dragon-ml-toolbox 4.3.0__tar.gz → 4.4.0__tar.gz

{dragon_ml_toolbox-4.3.0/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: 4.3.0
+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-4.3.0 → 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: 4.3.0
+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-4.3.0 → 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-4.3.0 → 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-4.3.0 → dragon_ml_toolbox-4.4.0}/ml_tools/data_exploration.py

@@ -126,7 +126,7 @@ 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:
         # validate targets
-        valid_targets = [target for target in targets if target in df_clean.columns]
+        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.")
@@ -134,10 +134,10 @@ def drop_rows_with_missing_data(df: pd.DataFrame, targets: Optional[list[str]],
         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
@@ -238,8 +238,9 @@ def split_features_targets(df: pd.DataFrame, targets: list[str]):
         - Shape of the features dataframe.
         - Shape of the targets dataframe.
     """
-    df_targets = df[targets]
-    df_features = df.drop(columns=targets)
+    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
 
@@ -644,5 +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-4.3.0 → dragon_ml_toolbox-4.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "4.3.0"
+version = "4.4.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }