dragon-ml-toolbox 3.0.0__py3-none-any.whl → 3.1.0__py3-none-any.whl

{dragon_ml_toolbox-3.0.0.dist-info → dragon_ml_toolbox-3.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.0.0
+Version: 3.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-3.0.0.dist-info → dragon_ml_toolbox-3.1.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-3.0.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-3.0.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
-ml_tools/ETL_engineering.py,sha256=SRiloWhSpopS4ay8mzUu0H4e9-37Ox_jDHzODqsQ8pc,31642
+dragon_ml_toolbox-3.1.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-3.1.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
+ml_tools/ETL_engineering.py,sha256=qxLbw8Vc0lOHUJm5ou280Tvw3oh_G1UHonxfa7nu_4Q,33008
 ml_tools/GUI_tools.py,sha256=uFx6zIrQZzDPSTtOSHz8ptz-fxZiQz-lXHcrqwuYV_E,20385
 ml_tools/MICE_imputation.py,sha256=ed-YeQkEAeHxTNkWIHs09T4YeYNF0aqAnrUTcdIEp9E,11372
 ml_tools/ML_callbacks.py,sha256=gHZk-lyzAax6iEtG26zHuoobdAZCFJ6BmI6pWoXkOrw,13189
@@ -13,13 +13,13 @@ ml_tools/VIF_factor.py,sha256=5GVAldH69Vkei3WRUZN1uPBMzGoOOeEOA-bgmZXbbUw,10301
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
 ml_tools/_pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
-ml_tools/data_exploration.py,sha256=Fzbz_DKZ7F2e3-JbahLqKr3aP6lt9aCK9rNOHvR7nlA,23665
+ml_tools/data_exploration.py,sha256=bOcCoQLeDPFJ7nB5Fsi16lzB22cG-c-mxObMsTetgS4,23655
 ml_tools/datasetmaster.py,sha256=N-uwfzWnl_qnoAqjbfS98I1pVNra5u6rhKLdWbFIReA,30122
 ml_tools/ensemble_learning.py,sha256=PPtBBLgLvaYOdY-MlcjXuxWWXf3JQavLNEysFgzjc_s,37470
 ml_tools/handle_excel.py,sha256=lwds7rDLlGSCWiWGI7xNg-Z7kxAepogp0lstSFa0590,12949
 ml_tools/logger.py,sha256=jC4Q2OqmDm8ZO9VpuZqBSWdXryqaJvLscqVJ6caNMOk,6009
 ml_tools/utilities.py,sha256=opNR-ACH6BnLkWAKcb19ef5tFxfx22TI6E2o0RYwiGA,21021
-dragon_ml_toolbox-3.0.0.dist-info/METADATA,sha256=nmhUu0bwN4z1letePaDzGIQlmDUaBQ32esqGB-OasU4,3273
-dragon_ml_toolbox-3.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-3.0.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-3.0.0.dist-info/RECORD,,
+dragon_ml_toolbox-3.1.0.dist-info/METADATA,sha256=yGk-slwRhPF23NxfVG0vR0NeIQbo_mJ-_ZEIomBLvrQ,3273
+dragon_ml_toolbox-3.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-3.1.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-3.1.0.dist-info/RECORD,,

ml_tools/ETL_engineering.py

@@ -25,18 +25,26 @@ __all__ = [
 
 class ColumnCleaner:
     """
-    Cleans and standardizes a single pandas Series based on a dictionary of regex-to-value replacement rules.
+    Cleans and standardizes a pandas Series by applying regex-to-replacement rules.
+    Supports sub-string replacements and case-insensitivity.
+    
+    Notes:
+    - Write separate, specific rules for each case. Don't combine patterns with an "OR".
+    - Define rules from most specific to more general to create a fallback system.
+    - Beware of chain replacements (rules matching strings that have already been changed by a previous rule).
     
     Args:
         rules (Dict[str, str]):
-            A dictionary where each key is a regular expression pattern and
-            each value is the standardized string to replace matches with.
+            A dictionary of regex patterns to replacement strings. Can use
+            backreferences in the replacement statement (e.g., r'\\1 \\2 \\3 \\4 \\5') for captured groups.
+        case_insensitive (bool):
+            If True, regex matching ignores case.
     """
-    def __init__(self, rules: Dict[str, str]):
+    def __init__(self, rules: Dict[str, str], case_insensitive: bool = True):
         if not isinstance(rules, dict):
             raise TypeError("The 'rules' argument must be a dictionary.")
 
