Charles Jekel

To clarify, all uses of `ssr` in `PiecewiseLinFit` are okay and don't need changing. Including `PiecewiseLinFit.r_squared`.

Penalty parameters generally range from 1e-1 to 1e-6, and yes it's super arbitrary. If you are looking at automatically performing these fits in a more robust manner, check out this...

The variance is very high in your case, and you may benefit from trying this https://github.com/cjekel/piecewise_linear_fit_py/issues/17#issuecomment-821732674 but replace `x` and `y` with your own data. It should be biased to...

What was the F ratio for both cases? ```python F = sigma_hat / sigma ``` Maybe it's better to pick the one that is closest to 1.0, since one over...

If you are trying to fit a model that looks like:  It's not really going to be possible with pwlf. (I'm not sure if this is the type of...

Well.. Instead of doing a rotation, you could break x and y into separate 1 dimensional predictions. Let's say that both x and y are functions of the arc length...

```python import numpy as np import matplotlib.pyplot as plt import pwlf from scipy.spatial.distance import cdist x = np.array([0.42486339, 0.55889496, 0.70537341, 0.79477838, 0.91180935, 1. , 0.95309654, 0.85868245, 0.77580449, 0.68867638, 0.60731633, 0.523983...

Which coefficients do you need directly? The arc length stuff is definitely a more complicated modeling approach. As far as doing one model, you could do fits to x as...

@loveis98 Can you sketch on that plot what kind of fit you'd expect to that data set? Is your data following some order of occurrences? ie, does x[0] y[0] occur...

Hi Yucheng, Thank you for this ambitious software contribution! I think there are many users that will find this really helpful. This is a functionality that has been requested dozens...