dragon-ml-toolbox 12.6.0__py3-none-any.whl → 12.7.0__py3-none-any.whl

{dragon_ml_toolbox-12.6.0.dist-info → dragon_ml_toolbox-12.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 12.6.0
+Version: 12.7.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: "Karl L. Loza Vidaurre" <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-12.6.0.dist-info → dragon_ml_toolbox-12.7.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-dragon_ml_toolbox-12.6.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
-dragon_ml_toolbox-12.6.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=iy2r_R7wjzsCbz_Q_jMsp_jfZ6oP8XW9QhwzRBH0mGY,1904
+dragon_ml_toolbox-12.7.0.dist-info/licenses/LICENSE,sha256=L35WDmmLZNTlJvxF6Vy7Uy4SYNi6rCfWUqlTHpoRMoU,1081
+dragon_ml_toolbox-12.7.0.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
@@ -34,8 +34,8 @@ ml_tools/math_utilities.py,sha256=PxoOrnuj6Ntp7_TJqyDWi0JX03WpAO5iaFNK2Oeq5I4,88
 ml_tools/optimization_tools.py,sha256=ewYMAdSGlFxYALAGFXn-MsHpvW_Sbx6I-sKg9Kp6rB8,13533
 ml_tools/path_manager.py,sha256=CyDU16pOKmC82jPubqJPT6EBt-u-3rGVbxyPIZCvDDY,18432
 ml_tools/serde.py,sha256=UIshIesHRFmxr8F6B3LxGG8bYc1HHK-nlE3kENSZL18,5288
-ml_tools/utilities.py,sha256=_uCYOo5f6Zp6wxabrHwDfjvaipqziD7BWSdKhjl2VGU,13923
-dragon_ml_toolbox-12.6.0.dist-info/METADATA,sha256=Bg2mEGcvqeyB4Pr-M3ETjAM3GOwr7FBH0s57XpuBij0,6166
-dragon_ml_toolbox-12.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-12.6.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-12.6.0.dist-info/RECORD,,
+ml_tools/utilities.py,sha256=OcAyV1tEcYAfOWlGjRgopsjDLxU3DcI5EynzvWV4q3A,15754
+dragon_ml_toolbox-12.7.0.dist-info/METADATA,sha256=Ek5m6-ExduWUlSvDJ26AYySjU5aILoyiUVlP5dDYWyY,6166
+dragon_ml_toolbox-12.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-12.7.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-12.7.0.dist-info/RECORD,,

ml_tools/utilities.py

@@ -12,6 +12,7 @@ from ._logger import _LOGGER
 # Keep track of available tools
 __all__ = [
     "load_dataframe",
+    "load_dataframe_greedy",
     "yield_dataframes_from_dir",
     "merge_dataframes",
     "save_dataframe_filename",
@@ -124,6 +125,54 @@ def load_dataframe(
     return df, df_name # type: ignore
 
 
+def load_dataframe_greedy(directory: Union[str, Path],
+                          use_columns: Optional[list[str]] = None,
+                          all_strings: bool = False,
+                          verbose: bool = True) -> pd.DataFrame:
+    """
+    Greedily loads the first found CSV file from a directory into a Pandas DataFrame.
+
+    This function scans the specified directory for any CSV files. It will
+    attempt to load the *first* CSV file it finds using the `load_dataframe`
+    function as a Pandas DataFrame.
+
+    Args:
+        directory (str, Path): 
+            The path to the directory to search for a CSV file.
+        use_columns (list[str] | None):
+            A list of column names to load. If None, all columns are loaded.
+        all_strings (bool): 
+            If True, loads all columns as string data types.
+
+    Returns:
+        pd.DataFrame: 
+            A pandas DataFrame loaded from the first CSV file found.
+
+    Raises:
+        FileNotFoundError: 
+            If the specified directory does not exist or the CSV file path
+            found is invalid.
+        ValueError: 
+            If the loaded DataFrame is empty or `use_columns` contains
+            invalid column names.
+    """
+    # validate directory
+    dir_path = make_fullpath(directory, enforce="directory")
+    
+    # list all csv files and grab one (should be the only one)
+    csv_dict = list_csv_paths(directory=dir_path, verbose=False)
+    
+    for df_path in csv_dict.values():
+        df , _df_name = load_dataframe(df_path=df_path,
+                                    use_columns=use_columns,
+                                    kind="pandas",
+                                    all_strings=all_strings,
+                                    verbose=verbose)
+        break
+    
+    return df
+
+
 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.