rgwfuncs 0.0.91__py3-none-any.whl → 0.0.93__py3-none-any.whl

rgwfuncs/df_lib.py

@@ -911,7 +911,6 @@ def send_dataframe_via_telegram(
         else:
             raise ValueError("Config must be either a path string or a dictionary")
 
-
     config = get_config(config)
 
     bot_config = next(
@@ -1232,17 +1231,13 @@ def order_columns(df: pd.DataFrame, column_order_str: str) -> pd.DataFrame:
     return df[new_order]
 
 
-def append_ranged_classification_column(
-        df: pd.DataFrame,
-        ranges: str,
-        target_col: str,
-        new_col_name: str) -> pd.DataFrame:
+def append_ranged_classification_column(df: pd.DataFrame, ranges: List[Union[int, float]], target_col: str, new_col_name: str) -> pd.DataFrame:
     """
     Append a ranged classification column to the DataFrame.
 
     Parameters:
         df: The DataFrame to modify.
-        ranges: A string representation of numeric ranges separated by commas.
+        ranges: A list of numeric range boundaries (integers or floats, last bin extends to infinity).
         target_col: The column to analyze.
         new_col_name: The name of the new classification column.
 
@@ -1259,52 +1254,55 @@ def append_ranged_classification_column(
         else:
             return str(int(number)).zfill(integer_length)
 
-    range_list = ranges.split(',')
-    has_decimals = any('.' in r for r in range_list)
+    # Check if any numbers in ranges are decimals
+    has_decimals = any(isinstance(r, float) and r % 1 != 0 for r in ranges)
 
     if has_decimals:
-        range_list = [float(r) for r in range_list]
+        range_list = [float(r) for r in ranges] + [float('inf')]
 
         max_decimal_length = max(
-            len(str(r).split('.')[1])
-            for r in range_list
-            if '.' in str(r)
+            len(str(r).split('.')[1]) if isinstance(r, float) and r % 1 != 0 else 0
+            for r in ranges
         )
 
         max_integer_length = max(
             len(str(int(float(r))))
-            for r in range_list
+            for r in ranges
         )
 
         labels = []
-
-        for i in range(len(range_list) - 1):
+        for i in range(len(ranges)):
             start = pad_number(
-                range_list[i],
-                max_integer_length,
-                max_decimal_length,
-                decimal=True
-            )
-
-            end = pad_number(
-                range_list[i + 1],
+                ranges[i],
                 max_integer_length,
                 max_decimal_length,
                 decimal=True
             )
-
-            label = f"{start} to {end}"
+            if i == len(ranges) - 1:
+                label = f"{start}+"
+            else:
+                end = pad_number(
+                    ranges[i + 1],
+                    max_integer_length,
+                    max_decimal_length,
+                    decimal=True
+                )
+                label = f"{start} - {end}"
             labels.append(label)
 
     else:
-        range_list = [int(r) for r in range_list]
+        range_list = [int(r) for r in ranges] + [float('inf')]
+        max_integer_length = max(len(str(int(r))) for r in ranges)
 
-        max_integer_length = max(
-            len(str(r))
-            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 = []
+        for i in range(len(ranges)):
+            start = pad_number(ranges[i], max_integer_length)
+            if i == len(ranges) - 1:
+                label = f"{start}+"
+            else:
+                end = pad_number(ranges[i + 1], max_integer_length)
+                label = f"{start} - {end}"
+            labels.append(label)
 
     # Ensure the target column is numeric
     df[target_col] = pd.to_numeric(df[target_col], errors='coerce')
@@ -1313,22 +1311,19 @@ def append_ranged_classification_column(
         bins=range_list,
         labels=labels,
         right=False,
-        include_lowest=True)
+        include_lowest=True
+    )
 
     return df
 
 
-def append_percentile_classification_column(
-        df: pd.DataFrame,
-        percentiles: str,
-        target_col: str,
-        new_col_name: str) -> pd.DataFrame:
+def append_percentile_classification_column(df: pd.DataFrame, percentiles: List[Union[int, float]], target_col: str, new_col_name: str) -> pd.DataFrame:
     """
     Append a percentile classification column to the DataFrame.
 
