dragon-ml-toolbox 4.2.1__py3-none-any.whl → 4.3.0__py3-none-any.whl

{dragon_ml_toolbox-4.2.1.dist-info → dragon_ml_toolbox-4.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.2.1
+Version: 4.3.0
 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-4.2.1.dist-info → dragon_ml_toolbox-4.3.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-4.2.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-4.2.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
-ml_tools/ETL_engineering.py,sha256=rlu0bUekdKREcTR0x1jn_TSEqhxgfq3QU71hy6ZyaD8,39503
+dragon_ml_toolbox-4.3.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-4.3.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+ml_tools/ETL_engineering.py,sha256=P7HN_e3vfmrOqDDK-IenyRSFQPr0N3V9e2gN75QFVWs,39372
 ml_tools/GUI_tools.py,sha256=n4ZZ5kEjwK5rkOCFJE41HeLFfjhpJVLUSzk9Kd9Kr_0,45410
 ml_tools/MICE_imputation.py,sha256=b6ZTs8RedXFifOpuMCzr68xM16mCBVh1Ua6kcGfiVtg,11462
 ml_tools/ML_callbacks.py,sha256=0a-Rbr0Xp_B1FNopOKBBmuJ4MqazS5JgDiT7wx1dHvE,13161
@@ -16,7 +16,7 @@ ml_tools/_logger.py,sha256=TpgYguxO-CWYqqgLW0tqFjtwZ58PE_W2OCfWNGZr0n0,1175
 ml_tools/_pytorch_models.py,sha256=ewPPsTHgmRPzMMWwObZOdH1vxm2Ij2VWZP38NC6zSH4,10135
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=a3ywSCQT7j5ypR-usnKh2l861d_aVJ93ZRVqxrHsBBw,4112
-ml_tools/data_exploration.py,sha256=rJhvxUqVbEuB_7HG-PfLH3vaA7hrZEtbVHg9QO9VS4A,22837
+ml_tools/data_exploration.py,sha256=T4nO9YSDGvrpom7JELtoQTyg7XTEmvQz-jG0KKxqTRk,23467
 ml_tools/datasetmaster.py,sha256=_tNC2v98eCQGr3nMW_EFs83TRgRme8Uc7ttg1vosmQU,30106
 ml_tools/ensemble_inference.py,sha256=0SNX3YAz5bpvtwYmqEwqyWeIJP2Pb-v-bemENRSO7qg,9426
 ml_tools/ensemble_learning.py,sha256=Zi1oy6G2FWnTI5hBwjlexwF3JKALFS2FN6F8HAlVi_s,35391
@@ -24,7 +24,7 @@ ml_tools/handle_excel.py,sha256=J9iwIqMZemoxK49J5osSwp9Ge0h9YTKyYGbOm53hcno,1300
 ml_tools/keys.py,sha256=kK9UF-hek2VcPGFILCKl5geoN6flmMOu7IzhdEA6z5Y,1068
 ml_tools/path_manager.py,sha256=Z8e7w3MPqQaN8xmTnKuXZS6CIW59BFwwqGhGc00sdp4,13692
 ml_tools/utilities.py,sha256=mz-M351DzxWxnYVcLX-7ZQ6c-RGoCV9g4VTS9Qif2Es,18348
-dragon_ml_toolbox-4.2.1.dist-info/METADATA,sha256=mzW1BLOxrCKZAoZgqzYRcNhHpO4fTNxDGvUwuF5wG88,6572
-dragon_ml_toolbox-4.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-4.2.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-4.2.1.dist-info/RECORD,,
+dragon_ml_toolbox-4.3.0.dist-info/METADATA,sha256=7aZO_5P8SDx4tPFTtb3MTAaRgf_vbcOEURaxpT3MGK8,6572
+dragon_ml_toolbox-4.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-4.3.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-4.3.0.dist-info/RECORD,,

ml_tools/ETL_engineering.py

@@ -3,6 +3,7 @@ import re
 from typing import Literal, Union, Optional, Any, Callable, List, Dict, Tuple
 from ._script_info import _script_info
 from ._logger import _LOGGER
+import warnings
 
