Open SRSteinkamp opened 6 years ago
It is true that those metadata would be useful. However, we will not be able to provide them for the running challenge.
I am with Guillaume right now, and he wants to moderate his answer: he will try to provide the TR, but makes no promises.
Ok, so the TR information should be available by tomorrow. We need to synchronize the autism kit (#39) as well as the different data set to make sure of not breakdown in the submission process.
The feature is now available in the last commit of this repository. You can access the TR data as:
In [1]: from problem import get_train_data
In [2]: X, y = get_train_data()
In [3]: X['repetition_time']
Out[3]:
subject_id
1932355398536124106 2.50000
5174041730092253771 3.00000
10219322676643534800 3.00000
10645466564919190227 2.50000
...
7789126193351344754 2.00000
9057622900394015793 2.00000
10099127552657342413 2.00000
Name: repetition_time, Length: 1127, dtype: float64
Thank you so much :) ... I really appreciate it, as I always feel a little guilty, when a quick question like this results in so much work for you guys.
Let's see how this can be put to use!
Dear all,
first of all thanks for organizing the challenge, it's a blast getting started with this :)
I was looking into creating features from the resting state data (not necessarily based on functional connectivity) and saw that the time series are of different length. Which is in a clinical setting with different sites definitely understandable.
However, now I am wondering whether the data was acquired using the same BOLD sequences. Or whether there are some information on acquisition parameters. Especially the TR, which would be necessary / useful for applying some temporal filtering on the data or using temporal features.
Best, Simon
(I hope I just didn't overlook the info somewhere...)