lib.py,sha256=A7EWsYxAfDev_N0-2GjRvAtp0bAwBPHIczXb8Gu9fzI,1107
 rgwfuncs/str_lib.py,sha256=rtAdRlnSJIu3JhI-tA_A0wCiPK2m-zn5RoGpBxv_g-4,2228
-rgwfuncs-0.0.59.dist-info/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
-rgwfuncs-0.0.59.dist-info/METADATA,sha256=h6wuBkH2hs3T4wdMCa8ACuhP3xUrUKU3iSZ7Hfg0RoU,58951
-rgwfuncs-0.0.59.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-rgwfuncs-0.0.59.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.59.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.59.dist-info/RECORD,,
+rgwfuncs-0.0.60.dist-info/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
+rgwfuncs-0.0.60.dist-info/METADATA,sha256=JareUKefKcxdm0rXKzudN9zjw9ljII5o3Llx7o1JrcA,58951
+rgwfuncs-0.0.60.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+rgwfuncs-0.0.60.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.60.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.60.dist-info/RECORD,,