 
 __all__ = [
@@ -50,7 +51,7 @@ class ColumnCleaner:
     ```python
     id_rules = {
         # Matches 'ID-12345' or 'ID 12345' and reformats to 'ID:12345'
-        r'ID[- ](\d+)': r'ID:$1'
+        r'ID[- ](\\d+)': r'ID:$1'
     }
 
     id_cleaner = ColumnCleaner(column_name='user_id', rules=id_rules)
@@ -700,26 +701,28 @@ class MultiNumberExtractor:
 
 class RatioCalculator:
     """
-    A transformer that parses a string ratio (e.g., "40:5" or "30/2") and computes the result of the division.
-
-    Args:
-        regex_pattern (str, optional):
-            The regex pattern to find the numerator and denominator. It MUST
-            contain exactly two capturing groups: the first for the
-            numerator and the second for the denominator. Defaults to a
-            pattern that handles common delimiters like ':' and '/'.
+    A transformer that parses a string ratio (e.g., "40:5" or "30/2") and
+    computes the result of the division. It gracefully handles strings that
+    do not match the pattern by returning null.
     """
     def __init__(
         self,
-        regex_pattern: str = r"(\d+\.?\d*)\s*[:/]\s*(\d+\.?\d*)"
+        # Default pattern includes the full-width colon '：'
+        regex_pattern: str = r"(\d+\.?\d*)\s*[:：/]\s*(\d+\.?\d*)"
     ):
-        # --- Validation ---
+        # --- Robust Validation ---
         try:
-            if re.compile(regex_pattern).groups != 2:
+            compiled_pattern = re.compile(regex_pattern)
+            if compiled_pattern.groups != 2:
                 raise ValueError(
-                    "regex_pattern must contain exactly two "
+                    "RatioCalculator regex_pattern must contain exactly two "
                     "capturing groups '(...)'."
                 )
+            if compiled_pattern.groupindex:
+                raise ValueError(
+                    "RatioCalculator must be initialized with unnamed capturing groups "
+                    "(e.g., '(\\d+)'), not named groups (e.g., '(?P<name>\\d+)')."
+                )
         except re.error as e:
             raise ValueError(f"Invalid regex pattern provided: {e}") from e
 
@@ -728,27 +731,20 @@ class RatioCalculator:
     def __call__(self, column: pl.Series) -> pl.Series:
         """
         Applies the ratio calculation logic to the input column.
-
-        Args:
-            column (pl.Series): The input Polars Series of ratio strings.
-
-        Returns:
-            pl.Series: A new Series of floats containing the division result.
-                       Returns null for invalid formats or division by zero.
+        This version uses .str.extract() for maximum stability.
         """
-        # .extract_groups returns a struct with a field for each capture group
-        # e.g., {"group_1": "40", "group_2": "5"}
-        groups = column.str.extract_groups(self.regex_pattern)
+        # Extract numerator (group 1) and denominator (group 2) separately.
+        numerator_expr = column.str.extract(self.regex_pattern, 1).cast(pl.Float64, strict=False)
+        denominator_expr = column.str.extract(self.regex_pattern, 2).cast(pl.Float64, strict=False)
 
-        # Extract numerator and denominator, casting to float
-        # strict=False ensures that non-matches become null
-        numerator = groups.struct.field("group_1").cast(pl.Float64, strict=False)
-        denominator = groups.struct.field("group_2").cast(pl.Float64, strict=False)
+        # Calculate the ratio, handling division by zero.
+        final_expr = pl.when(denominator_expr != 0).then(
+            numerator_expr / denominator_expr
+        ).otherwise(
+            None # Handles both null denominators and division by zero
+        )
 
-        # Safely perform division, returning null if denominator is 0
-        final_expr = pl.when(denominator != 0).then(numerator / denominator).otherwise(None)
-        
-        return pl.select(final_expr).to_series()
+        return pl.select(final_expr.round(4)).to_series()
 
 
 class CategoryMapper:

ml_tools/data_exploration.py

@@ -15,9 +15,9 @@ __all__ = [
     "summarize_dataframe",
     "drop_constant_columns",
     "drop_rows_with_missing_data",
-    "split_features_targets", 
     "show_null_columns",
     "drop_columns_with_missing_data",
+    "split_features_targets", 
     "split_continuous_binary", 
     "plot_correlation_heatmap", 
     "plot_value_distributions", 
@@ -125,7 +125,9 @@ def drop_rows_with_missing_data(df: pd.DataFrame, targets: Optional[list[str]],
 
