One LOWESS to Rule Them All
The fastest, most robust, and most feature-complete language-agnostic LOWESS (Locally Weighted Scatterplot Smoothing) implementation for Rust, Python, R, Julia, Node.js, C++, Go, Java, and WebAssembly.
The
lowess-projectcontains a complete ecosystem for LOWESS smoothing:
lowess- Core single-threaded Rust implementation withno_stdsupportfastLowess- Parallel CPU and GPU-accelerated Rust wrapper with ndarray integrationR bindings- extendr-based R bindingPython bindings- PyO3-based Python bindingJulia bindings- Native Julia binding with C FFINode.js bindings- Node.js bindingWebAssembly bindings- WASM bindingC++ bindings- Native C++ binding with CMake integrationGo bindings- cgo-based Go bindingJava bindings- JNI-based Java binding
Currently available for R, Python, Rust, Julia, Node.js, WebAssembly, C++, Go, and Java. See the documentation for your binding/crate below for installation instructions.
Binding / Crate Documentation lowess(Rust)docs.rs/lowess fastLowess(Rust)docs.rs/fastLowess Python lowess.readthedocs.io R thisisamirv.github.io/lowess-project/r Julia thisisamirv.github.io/lowess-project/julia Node.js thisisamirv.github.io/lowess-project/nodejs WebAssembly thisisamirv.github.io/lowess-project/wasm C++ thisisamirv.github.io/lowess-project/cpp Go thisisamirv.github.io/lowess-project/go Java thisisamirv.github.io/lowess-project/java
GPU acceleration (wgpu: Vulkan, Metal, DirectX 12, and
GLES on Android) is also supported for high-throughput batch smoothing.
See the GPU Backend page in the documentation for your binding/crate for
details.
| Feature | LOESS | LOWESS (This Crate) |
|---|---|---|
| Polynomial Degree | Linear, Quadratic, Cubic, Quartic | Linear (Degree 1) |
| Dimensions | Multivariate (n-D support) | Univariate (1-D only) |
| Flexibility | High (Distance metrics) | Standard |
| Complexity | Higher (Matrix inversion) | Lower (Weighted average/slope) |
Note: For a LOESS implementation, use
loess-project.
It is on average 200-327x faster than Python's
statsmodels.lowess and up to 7.8× faster than base
R's stats::lowess on a tested large, wide-window
workload. GPU fastLowess first beats CPU-parallel execution
at 25K–50K points, depending on smoothing fraction, and
reaches 4.7× speedup over parallel fastLowess CPU
execution at 1M points in the tested workload. Small workloads
can favor CPU because of GPU overhead; results vary by workload and
hardware. See the Benchmarks page for details.
For more details on the performance comparison, see the Benchmarks page in the documentation for your binding/crate.
This implementation is more robust than R's
lowess and Python's statsmodels due to two key
design choices:
MAD-Based Scale Estimation:
For robustness weight calculations, this crate uses Median Absolute Deviation (MAD) for scale estimation:
s = median(|r_i - median(r)|)
In contrast, statsmodels and R's lowess
uses the median of absolute residuals (MAR):
s = median(|r_i|)
Boundary Padding:
This crate applies a range of different boundary policies at dataset edges:
statsmodels and R's lowess do not apply
boundary padding, which can lead to:
A variety of features, supporting a range of use cases:
| Feature | This package | statsmodels | R (stats) |
|---|---|---|---|
| Kernel | 7 options | only Tricube | only Tricube |
| Robustness Weighting | 3 options | only Huber | only Huber |
| Scale Estimation | 2 options | only MAR | only MAR |
| Boundary Padding | 4 options | no padding | no padding |
| Zero Weight Fallback | 3 options | no | no |
| Auto Convergence | yes | no | no |
| Online Mode | yes | no | no |
| Streaming Mode | yes | no | no |
| Confidence Intervals | yes | no | no |
| Prediction Intervals | yes | no | no |
| Cross-Validation | 2 options | no | no |
| Parallel Execution | yes | no | no |
| GPU Acceleration | yes | no | no |
no-std Support |
yes | no | no |
All implementations are numerical twins of R's
lowess:
| Aspect | Status | Details |
|---|---|---|
| Accuracy | ✅ EXACT MATCH | Max diff < 1e-12 across all scenarios |
| Consistency | ✅ PERFECT | Multiple scenarios pass with strict tolerance |
| Robustness | ✅ VERIFIED | Robust smoothing matches R exactly |
Contributions are welcome! Please see CONTRIBUTING.md for more information.
See CHANGELOG.md for a history of changes.
Licensed under MIT or Apache-2.0.
If you use this software in your research, please cite it using the CITATION.cff file or the BibTeX entry below:
@software{lowess_project,
author = {Valizadeh, Amir},
title = {LOWESS Project: High-Performance Locally Weighted Scatterplot Smoothing},
year = {2026},
url = {https://github.com/thisisamirv/lowess-project},
license = {MIT OR Apache-2.0}
}