dragon-ml-toolbox 4.3.0__py3-none-any.whl → 4.5.0__py3-none-any.whl

{dragon_ml_toolbox-4.3.0.dist-info → dragon_ml_toolbox-4.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.3.0
+Version: 4.5.0
 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.dist-info → dragon_ml_toolbox-4.5.0.dist-info}/RECORD

@@ -1,22 +1,22 @@
-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
+dragon_ml_toolbox-4.5.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-4.5.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+ml_tools/ETL_engineering.py,sha256=4wwZXi9_U7xfCY70jGBaKniOeZ0m75ppxWpQBd_DmLc,39369
 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
 ml_tools/ML_evaluation.py,sha256=4dVqe6JF1Ukmk1sAcY8E5EG1oB1_oy2HXE5OT-pZwCs,10273
 ml_tools/ML_inference.py,sha256=Fh-X2UQn3AznWBjf-7iPSxwE-EzkGQm1VEIRUAkURmE,5336
 ml_tools/ML_trainer.py,sha256=dJjMfCEEM07Txy9KEH-2srZ3CZUa4lFWTJhpNWQ4Ndk,14974
-ml_tools/PSO_optimization.py,sha256=xtnPute5pkS_w-VvqOBgRLgke09mjfacGC2m9DiipHE,27626
+ml_tools/PSO_optimization.py,sha256=9bplCNOSe2Ozcz5yQRkbih7geuDO9UJ6dJTMSJJ8zVk,27965
 ml_tools/RNN_forecast.py,sha256=2CyjBLSYYc3xLHxwLXUmP5Qv8AmV1OB_EndETNX1IBk,1956
 ml_tools/SQL.py,sha256=9zzS6AFEJM9aj6nE31hDe8S9TqLonk-J1amwZoiHNbk,10468
 ml_tools/VIF_factor.py,sha256=2nUMupfUoogf8o6ghoFZk_OwWhFXU0R3C9Gj0HOlI14,10415
-ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 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=T4nO9YSDGvrpom7JELtoQTyg7XTEmvQz-jG0KKxqTRk,23467
+ml_tools/custom_logger.py,sha256=njM_0XPbQ1S-x5LeSQAaTo2if-XVOR_pQSGg4EDeiTU,4603
+ml_tools/data_exploration.py,sha256=qc_Oolxco2x9IhlYu5zPIuVBGiBw65HnypuGm8cQOOM,23677
 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-4.3.0.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,,
+dragon_ml_toolbox-4.5.0.dist-info/METADATA,sha256=PzpYHROSr85CBbNnCcS-XInzpOFhAyXbPZ5YkLaYbps,6572
+dragon_ml_toolbox-4.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-4.5.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-4.5.0.dist-info/RECORD,,

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):

ml_tools/PSO_optimization.py

@@ -2,7 +2,7 @@ import numpy as np
 from pathlib import Path
 import xgboost as xgb
 import lightgbm as lgb
-from typing import Literal, Union, Tuple, Dict, Optional
+from typing import Literal, Union, Tuple, Dict, Optional, Any
 import pandas as pd
 from copy import deepcopy
 from .utilities import (
@@ -25,6 +25,7 @@ from contextlib import nullcontext
 __all__ = [
     "ObjectiveFunction",
     "multiple_objective_functions_from_dir",
+    "parse_lower_upper_bounds",
     "run_pso",
     "plot_optimal_feature_distributions"
 ]
@@ -169,6 +170,18 @@ def multiple_objective_functions_from_dir(directory: Union[str,Path], add_noise:
     return objective_functions, objective_function_names
 
 
+def parse_lower_upper_bounds(source: dict[str,tuple[Any,Any]]):
+    """
+    Parse lower and upper boundaries, returning 2 lists:
+    
+    `lower_bounds`, `upper_bounds`
+    """
+    lower = [low[0] for low in source.values()]
+    upper = [up[1] for up in source.values()]
+    
+    return lower, upper
+
+
 def _set_boundaries(lower_boundaries: list[float], upper_boundaries: list[float]):
     assert len(lower_boundaries) == len(upper_boundaries), "Lower and upper boundaries must have the same length."
     assert len(lower_boundaries) >= 1, "At least one boundary pair is required."

ml_tools/__init__.py

@@ -0,0 +1 @@
+from .custom_logger import custom_logger

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:

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
 
@@ -347,7 +348,7 @@ def plot_correlation_heatmap(df: pd.DataFrame,
         full_path = save_path / plot_title
         
         plt.savefig(full_path, bbox_inches="tight", format='svg')
-        print(f"Saved correlation heatmap: '{plot_title}.svg'")
+        print(f"Saved correlation heatmap: '{plot_title}'")
     
     plt.show()
     plt.close()
@@ -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__)