Welcome to mealy’s documentation!

mealy is a Python package to perform Model Error AnaLYsis of scikit-learn models, leveraging an Error Tree, a Decision Tree predicting the failures and successes of a ML model.

The code of the project is on Github: mealy

Installation

Using Pypi

mealy can be installed through Pypi using:

$ pip install mealy

Installing locally

You can also fetch the code and install the package from your local repository. Again, the preferred way is to use pip.

$ git clone https://github.com/dataiku/mealy
$ cd mealy
$ pip install -e

Model Error Analysis

• Introduction to Model Error Analysis
  • Principle
  • Metrics

Example galleries

• Examples

API and developer reference

• mealy’s API Reference
  • mealy.error_analyzer
  • mealy.error_visualizer
  • mealy.metrics
  • mealy.preprocessing
  • mealy.error_analysis_utils
• Fork mealy on Github

Indices and tables

• Index

• Module Index

• Search Page