dragon-ml-toolbox 4.2.2__tar.gz → 4.4.0__tar.gz

{dragon_ml_toolbox-4.2.2/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-4.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.2.2
+Version: 4.4.0
 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-4.2.2 → dragon_ml_toolbox-4.4.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.2.2
+Version: 4.4.0
 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-4.2.2 → dragon_ml_toolbox-4.4.0}/ml_tools/ETL_engineering.py

@@ -569,7 +569,7 @@ class NumberExtractor:
         self,
         regex_pattern: str = r"(\d+\.?\d*)",
         dtype: Literal["float", "int"] = "float",
-        round_digits: Optional[int] = None,
+        round_digits: Optional[int] = 2,
     ):
         # --- Validation ---
         if not isinstance(regex_pattern, str):

{dragon_ml_toolbox-4.2.2 → dragon_ml_toolbox-4.4.0}/ml_tools/custom_logger.py

@@ -1,9 +1,9 @@
 from pathlib import Path
 from datetime import datetime
 from typing import Union, List, Dict, Any
-import pandas as pd
 import traceback
 import json
+import csv
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
@@ -18,7 +18,6 @@ def custom_logger(
     data: Union[
         List[Any],
         Dict[Any, Any],
-        pd.DataFrame,
         str,
         BaseException
     ],
@@ -75,7 +74,7 @@ def custom_logger(
             _log_exception_to_log(data, base_path.with_suffix(".log"))
 
         else:
-            raise ValueError("Unsupported data type. Must be list, dict, DataFrame, str, or BaseException.")
+            raise ValueError("Unsupported data type. Must be list, dict, str, or BaseException.")
 
         _LOGGER.info(f"🗄️ Log saved to: '{base_path}'")
 
@@ -106,8 +105,19 @@ def _log_dict_to_csv(data: Dict[Any, List[Any]], path: Path) -> None:
         padded_value = value + [None] * (max_length - len(value))
         sanitized_dict[sanitized_key] = padded_value
 
-    df = pd.DataFrame(sanitized_dict)
-    df.to_csv(path, index=False)
+    # The `newline=''` argument is important to prevent extra blank rows
+    with open(path, 'w', newline='', encoding='utf-8') as csv_file:
+        writer = csv.writer(csv_file)
+
+        # 1. Write the header row from the sanitized dictionary keys
+        header = list(sanitized_dict.keys())
+        writer.writerow(header)
+
+        # 2. Transpose columns to rows and write them
+        # zip(*sanitized_dict.values()) elegantly converts the column data
+        # (lists in the dict) into row-by-row tuples.
+        rows_to_write = zip(*sanitized_dict.values())
+        writer.writerows(rows_to_write)
 
 
 def _log_string_to_log(data: str, path: Path) -> None:

{dragon_ml_toolbox-4.2.2 → dragon_ml_toolbox-4.4.0}/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", 
@@ -125,17 +125,19 @@ 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 = _validate_columns(df_clean, targets)
+        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]
         else:
             print("✅ No rows with all targets missing.")
     else:
-        targets = []
+        valid_targets = []
 
     # Stage 2: Drop rows based on feature column missing values
-    feature_cols = [col for col in df_clean.columns if col not in targets]
+    feature_cols = [col for col in df_clean.columns if col not in valid_targets]
     if feature_cols:
         feature_na_frac = df_clean[feature_cols].isnull().mean(axis=1)
         rows_to_drop = feature_na_frac[feature_na_frac > threshold].index
@@ -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 +220,31 @@ 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.
+    """
+    valid_targets = _validate_columns(df, targets)
+    df_targets = df[valid_targets]
+    df_features = df.drop(columns=valid_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.
@@ -631,5 +645,10 @@ def standardize_percentages(
     return df_copy
 
 
+def _validate_columns(df: pd.DataFrame, columns: list[str]):
+    valid_columns = [column for column in columns if column in df.columns]
+    return valid_columns
+
+
 def info():
     _script_info(__all__)

{dragon_ml_toolbox-4.2.2 → dragon_ml_toolbox-4.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "4.2.2"
+version = "4.4.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }