supersmoother

library0.4pypypiunverified

Python implementation of Friedman's Supersmoother (smooth regression). Current version 0.4, no longer actively maintained; last release in 2016.

analytics

pip install supersmoother

github ↗homepage ↗

INSTALL

IMPORT

SIG · SUPERSMOOTHER

supersmoother

analyticspythonv0.4

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Supersmoother

✓ from supersmoother import Supersmoother

✗ from supersmoother import Supersmoother

Basic usage: instantiate Supersmoother, fit, predict.

import numpy as np from supersmoother import Supersmoother x = np.linspace(0, 10, 100) y = np.sin(x) + 0.1 * np.random.randn(100) model = Supersmoother() model.fit(x, y) y_smooth = model.predict(x) print(y_smooth[:5])

Debug

Known issues

deprecatedThe .smooth() method is deprecated; use .fit() and .predict() instead.

fix

Replace model.smooth(x, y) with model.fit(x, y); y_smooth = model.predict(x).

affects: 0.3 and earlier

gotchaData must be sorted by x when using default smoother. Input x must be monotonically increasing.

fix

Sort arrays before fitting: idx = np.argsort(x); x = x[idx]; y = y[idx].

affects: all

gotchaSupersmoother does not handle missing values (NaN). Input must be clean.

fix

Remove NaN values prior to fitting: mask = ~(np.isnan(x) | np.isnan(y)); x = x[mask]; y = y[mask].

affects: all

Upgrade

Version history

0.4latest on PyPI · released May 6, 2017

Audit

Dependencies

numpyrequiredcore dependency

scipyoptionaloptional, used for sparse smoothing

Agent activity

18 hits · last 30 days

node

OpenAI (training)

Resources

githubhttp://github.com/jakevdp/supersmoother ↗

homepagehttp://github.com/jakevdp/supersmoother ↗