     Parameters:
         df: The DataFrame to modify.
-        percentiles: A string representation of percentile values separated by commas.
+        percentiles: A list of percentile values (0-100, integers or floats).
         target_col: The column to analyze.
         new_col_name: The name of the new classification column.
 
@@ -1345,40 +1340,42 @@ def append_percentile_classification_column(
         else:
             return str(int(number)).zfill(integer_length)
 
-    percentiles_list = percentiles.split(',')
-    has_decimals = any('.' in p for p in percentiles_list)
+    # Check if any numbers in percentiles are decimals
+    has_decimals = any(isinstance(p, float) and p % 1 != 0 for p in percentiles)
 
     if has_decimals:
-        percentiles_list = [float(p) for p in percentiles_list]
-        max_decimal_length = max(len(str(p).split('.')[1]) for p in percentiles_list if '.' in str(p))
-        max_integer_length = max(len(str(int(float(p)))) for p in percentiles_list)
+        percentiles_list = [float(p) for p in percentiles]
+        max_decimal_length = max(
+            len(str(p).split('.')[1]) if isinstance(p, float) and p % 1 != 0 else 0
+            for p in percentiles
+        )
+        max_integer_length = max(len(str(int(float(p)))) for p in percentiles)
 
         labels = []
-
         for i in range(len(percentiles_list) - 1):
             start = pad_number(
                 percentiles_list[i],
                 max_integer_length,
                 max_decimal_length,
-                decimal=True)
+                decimal=True
+            )
             end = pad_number(
-                percentiles_list[i + 1], max_integer_length, max_decimal_length, decimal=True)
-
-            label = f"{start} to {end}"
+                percentiles_list[i + 1],
+                max_integer_length,
+                max_decimal_length,
+                decimal=True
+            )
+            label = f"{start} - {end}"
             labels.append(label)
     else:
-        percentiles_list = [int(p) for p in percentiles_list]
-
+        percentiles_list = [int(p) for p in percentiles]
         max_integer_length = max(len(str(p)) for p in percentiles_list)
 
         labels = []
-
         for i in range(len(percentiles_list) - 1):
             start = pad_number(percentiles_list[i], max_integer_length)
-
             end = pad_number(percentiles_list[i + 1], max_integer_length)
-
-            label = f"{start} to {end}"
+            label = f"{start} - {end}"
             labels.append(label)
 
     # Ensure the target column is numeric
@@ -1389,22 +1386,19 @@ def append_percentile_classification_column(
         df[target_col],
         bins=quantiles,
         labels=labels,
-        include_lowest=True)
+        include_lowest=True
+    )
 
     return df
 
 
-def append_ranged_date_classification_column(
-        df: pd.DataFrame,
-        date_ranges: str,
-        target_col: str,
-        new_col_name: str) -> pd.DataFrame:
+def append_ranged_date_classification_column(df: pd.DataFrame, date_ranges: list[str], target_col: str, new_col_name: str) -> pd.DataFrame:
     """
     Append a ranged date classification column to the DataFrame.
 
     Parameters:
         df: The DataFrame to modify.
-        date_ranges: A string representation of date ranges separated by commas.
+        date_ranges: A list of date strings in a format pandas can parse (e.g., ['2020-01-01', '2020-06-30', '2020-12-31']).
         target_col: The date column to analyze.
         new_col_name: The name of the new date classification column.
 
