search

hoffmangroup / segway

Application for semi-automated genomic annotation.
http://segway.hoffmanlab.org/
GNU General Public License v2.0
13 stars 7 forks source link

Setting resolution>1 fails for semi-supervised mode #61

Closed EricR86 closed 8 years ago

EricR86 commented 8 years ago

Original report (BitBucket issue) by Rachel Chan (Bitbucket: rcwchan).

Setting resolution>1 (ie, resolution=10) fails while in semi-supervised mode.

This is because of the assertion test that resolution==1. It seems that setting resolution>1 is not implemented yet for semisupervised mode.

On line 335 in segway/observations.py:

    if supervision_data is not None:
        assert resolution == 1  # not implemented yet
        int_blocks.append(supervision_data)

The rest of the function is downsampling/processing track data, which seems to work fine for unsupervised mode. There doesn't seem to be any other code related to semisupervised mode wrt downsampling data in particular (ie, labels etc).

@michaelmhoffman , would you happen to have any information about this and/or why the supervision labels aren't downsampled as well, for example?

Thanks!

EricR86 commented 8 years ago

Original comment by Rachel Chan (Bitbucket: rcwchan).

Fixed in pull request #48