zmzhang / airpls Goto Github PK

1.what is the use of i on line 50？
2.How to adjust itermax？

The R & Python code for computing the weight vector (e.g., https://github.com/zmzhang/airPLS/blob/a92b37a7bcc4d22eac02db2ebdb0a1b9ce1a1a55/airPLS.py#L81-L83C19) appear to differ from the equation given in the paper:

• The code uses e^(t * abs(x_i - z_i) / abs_d), which is e^(t * (z_i - x_i) / abs_d), not e^(t * (x_i - z_i) / abs_d) that the paper says.
• The code uses a special value for w_1 and w_m based on the max negative deviation, which is by definition negative.

The code thus weights points with a lower value more highly, whereas the paper does the opposite. I don't know why the code uses a value for the first and last weights that raises e to a negative power.

关于airPLS,我有几个问题想要请教一下：
（1）如果谱图中出现一个下降曲线，在去除基线后会形成为一个峰，这种情况该如何解决？

（2）有些平缓区域的基线消除不够，该如何调整？

The array edge value is determined by line 82 in the Python implementation.

It occurred to me that this expression is taking the maximum of negative values d[d<0].max() which will likely be close to 0 in most cases... resulting in the exponential evaluating to 1.

If this is not the intention, should the algorithm be updated to the max of the absolute of the negative values (i.e. d[d<0].abs().max())?

If this is the intention, can we just save the effort and set the value to 1? The difference between 1 and very close to 1 doesn't seem worth the computation here...