Beispiel #1
0
def load_file(file_name, standardize, demean):
    bbci_set = BBCIDataset(file_name,
                          load_sensor_names=get_EEG_sensors_sorted())
    log.info("Loading...")
    cnt = bbci_set.load()
    log.info("Set cz to zero and remove high absolute value trials")
    marker_def = dict([(str(i_class), [i_class])  for i_class in xrange(1,5)])
    clean_result = MaxAbsCleaner(threshold=800,
                                                  marker_def=marker_def,
                                                  segment_ival=[0,4000]).clean(cnt)
    
    cnt = restrict_cnt(cnt, marker_def.values(), clean_result.clean_trials, 
        clean_result.rejected_chan_names, copy_data=False)
    cnt = set_channel_to_zero(cnt, 'Cz')
    
    
    log.info("Resampling...")
    cnt = resample_cnt(cnt, newfs=250.0)
    
    log.info("Car filtering...")
    cnt = common_average_reference_cnt(cnt)
    if standardize:
        log.info("Standardizing...")
        cnt = exponential_standardize_cnt(cnt)
    if demean: 
        log.info("Demeaning...")
        cnt = exponential_demean_cnt(cnt)
    
    return cnt
Beispiel #2
0
def load_file(file_name, standardize, demean):
    bbci_set = BBCIDataset(file_name,
                           load_sensor_names=get_EEG_sensors_sorted())
    log.info("Loading...")
    cnt = bbci_set.load()
    log.info("Set cz to zero and remove high absolute value trials")
    marker_def = dict([(str(i_class), [i_class]) for i_class in xrange(1, 5)])
    clean_result = MaxAbsCleaner(threshold=800,
                                 marker_def=marker_def,
                                 segment_ival=[0, 4000]).clean(cnt)

    cnt = restrict_cnt(cnt,
                       marker_def.values(),
                       clean_result.clean_trials,
                       clean_result.rejected_chan_names,
                       copy_data=False)
    cnt = set_channel_to_zero(cnt, 'Cz')

    log.info("Resampling...")
    cnt = resample_cnt(cnt, newfs=250.0)

    log.info("Car filtering...")
    cnt = common_average_reference_cnt(cnt)
    if standardize:
        log.info("Standardizing...")
        cnt = exponential_standardize_cnt(cnt)
    if demean:
        log.info("Demeaning...")
        cnt = exponential_demean_cnt(cnt)

    return cnt
Beispiel #3
0
 def preprocess_test_set(self):
     if self.sensor_names is not None:
         self.sensor_names = sort_topologically(self.sensor_names)
         self.test_cnt = select_channels(self.test_cnt, self.sensor_names)
     if self.set_cz_to_zero is True:
         self.test_cnt = set_channel_to_zero(self.test_cnt, 'Cz')
     if self.resample_fs is not None:
         self.test_cnt = resample_cnt(self.test_cnt, newfs=self.resample_fs)
     if self.common_average_reference is True:
         self.test_cnt = common_average_reference_cnt(self.test_cnt)
     if self.standardize_cnt is True:
         self.test_cnt = exponential_standardize_cnt(self.test_cnt)
Beispiel #4
0
 def preprocess_test_set(self):
     if self.sensor_names is not None:
         self.sensor_names = sort_topologically(self.sensor_names)
         self.test_cnt = select_channels(self.test_cnt, self.sensor_names)
     if self.set_cz_to_zero is True:
         self.test_cnt = set_channel_to_zero(self.test_cnt, 'Cz')
     if self.resample_fs is not None:
         self.test_cnt = resample_cnt(self.test_cnt, newfs=self.resample_fs)
     if self.common_average_reference is True:
         self.test_cnt = common_average_reference_cnt(self.test_cnt)
     if self.standardize_cnt is True:
         self.test_cnt = exponential_standardize_cnt(self.test_cnt)
Beispiel #5
0
    def preprocess_set(self):
        # only remove rejected channels now so that clean function can
        # be called multiple times without changing cleaning results
        self.cnt = select_channels(self.cnt, self.rejected_chan_names,
            invert=True)
        if self.sensor_names is not None:
            # Note this does not respect order of sensor names,
            # it selects chans form given sensor names
            # but keeps original order
            self.cnt = select_channels(self.cnt, self.sensor_names)

        if self.set_cz_to_zero is True:
            self.cnt = set_channel_to_zero(self.cnt, 'Cz')
        if self.resample_fs is not None:
            self.cnt = resample_cnt(self.cnt, newfs=self.resample_fs)
        if self.common_average_reference is True:
            self.cnt = common_average_reference_cnt(self.cnt)
        if self.standardize_cnt is True:
            self.cnt = exponential_standardize_cnt(self.cnt)
Beispiel #6
0
    def preprocess_set(self):
        # only remove rejected channels now so that clean function can
        # be called multiple times without changing cleaning results
        self.cnt = select_channels(self.cnt,
                                   self.rejected_chan_names,
                                   invert=True)
        if self.sensor_names is not None:
            # Note this does not respect order of sensor names,
            # it selects chans form given sensor names
            # but keeps original order
            self.cnt = select_channels(self.cnt, self.sensor_names)

        if self.set_cz_to_zero is True:
            self.cnt = set_channel_to_zero(self.cnt, 'Cz')
        if self.resample_fs is not None:
            self.cnt = resample_cnt(self.cnt, newfs=self.resample_fs)
        if self.common_average_reference is True:
            self.cnt = common_average_reference_cnt(self.cnt)
        if self.standardize_cnt is True:
            self.cnt = exponential_standardize_cnt(self.cnt)