KIAPBCI/kiap_bci/analytics/dynamic_ranges.py

import matplotlib.pyplot as plt
import numpy as np
import yaml
import aux
from helpers import data_management as dm
import modules.classifier as clf
import analytics
import os
import itertools
from collections.abc import Iterable

    

params = aux.load_config()

if params.speller.type == 'exploration':
    data_tot, tt, triggers_tot, ch_rec_list, file_names = dm.get_raw(n_triggers=params.classifier.n_classes,
                                                                     exploration=True, trigger_pos=params.classifier.trigger_pos)
elif params.speller.type == 'feedback':
    data_tot, tt, triggers_tot, ch_rec_list, file_names = dm.get_raw(n_triggers=params.classifier.n_classes,
                                                                     feedback=True, trigger_pos=params.classifier.trigger_pos)
else:
    data_tot, tt, triggers_tot, ch_rec_list, file_names = dm.get_raw(n_triggers=params.classifier.n_classes, 
                                                                    trigger_pos=params.classifier.trigger_pos)

data = np.empty((0, params.daq.n_channels))

for fids in range(data_tot.shape[0]):
    data = np.concatenate((data, data_tot[fids,0]))


pp = np.percentile(data, params.daq.normalization.range, axis=0)

def create_channels_yaml(channels):
    out_dict = {'channels': []}
    for ch in channels:
        out_dict['channels'].append({'id': int(ch['id']), 
             'bottom': float(pp[0, ch['id']]),
             'top': float(pp[1, ch['id']]),
             'invert': ch['invert']}
             )
    return out_dict
    

print(f"\n\nSelected channels dynamic ranges:\n\n{yaml.dump(create_channels_yaml(params.daq.normalization.channels), sort_keys=False, default_flow_style=None)}\n")

# print(yaml.dump(out_dict, sort_keys=False, default_flow_style=None))

other_channels = [{'id':item, 'invert':False} for item in range(params.daq.n_channels) if item not in [ch.id for ch in params.daq.normalization.channels]]
print(f"\nOther channels dynamic ranges (nb: 'invert' is set to default!):\n\n{yaml.dump(create_channels_yaml(other_channels), sort_keys=False, default_flow_style=None)}\n")


pp_all = np.percentile(np.nanmean(data, axis=1), params.daq.normalization.range, axis=0)
out_dict = {'all_channels': {'bottom': float(pp_all[0]), 'top': float(pp_all[1]), 'invert': params.daq.normalization.all_channels.invert}}
print(f"All Channels bounds:\n\n{yaml.dump(out_dict, sort_keys=False, default_flow_style=None)}")