dragon-ml-toolbox 12.13.0__py3-none-any.whl → 14.3.0__py3-none-any.whl

ml_tools/utilities.py

@@ -7,16 +7,19 @@ from typing import Literal, Union, Optional, Any, Iterator, Tuple, overload
 from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
 from ._script_info import _script_info
 from ._logger import _LOGGER
+from ._schema import FeatureSchema
 
 
 # Keep track of available tools
 __all__ = [
     "load_dataframe",
     "load_dataframe_greedy",
+    "load_dataframe_with_schema",
     "yield_dataframes_from_dir",
     "merge_dataframes",
     "save_dataframe_filename",
     "save_dataframe",
+    "save_dataframe_with_schema",
     "distribute_dataset_by_target",
     "train_dataset_orchestrator",
     "train_dataset_yielder"
@@ -96,6 +99,7 @@ def load_dataframe(
         elif kind == "polars":
             pl_kwargs: dict[str,Any]
             pl_kwargs = {}
+            pl_kwargs['null_values'] = ["", " "]
             if use_columns:
                 pl_kwargs['columns'] = use_columns
                 
@@ -173,6 +177,68 @@ def load_dataframe_greedy(directory: Union[str, Path],
     return df
 
 
+def load_dataframe_with_schema(
+    df_path: Union[str, Path], 
+    schema: "FeatureSchema",
+    all_strings: bool = False,
+) -> Tuple[pd.DataFrame, str]:
+    """
+    Loads a CSV file into a Pandas DataFrame, strictly validating its
+    feature columns against a FeatureSchema.
+
+    This function wraps `load_dataframe`. After loading, it validates
+    that the first N columns of the DataFrame (where N =
+    len(schema.feature_names)) contain *exactly* the set of features
+    specified in the schema.
+
+    - If the columns are present but out of order, they are reordered.
+    - If any required feature is missing from the first N columns, it fails.
+    - If any extra column is found within the first N columns, it fails.
+
+    Columns *after* the first N are considered target columns and are
+    logged for verification.
+
+    Args:
+        df_path (str, Path): 
+            The path to the CSV file.
+        schema (FeatureSchema): 
+            The schema object to validate against.
+        all_strings (bool): 
+            If True, loads all columns as string data types.
+
+    Returns:
+        (Tuple[pd.DataFrame, str]):
+            A tuple containing the loaded, validated (and possibly
+            reordered) pandas DataFrame and the base name of the file.
+            
+    Raises:
+        ValueError: 
+            - If the DataFrame is missing columns required by the schema
+              within its first N columns.
+            - If the DataFrame's first N columns contain unexpected
+              columns that are not in the schema.
+        FileNotFoundError: 
+            If the file does not exist at the given path.
+    """
+    # Step 1: Load the dataframe using the original function
+    try:
+        df, df_name = load_dataframe(
+            df_path=df_path, 
+            use_columns=None,  # Load all columns for validation
+            kind="pandas", 
+            all_strings=all_strings,
+            verbose=True
+        )
+    except Exception as e:
+        _LOGGER.error(f"Failed during initial load for schema validation: {e}")
+        raise e
+    
+    # Step 2: Call the helper to validate and reorder
+    df_validated = _validate_and_reorder_schema(df=df, schema=schema)
+
+    return df_validated, df_name
+
+
 def yield_dataframes_from_dir(datasets_dir: Union[str,Path], verbose: bool=True):
     """
     Iterates over all CSV files in a given directory, loading each into a Pandas DataFrame.
@@ -288,15 +354,25 @@ def save_dataframe_filename(df: Union[pd.DataFrame, pl.DataFrame], save_dir: Uni
         
     # --- Type-specific saving logic ---
     if isinstance(df, pd.DataFrame):
-        df.to_csv(output_path, index=False, encoding='utf-8')
+        # Transform "" to np.nan before saving
+        df_to_save = df.replace(r'^\s*$', np.nan, regex=True)
+        # Save
+        df_to_save.to_csv(output_path, index=False, encoding='utf-8')
     elif isinstance(df, pl.DataFrame):
-        df.write_csv(output_path) # Polars defaults to utf8 and no index
+        # Transform empty strings to Null
+        df_to_save = df.with_columns(
+            pl.when(pl.col(pl.Utf8).str.strip() == "")
+            .then(None)
+            .otherwise(pl.col(pl.Utf8))
+        )
+        # Save
+        df_to_save.write_csv(output_path)
     else:
         # This error handles cases where an unsupported type is passed
         _LOGGER.error(f"Unsupported DataFrame type: {type(df)}. Must be pandas or polars.")
         raise TypeError()
     
-    _LOGGER.info(f"Saved dataset: '{filename}' with shape: {df.shape}")
+    _LOGGER.info(f"Saved dataset: '{filename}' with shape: {df_to_save.shape}")
 
 
 def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
@@ -319,6 +395,52 @@ def save_dataframe(df: Union[pd.DataFrame, pl.DataFrame], full_path: Path):
                             filename=full_path.name)
 
