dragon-ml-toolbox 1.4.1__tar.gz → 1.4.3__tar.gz

{dragon_ml_toolbox-1.4.1 → dragon_ml_toolbox-1.4.3}/LICENSE-THIRD-PARTY.md

@@ -8,7 +8,12 @@ This project depends on the following third-party packages. Each is governed by
 - [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)
+- [ipykernel](https://github.com/ipython/ipykernel/blob/main/COPYING.rst)
+- [notebook](https://github.com/jupyter/notebook/blob/main/LICENSE)
+- [jupyterlab](https://github.com/jupyterlab/jupyterlab/blob/main/LICENSE)
+- [ipywidgets](https://github.com/jupyter-widgets/ipywidgets/blob/main/LICENSE)
 - [torch](https://github.com/pytorch/pytorch/blob/main/LICENSE)
+- [torchvision](https://github.com/pytorch/vision/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)
@@ -19,5 +24,5 @@ This project depends on the following third-party packages. Each is governed by
 - [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)
+- [plotnine](https://github.com/has2k1/plotnine/blob/main/LICENSE.txt)
 - [pyswarm](https://pythonhosted.org/pyswarm/#license)

{dragon_ml_toolbox-1.4.1/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-1.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.1
+Version: 1.4.3
 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-1.4.1 → dragon_ml_toolbox-1.4.3/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 1.4.1
+Version: 1.4.3
 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-1.4.1 → dragon_ml_toolbox-1.4.3}/ml_tools/MICE_imputation.py

@@ -3,7 +3,7 @@ import miceforest as mf
 import os
 import matplotlib.pyplot as plt
 import numpy as np
-from ml_tools.utilities import load_dataframe, list_csv_paths, sanitize_filename, _script_info
+from ml_tools.utilities import load_dataframe, list_csv_paths, sanitize_filename, _script_info, merge_dataframes, save_dataframe
 from plotnine import ggplot, labs, theme, element_blank # type: ignore
 
 
@@ -49,15 +49,11 @@ def apply_mice(df: pd.DataFrame, df_name: str, resulting_datasets: int=1, iterat
     return kernel, imputed_datasets, imputed_dataset_names
 
 
-def save_imputed_datasets(save_dir: str, imputed_datasets: list, imputed_dataset_names: list[str]):
-    # Check path
-    os.makedirs(save_dir, exist_ok=True)
-    
+def save_imputed_datasets(save_dir: str, imputed_datasets: list, df_targets: pd.DataFrame, imputed_dataset_names: list[str]):    
     for imputed_df, subname in zip(imputed_datasets, imputed_dataset_names):
-        output_path = os.path.join(save_dir, subname + ".csv")
-        imputed_df.to_csv(output_path, index=False, encoding='utf-8')
-        print(f"\tSaved {subname} with shape {imputed_df.shape}")
-        
+        merged_df = merge_dataframes(imputed_df, df_targets, direction="horizontal", verbose=False)
+        save_dataframe(df=merged_df, save_dir=save_dir, filename=subname)
+
 
 #Get names of features that had missing values before imputation
 def get_na_column_names(df: pd.DataFrame):
@@ -119,7 +115,7 @@ def get_convergence_diagnostic(kernel: mf.ImputationKernel, imputed_dataset_name
             plt.savefig(save_path, bbox_inches='tight', format="svg")
             plt.close()
             
-        print(f"\t{dataset_file_dir} completed.")
+        print(f"{dataset_file_dir} completed.")
 
 
 # Imputed distributions
@@ -131,7 +127,8 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
     '''
     # Check path
     os.makedirs(root_dir, exist_ok=True)
-    local_save_dir = os.path.join(root_dir, f"Distribution_Metrics_{df_name}_imputed")
+    local_dir_name = f"Distribution_Metrics_{df_name}_imputed"
+    local_save_dir = os.path.join(root_dir, local_dir_name)
     if not os.path.isdir(local_save_dir):
         os.makedirs(local_save_dir)
     
@@ -202,10 +199,10 @@ def get_imputed_distributions(kernel: mf.ImputationKernel, df_name: str, root_di
             fig = kernel.plot_imputed_distributions(variables=[feature])
             _process_figure(fig, feature)
 
-    print("\tImputed distributions saved successfully.")
+    print(f"{local_dir_name} completed.")
 
 
-def run_mice_pipeline(df_path_or_dir: str, save_datasets_dir: str, save_metrics_dir: str, resulting_datasets: int=1, iterations: int=20, random_state: int=101):
+def run_mice_pipeline(df_path_or_dir: str, target_columns: list[str], save_datasets_dir: str, save_metrics_dir: str, resulting_datasets: int=1, iterations: int=20, random_state: int=101):
     """
     Call functions in sequence for each dataset in the provided path or directory:
         1. Load dataframe
@@ -213,6 +210,8 @@ def run_mice_pipeline(df_path_or_dir: str, save_datasets_dir: str, save_metrics_
         3. Save imputed dataset(s)
         4. Save convergence metrics
         5. Save distribution metrics
+        
+    Target columns must be skipped from the imputation.
     """
     # Check paths
     os.makedirs(save_datasets_dir, exist_ok=True)
@@ -228,9 +227,11 @@ def run_mice_pipeline(df_path_or_dir: str, save_datasets_dir: str, save_metrics_
     for df_path in all_file_paths:
         df, df_name = load_dataframe(df_path=df_path)
         
