Fix n_fft_samples docstring: uses next_fast_len, not next power of 2

[Copilot]

The Multitaper class docstring incorrectly stated that n_fft_samples defaults to "next power of 2 >= n_time_samples_per_window". The implementation actually uses scipy.fft.next_fast_len() (or cupy.fft.next_fast_len() for GPU), which returns an FFT-efficient length that may not be a power of 2.

For example:

from scipy.fft import next_fast_len
next_fast_len(30000)  # Returns 30000, not 32768
next_fast_len(100)    # Returns 100, not 128

Changes

• Updated n_fft_samples parameter docstring in Multitaper.__init__() to accurately describe the behavior:
  • Removed incorrect "next power of 2" claim
  • Added reference to scipy.fft.next_fast_len / cupy.fft.next_fast_len
  • Clarified that the value is chosen for FFT efficiency, not strictly power-of-2 alignment

Original prompt

---

This section details on the original issue you should resolve

<issue_title>multitaper DocString incorrect</issue_title>
<issue_description>the Multitaper constructor says:
n_fft_samples : int, optional Length of FFT. If None, uses next power of 2 >= n_time_samples_per_window.

But e.g. if the data length is 30000, it gives 30000. This is because cupy.fft.next_fast_len(30000)=30000. I'm not sure why it thinks that 30000 is a fast length. From its docstring: "note::
It may return a different value to :func:scipy.fft.next_fast_len
as pocketfft's prime factors are different from cuFFT's factors.
For details, see the cuFFT documentation_."

Maybe we should change the docstring to say:
n_fft_samples : int, optional Length of FFT. If None, uses a value >= n_time_samples_per window chosen to be fast for the FFT algorithm, cupy.fft.next_fast_len(n_time_samples_per_window).</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes multitaper DocString incorrect #73

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[codecov]

Welcome to Codecov 🎉

Once you merge this PR into your default branch, you're all set! Codecov will compare coverage reports and display results in all future pull requests.

Thanks for integrating Codecov - We've got you covered ☂️

[Copilot]

Pull Request Overview

This PR updates the documentation for the n_fft_samples parameter in the Multitaper class to provide more accurate and detailed information about how the FFT length is determined when not explicitly specified.

• Updated the n_fft_samples parameter description to clarify that it uses scipy.fft.next_fast_len (or cupy.fft.next_fast_len for GPU) instead of simply the next power of 2

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.