Skip to main content
Donate to the Python Software Foundation or Purchase a PyCharm License to Benefit the PSF! Donate Now

A wrapper for sklearn, that makes it easier to write, tune and evaluate classification and regression systems

Project description

scikit-learn sidekick

A wrapper for scikit-learn that makes it easier to write, tune and evaluate classification and regression systems



Install from the python package index:

```pip install sklearnsk

Or clone this repository and install:

```pip install .



Defining your classification or regression algorithm

The **ConfigurableAlgorithm** abstract class provides a template for implementing your classification or regression algorithm.
If you follow this template, then you will be able to easily tune and evaluate your algorithm without writing a lot of additional,
repetitive code.

The main idea of this template is that it forces you to create a class that has a consistent interface: all algorithms
must have a fit and a predict method, and must be able to be instantiated with a single property; a config dictionary.

This config dictionary is where you define:

* the underlying classification or regression algorithm you use (e.g. SVC, RandomForest, LinearRegression, etc)
* any hyper-parameters involved in tuning the algorithm (e.g. C, gamma, max_depth)
* the individual features or feature groups you might want to turn on or off
* any parameters involved in generating features (e.g. ngram range, max K for K-best feature selection, etc)

Basically, if there are any knobs at all that you would want to fiddle with for tuning your system or performing any feature
analysis, you should be able to manipulate them by changing the config dictionary.

When you implement ConfigurableAlgorithm, you must implement the following methods:


Should return a dictionary associating keys with default values. The config dictionary used to instantiate the Algorithm
will be merged with this dictionary, so that the.

In particular, this dictionary should provide

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
sklearnsk-0.1.2-py3-none-any.whl (9.0 kB) Copy SHA256 hash SHA256 Wheel py3
sklearnsk-0.1.2.tar.gz (9.5 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page