+        df, df_targets = _skip_targets(df, target_columns)
+        
         kernel, imputed_datasets, imputed_dataset_names = apply_mice(df=df, df_name=df_name, resulting_datasets=resulting_datasets, iterations=iterations, random_state=random_state)
         
-        save_imputed_datasets(save_dir=save_datasets_dir, imputed_datasets=imputed_datasets, imputed_dataset_names=imputed_dataset_names)
+        save_imputed_datasets(save_dir=save_datasets_dir, imputed_datasets=imputed_datasets, df_targets=df_targets, imputed_dataset_names=imputed_dataset_names)
         
         imputed_column_names = get_na_column_names(df=df)
         
@@ -239,5 +240,12 @@ def run_mice_pipeline(df_path_or_dir: str, save_datasets_dir: str, save_metrics_
         get_imputed_distributions(kernel=kernel, df_name=df_name, root_dir=save_metrics_dir, column_names=imputed_column_names)
 
 
+def _skip_targets(df: pd.DataFrame, target_cols: list[str]):
+    valid_targets = [col for col in target_cols if col in df.columns]
+    df_targets = df[valid_targets]
+    df_feats = df.drop(columns=valid_targets)
+    return df_feats, df_targets
+
+
 def info():
     _script_info(__all__)

{dragon_ml_toolbox-1.4.1 → dragon_ml_toolbox-1.4.3}/ml_tools/data_exploration.py

@@ -5,10 +5,8 @@ import seaborn as sns
 from IPython import get_ipython
 from IPython.display import clear_output
 import time
-from typing import Union, Literal, Dict, Tuple
+from typing import Union, Literal, Dict, Tuple, Iterator
 import os
-import sys
-import textwrap
 from ml_tools.utilities import sanitize_filename, _script_info
 
 
@@ -24,7 +22,8 @@ __all__ = [
     "check_value_distributions", 
     "plot_value_distributions", 
     "clip_outliers_single", 
-    "clip_outliers_multi"
+    "clip_outliers_multi",
+    "distribute_datasets_by_target"
 ]
 
 
@@ -113,7 +112,7 @@ def show_null_columns(df: pd.DataFrame, round_digits: int = 2):
     Parameters:
         df (pd.DataFrame): The input DataFrame.
         round_digits (int): Number of decimal places for the percentage.
-        
+
     Returns:
         pd.DataFrame: A DataFrame summarizing missing values in each column.
     """
@@ -133,13 +132,14 @@ def show_null_columns(df: pd.DataFrame, round_digits: int = 2):
     return null_summary
 
 
-def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7) -> pd.DataFrame:
+def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7, show_nulls_after: bool = True) -> pd.DataFrame:
     """
     Drops columns with more than `threshold` fraction of missing values.
 
     Parameters:
         df (pd.DataFrame): The input DataFrame.
         threshold (float): Fraction of missing values above which columns are dropped.
+        show_nulls_after (bool): Prints `show_null_columns` after dropping columns. 
 
     Returns:
         pd.DataFrame: A new DataFrame without the dropped columns.
@@ -150,10 +150,15 @@ def drop_columns_with_missing_data(df: pd.DataFrame, threshold: float = 0.7) ->
     if len(cols_to_drop) > 0:
         print(f"Dropping columns with more than {threshold*100:.0f}% missing data:")
         print(list(cols_to_drop))
+        
+        result_df = df.drop(columns=cols_to_drop)
+        if show_nulls_after:
+            show_null_columns(df=result_df).head(20)
+        
+        return result_df
     else:
         print(f"No columns have more than {threshold*100:.0f}% missing data.")
-
-    return df.drop(columns=cols_to_drop)
+        return df
 
 
 def split_continuous_binary(df: pd.DataFrame) -> Tuple[pd.DataFrame, pd.DataFrame]:
@@ -514,6 +519,34 @@ def clip_outliers_multi(
     return new_df
 
 
+def distribute_datasets_by_target(
+    df: pd.DataFrame,
+    target_columns: list[str]
+) -> Iterator[Tuple[str, pd.DataFrame]]:
+    """
+    Yields cleaned DataFrames for each target column, where rows with missing
+    target values are removed. The target column is placed at the end.
+
+    Parameters
+    ----------
+    df : pd.DataFrame
+        Preprocessed dataframe with all feature and target columns ready to train.
+    target_columns : List[str]
+        List of target column names to generate per-target DataFrames.
+
+    Yields
+    ------
+    Tuple[str, pd.DataFrame]
+        * First element is the target column name.
+        * Second element is the corresponding cleaned DataFrame.
+    """
+    feature_columns = [col for col in df.columns if col not in target_columns]
+
+    for target in target_columns:
+        subset = df[feature_columns + [target]].dropna(subset=[target])
+        yield target, subset
+
+
 def _is_notebook():
     return get_ipython() is not None