     # Stage 1: Drop rows with all target columns missing
     if targets is not None:
-        target_na = df_clean[targets].isnull().all(axis=1)
+        # validate targets
+        valid_targets = [target for target in targets if target in df_clean.columns]
+        target_na = df_clean[valid_targets].isnull().all(axis=1)
         if target_na.any():
             print(f"🧹 Dropping {target_na.sum()} rows with all target columns missing.")
             df_clean = df_clean[~target_na]
@@ -150,30 +152,6 @@ def drop_rows_with_missing_data(df: pd.DataFrame, targets: Optional[list[str]],
     return df_clean
 
 
-def split_features_targets(df: pd.DataFrame, targets: list[str]):
-    """
-    Splits a DataFrame's columns into features and targets.
-
-    Args:
-        df (pd.DataFrame): Pandas DataFrame containing the dataset.
-        targets (list[str]): List of column names to be treated as target variables.
-
-    Returns:
-        tuple: A tuple containing:
-            - pd.DataFrame: Features dataframe.
-            - pd.DataFrame: Targets dataframe.
-
-    Prints:
-        - Shape of the original dataframe.
-        - Shape of the features dataframe.
-        - Shape of the targets dataframe.
-    """
-    df_targets = df[targets]
-    df_features = df.drop(columns=targets)
-    print(f"Original shape: {df.shape}\nFeatures shape: {df_features.shape}\nTargets shape: {df_targets.shape}")
-    return df_features, df_targets
-
-
 def show_null_columns(df: pd.DataFrame, round_digits: int = 2):
     """
     Displays a table of columns with missing values, showing both the count and
@@ -202,7 +180,7 @@ def show_null_columns(df: pd.DataFrame, round_digits: int = 2):
     return null_summary
 
 
-def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, show_nulls_after: bool = True) -> pd.DataFrame:
+def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, show_nulls_after: bool = True, skip_columns: Optional[List[str]]=None) -> pd.DataFrame:
     """
     Drops columns with more than `threshold` fraction of missing values.
 
@@ -210,11 +188,22 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, sho
         df (pd.DataFrame): The input DataFrame.
         threshold (float): Fraction of missing values above which columns are dropped.
         show_nulls_after (bool): Prints `show_null_columns` after dropping columns. 
+        skip_columns (list[str] | None): If given, these columns wont be included in the drop process. 
 
     Returns:
         pd.DataFrame: A new DataFrame without the dropped columns.
     """
-    missing_fraction = df.isnull().mean()
+    # If skip_columns is provided, create a list of columns to check.
+    # Otherwise, check all columns.
+    cols_to_check = df.columns
+    if skip_columns:
+        # Use set difference for efficient exclusion
+        cols_to_check = df.columns.difference(skip_columns)
+
+    # Calculate the missing fraction only on the columns to be checked
+    missing_fraction = df[cols_to_check].isnull().mean()
+    
+    
     cols_to_drop = missing_fraction[missing_fraction > threshold].index
 
     if len(cols_to_drop) > 0:
@@ -231,6 +220,30 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, sho
         return df
 
 
+def split_features_targets(df: pd.DataFrame, targets: list[str]):
+    """
+    Splits a DataFrame's columns into features and targets.
+
+    Args:
+        df (pd.DataFrame): Pandas DataFrame containing the dataset.
+        targets (list[str]): List of column names to be treated as target variables.
+
+    Returns:
+        tuple: A tuple containing:
+            - pd.DataFrame: Features dataframe.
+            - pd.DataFrame: Targets dataframe.
+
+    Prints:
+        - Shape of the original dataframe.
+        - Shape of the features dataframe.
+        - Shape of the targets dataframe.
+    """
+    df_targets = df[targets]
+    df_features = df.drop(columns=targets)
+    print(f"Original shape: {df.shape}\nFeatures shape: {df_features.shape}\nTargets shape: {df_targets.shape}")
+    return df_features, df_targets
+
+
 def split_continuous_binary(df: pd.DataFrame) -> Tuple[pd.DataFrame, pd.DataFrame]:
     """
     Split DataFrame into two DataFrames: one with continuous columns, one with binary columns.