@@ -1412,28 +1406,26 @@ def append_ranged_date_classification_column(
         A new DataFrame with the date classification column appended.
     """
 
-    date_list = [pd.to_datetime(date) for date in date_ranges.split(',')]
+    date_list = [pd.to_datetime(date) for date in date_ranges]
 
     labels = []
-
     for i in range(len(date_list) - 1):
         start_date = date_list[i].strftime('%Y-%m-%d')
         end_date = date_list[i + 1].strftime('%Y-%m-%d')
-        label = f"{start_date} to {end_date}"
+        label = f"{start_date} - {end_date}"
         labels.append(label)
 
     df[new_col_name] = pd.cut(
         pd.to_datetime(df[target_col]),
         bins=date_list,
         labels=labels,
-        right=False)
+        right=False
+    )
 
     return df
 
 
-def rename_columns(df: pd.DataFrame,
-                   rename_pairs: Dict[str,
-                                      str]) -> pd.DataFrame:
+def rename_columns(df: pd.DataFrame, rename_pairs: Dict[str, str]) -> pd.DataFrame:
     """
     Rename columns in the DataFrame.
 

rgwfuncs/str_lib.py

@@ -45,8 +45,6 @@ def send_telegram_message(preset_name: str, message: str, config: Optional[Union
         else:
             raise ValueError("Config must be either a path string or a dictionary")
 
-
-
     def get_telegram_preset(config: dict, preset_name: str) -> dict:
         """Get the Telegram preset configuration."""
         presets = config.get("telegram_bot_presets", [])

{rgwfuncs-0.0.91.dist-info → rgwfuncs-0.0.93.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rgwfuncs
-Version: 0.0.91
+Version: 0.0.93
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson
@@ -1249,7 +1249,7 @@ Append a ranged classification column to the DataFrame.
 
 • Parameters:
   - df (pd.DataFrame)
-  - ranges (str): Ranges separated by commas (e.g., "0-10,11-20,21-30").
+  - ranges (list[int | float]): List of numeric range boundaries (e.g., [0, 10, 20, 30]), last bin extends to infinity.
   - `target_col` (str): The column to classify.
   - `new_col_name` (str): Name of the new classification column.
 
@@ -1257,14 +1257,14 @@ Append a ranged classification column to the DataFrame.
   - pd.DataFrame
 
 • Example:
-    
+
     from rgwfuncs import append_ranged_classification_column
     import pandas as pd
 
     df = pd.DataFrame({'Scores': [5, 12, 25]})
-    df_classified = append_ranged_classification_column(df, '0-10,11-20,21-30', 'Scores', 'ScoreRange')
+    df_classified = append_ranged_classification_column(df, [0, 10, 20, 30], 'Scores', 'ScoreRange')
     print(df_classified)
-    
+
 
 --------------------------------------------------------------------------------
 
@@ -1273,7 +1273,7 @@ Append a percentile classification column to the DataFrame.
 
 • Parameters:
   - df (pd.DataFrame)
-  - percentiles (str): Percentile values separated by commas (e.g., "25,50,75").
+  - percentiles (list[int | float]): List of percentile values (0-100, e.g., [25, 50, 75]).
   - `target_col` (str)
   - `new_col_name` (str)
 
@@ -1281,14 +1281,14 @@ Append a percentile classification column to the DataFrame.
   - pd.DataFrame
 
 • Example:
-    
+
     from rgwfuncs import append_percentile_classification_column
     import pandas as pd
 
     df = pd.DataFrame({'Values': [10, 20, 30, 40, 50]})
-    df_classified = append_percentile_classification_column(df, '25,50,75', 'Values', 'ValuePercentile')
+    df_classified = append_percentile_classification_column(df, [25, 50, 75], 'Values', 'ValuePercentile')
     print(df_classified)
-    
+
 
 --------------------------------------------------------------------------------
 
@@ -1297,7 +1297,7 @@ Append a ranged date classification column to the DataFrame.
 
