dragon-ml-toolbox 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

{dragon_ml_toolbox-1.2.0.dist-info → dragon_ml_toolbox-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.2.0
+Version: 1.2.1
 Summary: A collection of tools for data science and machine learning projects
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -11,6 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+License-File: LICENSE-THIRD-PARTY.md
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: matplotlib

{dragon_ml_toolbox-1.2.0.dist-info → dragon_ml_toolbox-1.2.1.dist-info}/RECORD

@@ -1,9 +1,10 @@
-dragon_ml_toolbox-1.2.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-1.2.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-1.2.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=e1Hg5ZtaBpDV7ZvxhLe1ac28l7nMjvi1MSE5YvB1s-o,1472
 ml_tools/MICE_imputation.py,sha256=Xvupj6w4NJ7d8gcJbpp1y3LVVnWEfvx-It7oEksuT5I,7349
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ml_tools/data_exploration.py,sha256=AMQ5XLrRhV6dLhptjl2Jppgk9JJ06ZjXEuvqkjC3gt0,26998
+ml_tools/data_exploration.py,sha256=laTNbN5_xlhqWiKfF-cJ9yMZ8zAM2a-AryqgiIQBBLg,26649
 ml_tools/datasetmaster.py,sha256=VUneKshnmjOGbtqVVGTFcIMRKF3s6ZDYrosIYKDjD80,28956
-ml_tools/ensemble_learning.py,sha256=uA7A94CLv8o2l125oTEi0cjHusZkB-7Mnrtn7SGTfjs,29714
+ml_tools/ensemble_learning.py,sha256=5UmlXI3Orm5zL0P07Ub_Y0gwjruH-REHY-cFWQpJWb0,29085
 ml_tools/handle_excel.py,sha256=IR0VQc3hYdmjwC31E5YxDnRcWig4jSIx7Y_7to-KZz4,11969
 ml_tools/logger.py,sha256=XwSpCUzw2Le24fJHyljBxNLgw63SwjZ0pMjTJqf0ylI,4622
 ml_tools/particle_swarm_optimization.py,sha256=jpkje4OETC9fyISxxUTx4XGrImSU6gDEcwz46ZDs2bQ,19250
@@ -11,7 +12,7 @@ ml_tools/pytorch_models.py,sha256=Oykw02sOZLCjvSadQd64UGesBN7kq0x1EGXHusvYiQI,99
 ml_tools/trainer.py,sha256=Zd7AaHeoNd8dEas2JChWoHaCUpWUVRDUMybuHaKJ0XY,16740
 ml_tools/utilities.py,sha256=mG_--EFplfI9H7OhrWI8VkdNJtTbs4Wbz32xvcFWps8,5518
 ml_tools/vision_helpers.py,sha256=lBAW6dzAK-HOswAt1fU_tfP9hkNLY5D8c_I_7hhEXno,7528
-dragon_ml_toolbox-1.2.0.dist-info/METADATA,sha256=LmlbpETQETUcZuGatEtnP6JttrkN7kVObxjzvl5INfk,5128
-dragon_ml_toolbox-1.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-1.2.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-1.2.0.dist-info/RECORD,,
+dragon_ml_toolbox-1.2.1.dist-info/METADATA,sha256=_dLYb0G6dqpxh2jeWdWuG91LHQZCNDq2HVxbcBLlcu0,5165
+dragon_ml_toolbox-1.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-1.2.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-1.2.1.dist-info/RECORD,,

dragon_ml_toolbox-1.2.1.dist-info/licenses/LICENSE-THIRD-PARTY.md

@@ -0,0 +1,23 @@
+# Third-Party Licenses
+
+This project depends on the following third-party packages. Each is governed by its own license, linked below.
+
+- [pandas](https://github.com/pandas-dev/pandas/blob/main/LICENSE)
+- [numpy](https://github.com/numpy/numpy/blob/main/LICENSE.txt)
+- [matplotlib](https://github.com/matplotlib/matplotlib/blob/main/LICENSE/LICENSE)
+- [seaborn](https://github.com/mwaskom/seaborn/blob/main/LICENSE)
+- [statsmodels](https://github.com/statsmodels/statsmodels/blob/main/LICENSE.txt)
+- [ipython](https://github.com/ipython/ipython/blob/main/COPYING.rst)
+- [torch](https://github.com/pytorch/pytorch/blob/main/LICENSE)
+- [scikit-learn](https://github.com/scikit-learn/scikit-learn/blob/main/COPYING)
+- [imblearn](https://github.com/scikit-learn-contrib/imbalanced-learn/blob/main/LICENSE)
+- [Pillow](https://github.com/python-pillow/Pillow/blob/main/LICENSE)
+- [joblib](https://github.com/joblib/joblib/blob/main/LICENSE.txt)
+- [xgboost](https://github.com/dmlc/xgboost/blob/main/LICENSE)
+- [lightgbm](https://github.com/microsoft/LightGBM/blob/master/LICENSE)
+- [shap](https://github.com/shap/shap/blob/master/LICENSE)
+- [openpyxl](https://github.com/chronossc/openpyxl/blob/main/LICENSE)
+- [miceforest](https://github.com/AnotherSamWilson/miceforest/blob/main/LICENSE)
+- [polars](https://github.com/pola-rs/polars/blob/main/LICENSE)
+- [torchvision](https://github.com/pytorch/vision/blob/main/LICENSE)
+- [pyswarm](https://pythonhosted.org/pyswarm/#license)

