tessl/pypi-interpret

Fit interpretable models and explain blackbox machine learning with comprehensive interpretability tools.

—

Pending

Overview

Eval results

Files

Data Analysis

Name: tessl/pypi-interpret
Author: tessl

Tools for understanding dataset characteristics and feature distributions to inform model selection and feature engineering decisions.

Capabilities

Class Distribution Analysis

Analyzes class distributions in classification datasets to identify imbalances and understand target variable characteristics.

class ClassHistogram:
    def __init__(self, feature_names=None, **kwargs):
        """
        Class distribution analyzer.
        
        Parameters:
            feature_names (list, optional): Names for features
            **kwargs: Additional arguments
        """
    
    def explain_data(self, X, y, name=None):
        """
        Analyze class distributions in the dataset.
        
        Parameters:
            X (array-like): Feature data
            y (array-like): Target labels
            name (str, optional): Name for explanation
            
        Returns:
            Explanation object with class distribution analysis
        """

Marginal Distribution Analysis

Analyzes marginal distributions of features to understand data characteristics and identify potential issues.

class Marginal:
    def __init__(self, feature_names=None, feature_types=None, **kwargs):
        """
        Marginal distribution analyzer.
        
        Parameters:
            feature_names (list, optional): Names for features
            feature_types (list, optional): Types for features
            **kwargs: Additional arguments
        """
    
    def explain_data(self, X, y=None, name=None):
        """
        Analyze marginal feature distributions.
        
        Parameters:
            X (array-like): Feature data
            y (array-like, optional): Target labels
            name (str, optional): Name for explanation
            
        Returns:
            Explanation object with marginal distribution analysis
        """

Usage Examples

from interpret.data import ClassHistogram, Marginal
from interpret import show
from sklearn.datasets import load_wine

# Load dataset
data = load_wine()
X, y = data.data, data.target

# Analyze class distribution
class_hist = ClassHistogram(feature_names=data.feature_names)
class_exp = class_hist.explain_data(X, y, name="Class Distribution")
show(class_exp)

# Analyze feature distributions
marginal = Marginal(feature_names=data.feature_names)
marginal_exp = marginal.explain_data(X, y, name="Feature Distributions")
show(marginal_exp)

Install with Tessl CLI