 • Parameters:
   - df (pd.DataFrame)
-  - `date_ranges` (str): Date ranges separated by commas, e.g., `2020-01-01_2020-06-30,2020-07-01_2020-12-31`
+  - `date_ranges` (list[str]): List of date strings in a format pandas can parse (e.g., ['2020-01-01', '2020-06-30', '2020-12-31']).
   - `target_col` (str)
   - `new_col_name` (str)
 
@@ -1305,19 +1305,18 @@ Append a ranged date classification column to the DataFrame.
   - pd.DataFrame
 
 • Example:
-    
+
     from rgwfuncs import append_ranged_date_classification_column
     import pandas as pd
 
-    df = pd.DataFrame({'EventDate': pd.to_datetime(['2020-03-15','2020-08-10'])})
+    df = pd.DataFrame({'EventDate': pd.to_datetime(['2020-03-15', '2020-08-10'])})
     df_classified = append_ranged_date_classification_column(
         df,
-        '2020-01-01_2020-06-30,2020-07-01_2020-12-31',
+        ['2020-01-01', '2020-06-30', '2020-12-31'],
         'EventDate',
         'DateRange'
     )
     print(df_classified)
-    
 
 --------------------------------------------------------------------------------
 

rgwfuncs-0.0.93.dist-info/RECORD

@@ -0,0 +1,12 @@
+rgwfuncs/__init__.py,sha256=LSn54Tlyskcb6Wab_wUpPLB6UGMe5LdrB3GU88mDEbU,1712
+rgwfuncs/algebra_lib.py,sha256=rKFITfpWfgdBswnbMUuS41XgndEt-jUVz2ObO_ik7eM,42234
+rgwfuncs/df_lib.py,sha256=LHG6E-umLGVdDRWjziFrRb_YSlTronHv2QwEFBrTAt4,75528
+rgwfuncs/docs_lib.py,sha256=i63NzX-V8cGhikYdtkRGAEe2VcuwpXxDUyTRa9xI7l8,1972
+rgwfuncs/interactive_shell_lib.py,sha256=YN0ZnM5twIsOeDKuOQ9ZGURCvvBX0RZjM4a1vO1C3E8,4281
+rgwfuncs/str_lib.py,sha256=hE0VfP6rhQpczsKyCZvH3G1aMRwngKnkW3NTYCEc0Po,3208
+rgwfuncs-0.0.93.dist-info/licenses/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
+rgwfuncs-0.0.93.dist-info/METADATA,sha256=eEiNMD4k_feeK6mxhrVqlvDTRONwsPosvR-pj9hYlAI,61443
+rgwfuncs-0.0.93.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+rgwfuncs-0.0.93.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.93.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.93.dist-info/RECORD,,

{rgwfuncs-0.0.91.dist-info → rgwfuncs-0.0.93.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.0.2)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

rgwfuncs-0.0.91.dist-info/RECORD

@@ -1,12 +0,0 @@
-rgwfuncs/__init__.py,sha256=LSn54Tlyskcb6Wab_wUpPLB6UGMe5LdrB3GU88mDEbU,1712
-rgwfuncs/algebra_lib.py,sha256=rKFITfpWfgdBswnbMUuS41XgndEt-jUVz2ObO_ik7eM,42234
-rgwfuncs/df_lib.py,sha256=coAmZ2RyWvovorNekQnLW5cUIZyY-h6s88YUm0ytFAw,75107
-rgwfuncs/docs_lib.py,sha256=i63NzX-V8cGhikYdtkRGAEe2VcuwpXxDUyTRa9xI7l8,1972
-rgwfuncs/interactive_shell_lib.py,sha256=YN0ZnM5twIsOeDKuOQ9ZGURCvvBX0RZjM4a1vO1C3E8,4281
-rgwfuncs/str_lib.py,sha256=-dcJt-jE0YG-XwHcNslCM_Gp-L0Ho0zYFPxjrxepzzA,3210
-rgwfuncs-0.0.91.dist-info/licenses/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
-rgwfuncs-0.0.91.dist-info/METADATA,sha256=BVQ4dPy_oI5jTtqwEBfj96OGqwIlOy8Ib57Je7Q6Tuk,61390
-rgwfuncs-0.0.91.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
-rgwfuncs-0.0.91.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.91.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.91.dist-info/RECORD,,