ml_tools/data_exploration.py

@@ -15,8 +15,7 @@ from ml_tools.utilities import sanitize_filename
 
 
 # Keep track of all available functions, show using `info()`
-__all__ = ["load_dataframe",
-           "summarize_dataframe",
+__all__ = ["summarize_dataframe",
            "drop_rows_with_missing_data",
            "split_features_targets", 
            "show_null_columns",
@@ -33,21 +32,6 @@ __all__ = ["load_dataframe",
            "drop_vif_based"]
 
 
-def load_dataframe(df_path: str) -> pd.DataFrame:
-    """
-    Loads a DataFrame from a CSV file.
-
-    Args:
-        df_path (str): Path to the CSV file.
-
-    Returns:
-        pd.DataFrame: Loaded DataFrame.
-    """
-    df = pd.read_csv(df_path, encoding='utf-8')
-    print(f"DataFrame shape {df.shape}")
-    return df
-
-
 def summarize_dataframe(df: pd.DataFrame, round_digits: int = 2):
     """
     Returns a summary DataFrame with data types, non-null counts, number of unique values,

ml_tools/ensemble_learning.py

@@ -21,6 +21,8 @@ from sklearn.preprocessing import StandardScaler, MaxAbsScaler, MinMaxScaler
 from sklearn.metrics import accuracy_score, classification_report, ConfusionMatrixDisplay, mean_absolute_error, mean_squared_error, r2_score, roc_curve, roc_auc_score
 import shap
 
+from .utilities import yield_dataframes_from_dir
+
 import warnings # Ignore warnings 
 warnings.filterwarnings('ignore', category=DeprecationWarning)
 warnings.filterwarnings('ignore', category=FutureWarning)
@@ -28,23 +30,6 @@ warnings.filterwarnings('ignore', category=UserWarning)
 
 
 ###### 1. Dataset Loader ######
-#Load imputed datasets as a generator
-def yield_imputed_dataframe(datasets_dir: str):
-    '''
-    Yields a tuple `(dataframe, dataframe_name)`
-    '''
-    dataset_filenames = [dataset for dataset in os.listdir(datasets_dir) if dataset.endswith(".csv")]
-    if not dataset_filenames:
-        raise IOError(f"No imputed datasets have been found at {datasets_dir}")
-    
-    for dataset_filename in dataset_filenames:
-        full_path = os.path.join(datasets_dir, dataset_filename)
-        df = pd.read_csv(full_path)
-        #remove extension
-        filename = os.path.splitext(os.path.basename(dataset_filename))[0]
-        print(f"Working on dataset: {filename}")
-        yield (df, filename)
-
 #Split a dataset into features and targets datasets
 def dataset_yielder(df: pd.DataFrame, target_cols: list[str]):
     ''' 
@@ -543,7 +528,7 @@ def get_shap_values(model, model_name: str,
             plot_size=figsize,
             max_display=max_display_features,
             alpha=0.7,
-            color=plt.get_cmap('viridis')
+            color=plt.get_cmap('viridis') # type: ignore
         )
         
         # Add professional styling
@@ -674,7 +659,7 @@ def run_pipeline(datasets_dir: str, save_dir: str, target_columns: list[str], ta
     #Check paths
     _check_paths(datasets_dir, save_dir)
     #Yield imputed dataset
-    for dataframe, dataframe_name in yield_imputed_dataframe(datasets_dir):
+    for dataframe, dataframe_name in yield_dataframes_from_dir(datasets_dir):
         #Yield features dataframe and target dataframe
         for df_features, df_target, feature_names, target_name in dataset_yielder(df=dataframe, target_cols=target_columns):
             #Dataset pipeline