 
+def save_dataframe_with_schema(
+    df: pd.DataFrame, 
+    full_path: Path,
+    schema: "FeatureSchema"
+) -> None:
+    """
+    Saves a pandas DataFrame to a CSV, strictly enforcing that the
+    first N columns match the FeatureSchema.
+
+    This function validates that the first N columns of the DataFrame
+    (where N = len(schema.feature_names)) contain *exactly* the set
+    of features specified in the schema.
+    
+    - If the columns are present but out of order, they are reordered.
+    - If any required feature is missing from the first N columns, it fails.
+    - If any extra column is found within the first N columns, it fails.
+
+    Columns *after* the first N are considered target columns and are
+    logged for verification.
+
+    Args:
+        df (pd.DataFrame): 
+            The DataFrame to save.
+        full_path (Path): 
+            The complete file path where the DataFrame will be saved.
+        schema (FeatureSchema): 
+            The schema object to validate against.
+
+    Raises:
+        ValueError: 
+            - If the DataFrame is missing columns required by the schema
+              within its first N columns.
+            - If the DataFrame's first N columns contain unexpected
+              columns that are not in the schema.
+    """
+    if not isinstance(full_path, Path) or not full_path.suffix.endswith(".csv"):
+        _LOGGER.error('A path object pointing to a .csv file must be provided.')
+        raise ValueError()
+    
+    # Call the helper to validate and reorder
+    df_to_save = _validate_and_reorder_schema(df=df, schema=schema)
+    
+    # Call the original save function
+    save_dataframe(df=df_to_save, full_path=full_path)
+
+
 def distribute_dataset_by_target(
     df_or_path: Union[pd.DataFrame, str, Path],
     target_columns: list[str],
@@ -431,5 +553,72 @@ def train_dataset_yielder(
         yield (df_features, df_target, feature_names, target_col)
 
 
+def _validate_and_reorder_schema(
+    df: pd.DataFrame, 
+    schema: "FeatureSchema"
+) -> pd.DataFrame:
+    """
+    Internal helper to validate and reorder a DataFrame against a schema.
+
+    Checks for missing, extra, and out-of-order feature columns
+    (the first N columns). Returns a reordered DataFrame if necessary.
+    Logs all actions.
+
+    Raises:
+        ValueError: If validation fails.
+    """
+    # Get schema and DataFrame column info
+    expected_features = list(schema.feature_names)
+    expected_set = set(expected_features)
+    n_features = len(expected_features)
+    
+    all_df_columns = df.columns.to_list()
+
+    # --- Strict Validation ---
+
+    # 0. Check if DataFrame is long enough
+    if len(all_df_columns) < n_features:
+        _LOGGER.error(f"DataFrame has only {len(all_df_columns)} columns, but schema requires {n_features} features.")
+        raise ValueError()
+    
+    df_feature_cols = all_df_columns[:n_features]
+    df_feature_set = set(df_feature_cols)
+    df_target_cols = all_df_columns[n_features:]
+
+    # 1. Check for missing features
+    missing_from_df = expected_set - df_feature_set
+    if missing_from_df:
+        _LOGGER.error(f"DataFrame's first {n_features} columns are missing required schema features: {missing_from_df}")
+        raise ValueError()
+
+    # 2. Check for extra (unexpected) features
+    extra_in_df = df_feature_set - expected_set
+    if extra_in_df:
+        _LOGGER.error(f"DataFrame's first {n_features} columns contain unexpected columns: {extra_in_df}")
+        raise ValueError()
+
+    # --- Reordering ---
+    
+    df_to_process = df
+
+    # If we pass validation, the sets are equal. Now check order.
+    if df_feature_cols == expected_features:
+        _LOGGER.info("DataFrame feature columns already match schema order.")
+    else:
+        _LOGGER.warning("DataFrame feature columns do not match schema order. Reordering...")
+        
+        # Rebuild the DataFrame with the correct feature order + target columns
+        new_order = expected_features + df_target_cols
+        df_to_process = df[new_order]
+
+    # Log the presumed target columns for user verification
+    if not df_target_cols:
+        _LOGGER.warning(f"No target columns were found after index {n_features-1}.")
+    else:
+        _LOGGER.info(f"Presumed Target Columns: {df_target_cols}")
+    
+    return df_to_process # type: ignore
+
+
 def info():
     _script_info(__all__)

