It is the 326774520 id. In order to know that it was this id, I checked the lengths of each id for each npy file. I didn’t have any particular error that pointed me to this id, it was the only one that didn’t have the same lengths.
When I launched the extraction with the output h5 format I had this error :
Traceback (most recent call last):
File "extractor_2.py", line 263, in <module>
if __name__ == "__main__": main()
File "extractor_2.py", line 258, in main
run_feature_vector_extraction(ids=ids, **module.args)
File "extractor_2.py", line 241, in run_feature_vector_extraction
su.save_results_to_h5(used_ids, results_dict, output_dir, output_code)
File "E:\MARGAUX\new_ipfx_2\ipfx\ipfx\script_utils.py", line 305, in save_results_to_h5
compression="gzip")
File "C:\Users\marga\anaconda3\envs\ipfxnwb2\lib\site-packages\h5py\_hl\group.py", line 136, in create_dataset
dsid = dataset.make_new_dset(self, shape, dtype, data, **kwds)
File "C:\Users\marga\anaconda3\envs\ipfxnwb2\lib\site-packages\h5py\_hl\dataset.py", line 118, in make_new_dset
tid = h5t.py_create(dtype, logical=1)
File "h5py\h5t.pyx", line 1634, in h5py.h5t.py_create
File "h5py\h5t.pyx", line 1656, in h5py.h5t.py_create
File "h5py\h5t.pyx", line 1711, in h5py.h5t.py_create
TypeError: Object dtype dtype('O') has no native HDF5 equivalent
When I launched the script with the npy format as output, I only had this sentence which signaled a length problem:
Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
The ids that I had previously removed because they were in the fv_errors_test.json had no length problem. Here are error messages of some of those ids :
{
"id": 480952106,
"error": {
"error": {
"type": "dataset",
"details": "Traceback (most recent call last):\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\script_utils.py\", line 72, in dataset_for_specimen_id\n nwb_file=nwb_path, sweep_info=sweep_info, ontology=ontology)\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\aibs_data_set.py\", line 16, in __init__\n self._nwb_data = nwb_reader.create_nwb_reader(nwb_file)\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\nwb_reader.py\", line 685, in create_nwb_reader\n nwb_version = get_nwb_version(nwb_file)\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\nwb_reader.py\", line 624, in get_nwb_version\n with h5py.File(nwb_file, 'r') as f:\n File \"C:\\Users\\marga\\anaconda3\\envs\\ipfxnwb2\\lib\\site-packages\\h5py\\_hl\\files.py\", line 408, in __init__\n swmr=swmr)\n File \"C:\\Users\\marga\\anaconda3\\envs\\ipfxnwb2\\lib\\site-packages\\h5py\\_hl\\files.py\", line 173, in make_fid\n fid = h5f.open(name, flags, fapl=fapl)\n File \"h5py\\_objects.pyx\", line 54, in h5py._objects.with_phil.wrapper\n File \"h5py\\_objects.pyx\", line 55, in h5py._objects.with_phil.wrapper\n File \"h5py\\h5f.pyx\", line 88, in h5py.h5f.open\nOSError: Unable to open file (truncated file: eof = 34531238, sblock->base_addr = 0, stored_eof = 83224070)\n"
}
}
},
{
"id": 490278904,
"error": {
"error": {
"type": "processing",
"details": "Traceback (most recent call last):\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\extractor_2.py\", line 182, in data_for_specimen_id\n lsq_features, target_amplitudes, shift=10)\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\feature_vectors.py\", line 612, in identify_suprathreshold_spike_info\n features, target_amplitudes, shift, amp_tolerance)\n File \"E:\\MARGAUX\\new_ipfx_2\\ipfx\\ipfx\\feature_vectors.py\", line 695, in _identify_suprathreshold_indices\n raise er.FeatureError(\"Could not find at least two spiking sweeps matching requested amplitude levels\")\nipfx.error.FeatureError: Could not find at least two spiking sweeps matching requested amplitude levels\n"
}
}
}