Computes Adjusted R² Score for regression models. Args: y_true (array-like): True target values. y_pred (array-like): Predic

Generate a basic statistical profile for a CSV dataset. Args: file_path: Path to a CSV file. Returns: A dictionary containin

Benchmarks a machine learning model for classification or regression. Args: model: Scikit-learn compatible model. X (pd.Data

Benchmark a model for classification or regression. Returns a dict of metrics and timing.

Extracts and returns feature importance from a fitted model, if available. Args: model: A trained scikit-learn compatible model.

Extract normalized feature importance from a fitted model. Supports tree models with feature_importances_ and linear models with coef_.

Plots a confusion matrix. Args: y_true (array-like): True labels. y_pred (array-like): Predicted labels. labels (lis

Plots feature importance as a horizontal bar chart. Args: feature_importance (dict): Dictionary of feature names and their importanc

Plots benchmark metrics as a bar chart. Args: metrics (dict): Dictionary of benchmark metrics.

Analyzes and summarizes the types of columns in the dataset. Args: df (pd.DataFrame): Input dataset. Returns: dict: Cou

Compares multiple machine learning models on a given dataset. Args: models (dict): A dictionary where keys are model names and value

Checks the balance of classes in a categorical target variable. Args: df (pd.DataFrame): Input dataset. target_column (str):

Checks the balance of classes in a categorical target variable. Args: df (pd.DataFrame): Input dataset. target_column (str):

Computes confusion matrices for multiple classification models. Args: models (dict): Dictionary of classification models. X

Computes a detailed classification report for multiple models. Args: models (dict): Dictionary of classification models. X (

Computes the number of unique values for categorical features. Args: df (pd.DataFrame): Input dataset. categorical_features

Computes additional error metrics for multiple regression models. Args: models (dict): Dictionary of regression models. X (p

Identifies anomalous values based on standard deviations from the mean. Args: df (pd.DataFrame): Input dataset. numerical_fe

Identifies columns with constant values. Args: df (pd.DataFrame): Input dataset. Returns: list: List of constant column

Identifies duplicate rows in a dataset. Args: df (pd.DataFrame): Input dataset. Returns: pd.DataFrame: Duplicate rows i

Identifies duplicate rows in a dataset. Args: df (pd.DataFrame): Input dataset. Returns: pd.DataFrame: Duplicate rows i

Identifies missing values in the dataset. Args: df (pd.DataFrame): Input dataset. Returns: pd.DataFrame: Table showing

Identifies missing values in the dataset. Args: df (pd.DataFrame): Input dataset. Returns: pd.DataFrame: Table showing

Identifies outliers in numerical columns using the IQR method. Args: df (pd.DataFrame): Input dataset. threshold (float): Th

Identifies outliers in numerical columns using the IQR method. Args: df (pd.DataFrame): Input dataset. threshold (float): Th

Identifies outliers in numerical features using the Interquartile Range (IQR) method. Args: df (pd.DataFrame): Dataset containing nu

Generates a classification report with precision, recall, and F1-score. Args: model: A scikit-learn compatible classification model.

Evaluates a classification model using Cohen's Kappa score. Args: model: A scikit-learn compatible classification model. X (

Estimates the confidence interval for model accuracy using bootstrapping. Args: model: A scikit-learn compatible classification mode

Evaluates a classification model using log loss. Args: model: A scikit-learn compatible classification model with `predict_proba` me

Evaluates a regression model using Mean Squared Log Error (MSLE). Args: model: A scikit-learn compatible regression model. X

Evaluates a regression model using the median absolute error. Args: model: A scikit-learn compatible regression model. X (pd

Evaluates a classification model using ROC AUC score and plots the ROC curve. Args: model: A scikit-learn compatible classification

Evaluates a classification model with varying probability thresholds. Args: model: A scikit-learn compatible classification model wi

Identifies columns with missing value percentage higher than the given threshold. Args: df (pd.DataFrame): Input dataset. th

Computes additional summary statistics for numerical features. Args: df (pd.DataFrame): Input dataset. Returns: pd.Data

Computes additional summary statistics for numerical features. Args: df (pd.DataFrame): Input dataset. Returns: pd.Data

Identifies highly correlated features in a dataset. Args: df (pd.DataFrame): Input dataset. threshold (float): Correlation t

Identifies highly correlated features in a dataset. Args: df (pd.DataFrame): Input dataset. threshold (float): Correlation t

Configures logging for the package. Args: log_level (int): Logging level (default: logging.INFO). log_file (str): Path to th

Loads configuration settings from a JSON file. Args: config_file (str): Path to the configuration file (default: 'config.json').

Normalizes numerical features using Min-Max Scaling. Args: df (pd.DataFrame): Dataset containing numerical features. numeric

Plots actual vs predicted values for regression. Args: y_true (array-like): True values. y_pred (array-like): Predicted valu

Creates boxplots for multiple numerical features to detect outliers. Args: df (pd.DataFrame): DataFrame containing numerical feature

Creates a box plot comparing a categorical feature against a numerical feature. Args: df (pd.DataFrame): Input DataFrame. ca

Plots the distribution of class labels in a dataset. Args: y (array-like): Target labels.

Plot confusion matrix.

Plots a heatmap of feature correlations. Args: df (pd.DataFrame): DataFrame containing numerical features.

Plot correlation heatmap for numeric columns.

Plots the distribution of a numerical feature. Args: df (pd.DataFrame): DataFrame containing the feature. feature (str): Col

Plot feature importance as horizontal bar chart.

Plots the learning curve of a model. Args: model: A scikit-learn compatible model. X (pd.DataFrame or np.ndarray): Feature m

Plot a learning curve for a model.

Plot metric dict as a bar chart.

Plots pairwise relationships between numerical features. Args: df (pd.DataFrame): DataFrame containing numerical features. n

Plots the Precision-Recall curve. Args: y_true (array-like): True binary labels. y_scores (array-like): Predicted probabilit

Plots residuals (errors) of a regression model. Args: y_true (array-like): True values. y_pred (array-like): Predicted value

Plots the Receiver Operating Characteristic (ROC) curve. Args: y_true (array-like): True binary labels. y_scores (array-like

Plots accuracy, precision, recall, and F1-score against different thresholds. Args: threshold_df (pd.DataFrame): DataFrame containin

Preprocesses the dataset by handling missing values, scaling numerical features, and encoding categorical features. Args: df (pd

Generates a detailed statistical profile of the dataset. Args: file_path (str): Path to the CSV file containing dataset. Return

Generates a detailed statistical profile of the dataset. Args: file_path (str): Path to the CSV file containing the dataset. Re

Reduces the cardinality of categorical features by grouping rare categories into a single category. Args: df (pd.DataFrame): The dat

Summarizes the top N most frequent categories in a categorical column. Args: df (pd.DataFrame): Input dataset. column (str):