dragon_ml_toolbox-12.13.0.dist-info/RECORD

@@ -1,41 +0,0 @@
-dragon_ml_toolbox-12.13.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.13.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
-ml_tools/ETL_cleaning.py,sha256=2VBRllV8F-ZiPylPp8Az2gwn5ztgazN0BH5OKnRUhV0,20402
-ml_tools/ETL_engineering.py,sha256=KfYqgsxupAx6e_TxwO1LZXeu5mFkIhVXJrNjP3CzIZc,54927
-ml_tools/GUI_tools.py,sha256=Va6ig-dHULPVRwQYYtH3fvY5XPIoqRcJpRW8oXC55Hw,45413
-ml_tools/MICE_imputation.py,sha256=X273Qlgoqqg7KTmoKd75YDyAPB0UIbTzGP3xsCmRh3E,11717
-ml_tools/ML_callbacks.py,sha256=2ZazJjlbClP-ALc8q0ru2oalkugbhO3TFwPg4RFZpck,14056
-ml_tools/ML_datasetmaster.py,sha256=kedCGneR3S2zui0_JFZN6TBL5e69XWkdpkE_QohyqSM,31433
-ml_tools/ML_evaluation.py,sha256=h7fAtk0lS4gTqQ46fiVjucTvFlX4rsufKnEtate6Nu0,18381
-ml_tools/ML_evaluation_multi.py,sha256=Kn9n5lfxo7A0TvgIDMx8UHZCvzTqv1ViezzwJBF-ypM,15970
-ml_tools/ML_inference.py,sha256=ymFvncFsU10PExq87xnEj541DKV5ck0nMuK8ToJHzVQ,23067
-ml_tools/ML_models.py,sha256=G64NPhYZfYvHTIUwkIrMrNLgfDTKJwqdc8jwesPqB9E,28090
-ml_tools/ML_optimization.py,sha256=es3TlQbY7RYgJMZnznkjYGbUxFnAqzZxE_g3_qLK9Q8,22960
-ml_tools/ML_scaler.py,sha256=tw6onj9o8_kk3FQYb930HUzvv1zsFZe2YZJdF3LtHkU,7538
-ml_tools/ML_simple_optimization.py,sha256=W2mce1XFCuiOHTOjOsCNbETISHn5MwYlYsTIXH5hMMo,18177
-ml_tools/ML_trainer.py,sha256=UmCuKr_GzQGYqhEZ-kaRv9Buj44DsNyuOzmOM7Fw8N0,24569
-ml_tools/ML_utilities.py,sha256=EnKpPTnJ2qjZmz7kvows4Uu5CfSA7ByRmI1v2-KarKw,9337
-ml_tools/PSO_optimization.py,sha256=fVHeemqilBS0zrGV25E5yKwDlGdd2ZKa18d8CZ6Q6Fk,22961
-ml_tools/RNN_forecast.py,sha256=Qa2KoZfdAvSjZ4yE78N4BFXtr3tTr0Gx7tQJZPotsh0,1967
-ml_tools/SQL.py,sha256=vXLPGfVVg8bfkbBE3HVfyEclVbdJy0TBhuQONtMwSCQ,11234
-ml_tools/VIF_factor.py,sha256=at5IVqPvicja2-DNSTSIIy3SkzDWCmLzo3qTG_qr5n8,10422
-ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
-ml_tools/_logger.py,sha256=dlp5cGbzooK9YSNSZYB4yjZrOaQUGW8PTrM411AOvL8,4717
-ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
-ml_tools/constants.py,sha256=3br5Rk9cL2IUo638eJuMOGdbGQaWssaUecYEvSeRBLM,3322
-ml_tools/custom_logger.py,sha256=7tSAgRL7e-Ekm7rS1FLDocaPLCnaoKc7VSrtfwCtCEg,10067
-ml_tools/data_exploration.py,sha256=haddQFsXAWzuf84NLItcZ4Q7vzN3YWjFoh7lPlWUczo,50679
-ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
-ml_tools/ensemble_inference.py,sha256=0yLmLNj45RVVoSCLH1ZYJG9IoAhTkWUqEZmLOQTFGTY,9348
-ml_tools/ensemble_learning.py,sha256=vsIED7nlheYI4w2SBzP6SC1AnNeMfn-2A1Gqw5EfxsM,21964
-ml_tools/handle_excel.py,sha256=pfdAPb9ywegFkM9T54bRssDOsX-K7rSeV0RaMz7lEAo,14006
-ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
-ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,8800
-ml_tools/optimization_tools.py,sha256=P074YCuZzkqkONnAsM-Zb9DTX_i8cRkkJLpwAWz6CRw,13521
-ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
-ml_tools/serde.py,sha256=ll2mVC0sO2jIEdG3K6xMcgEN13N4YSb8VjviGvw_ers,4949
-ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
-dragon_ml_toolbox-12.13.0.dist-info/METADATA,sha256=p3-oOSqq1hhJj13KjIXeFnwBu3UTfBJu5mTDL9MCpdU,6167
-dragon_ml_toolbox-12.13.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.13.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.13.0.dist-info/RECORD,,