A fast implementation of the LOESS algorithm in Python
Project description
PyLOESS
This is a vectorized implementation of LOESS that supports polynomial models. It is fast enough for bootstrap resampling for computing prediction intervals.
Installation
pip install pyloess
Usage
from pyloess import loess
# Generate some data
import numpy as np
np.random.seed(0)
x = np.random.uniform(0, 10, 100)
y = np.sin(x) + np.random.normal(0, 0.1, 100)
x_new = np.linspace(0, 10, 1000)
# Evaluate the loess model
y_new = loess(x, y, eval_x=x_new, span=0.33, degree=2)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pyloess-0.1.0.tar.gz
(4.0 kB
view hashes)