-        # Validate that all keys are valid regular expressions
+        # Validate regex patterns
         for pattern in rules.keys():
             try:
                 re.compile(pattern)
@@ -44,32 +52,52 @@ class ColumnCleaner:
                 raise ValueError(f"Invalid regex pattern '{pattern}': {e}") from e
 
         self.rules = rules
+        self.case_insensitive = case_insensitive
 
     def clean(self, series: pd.Series) -> pd.Series:
         """
-        Applies the standardization rules to the provided Series (requires string data).
+        Applies the standardization rules sequentially to the provided Series.
         
-        Non-matching values are kept as they are.
-
         Args:
             series (pd.Series): The pandas Series to clean.
 
         Returns:
-            pd.Series: A new Series with the values cleaned and standardized.
+            pd.Series: A new Series with the regex replacements applied.
         """
-        return series.astype(str).replace(self.rules, regex=True)
+        cleaned_series = series.astype(str)
+        
+        # Set the regex flags based on the case_insensitive setting
+        flags = re.IGNORECASE if self.case_insensitive else 0
+        
+        # Sequentially apply each regex rule
+        for pattern, replacement in self.rules.items():
+            cleaned_series = cleaned_series.str.replace(
+                pattern, 
+                replacement, 
+                regex=True,
+                flags=flags
+            )
+            
+        return cleaned_series
 
 
 class DataFrameCleaner:
     """
     Orchestrates the cleaning of multiple columns in a pandas DataFrame using a nested dictionary of rules and `ColumnCleaner` objects.
+    
+    Chosen case-sensitivity is applied to all columns.
+    
+    Notes:
+    - Write separate, specific rules for each case. Don't combine patterns with an "OR".
+    - Define rules from most specific to more general to create a fallback system.
+    - Beware of chain replacements (rules matching strings that have already been changed by a previous rule).
 
     Args:
         rules (Dict[str, Dict[str, str]]):
             A nested dictionary where each top-level key is a column name,
             and its value is a dictionary of regex rules for that column, as expected by `ColumnCleaner`.
     """
-    def __init__(self, rules: Dict[str, Dict[str, str]]):
+    def __init__(self, rules: Dict[str, Dict[str, str]], case_insensitive: bool = True):
         if not isinstance(rules, dict):
             raise TypeError("The 'rules' argument must be a nested dictionary.")
         
@@ -81,6 +109,7 @@ class DataFrameCleaner:
                 )
         
         self.rules = rules
+        self.case_insensitive = case_insensitive
 
     def clean(self, df: pd.DataFrame) -> pd.DataFrame:
         """
@@ -109,7 +138,7 @@ class DataFrameCleaner:
         
         for column_name, column_rules in self.rules.items():
             # Create and apply the specific cleaner for the column
-            cleaner = ColumnCleaner(rules=column_rules)
+            cleaner = ColumnCleaner(rules=column_rules, case_insensitive=self.case_insensitive)
             df_cleaned[column_name] = cleaner.clean(df_cleaned[column_name])
             
         return df_cleaned

ml_tools/data_exploration.py

@@ -587,14 +587,14 @@ def standardize_percentages(
     Standardizes numeric columns containing mixed-format percentages.
 
     This function cleans columns where percentages might be entered as whole
-    numbers (e.g., 55) or as proportions (e.g., 0.55). It assumes values
+    numbers (55) and as proportions (0.55). It assumes values
     between 0 and 1 are proportions and multiplies them by 100.
 
     Args:
         df (pd.Dataframe): The input pandas DataFrame.
         columns (list[str]): A list of column names to standardize.
         treat_one_as_proportion (bool):
-            - If True (default): The value `1` is treated as a proportion and converted to `100`.
+            - If True (default): The value `1` is treated as a proportion and converted to `100%`.
             - If False: The value `1` is treated as `1%`.
         round_digits (int): The number of decimal places to round the final result to.