- eelbrain.boosting(y, x, tstart, tstop, scale_data=True, delta=0.005, mindelta=None, error='l2', basis=0, basis_window='hamming', partitions=None, model=None, validate=1, test=0, data=None, selective_stopping=0, partition_results=False, debug=False)
Estimate a linear filter with coordinate descent
y (NDVar) – Signal to predict. When
ycontains more than one signal (e.g., multiple EEG channels), results for each signal will be computed independently. Muiltiple cases along a
Casedimension are treated as different trials which share a filter. For correlation fit metrics, a
Spacedimension is interpreted as defining a vector measure.
x (NDVar | sequence of NDVar) – Signal to use to predict
y. Can be sequence of NDVars to include multiple predictors. Time dimension must correspond to
tstart (scalar | sequence of scalar) – Start of the TRF in seconds. A list can be used to specify different values for each item in
tstop (scalar | sequence of scalar) – Stop of the TRF in seconds. Format must match
scale_data (bool | 'inplace') – Scale
xbefore boosting: subtract the mean and divide by the standard deviation (when
error='l2') or the mean absolute value (when
'inplace'to save memory by scaling the original objects specified as
xinstead of making a copy. The data scale is stored in the
delta (float) – Step for changes in the kernel.
mindelta (float) – If the error for the training data can’t be reduced, divide
deltain half until
delta < mindelta. The default is
mindelta = delta, i.e.
error (Literal['l1', 'l2']) –
Error function to use (default is
error='l1': the sum of the absolute differences between
h * x.
error='l2': the sum of the squared differences between
h * x.
y, the error is defined based on the distance in space for each data point.
basis (float) – Use a basis of windows with this length for the kernel (by default, impulses are used).
basis_window (str | scalar | tuple) – Basis window (see
scipy.signal.get_window()for options; default is
partitions (int) – Divide the data into this many
partitionsfor cross-validation-based early stopping. In each partition,
n - 1segments are used for training, and the remaining segment is used for validation. If data is continuous, data are divided into contiguous segments of equal length (default 10). If data has cases, cases are divided with
min(n_cases, 10); if
n_casesis the lowest number of cases in any cell of the model). See Data partitions for boosting example.
model (Union[Factor, Interaction, NestedEffect, str]) – If data has cases, divide cases into different categories (division for crossvalidation is done separately for each cell).
data (Dataset) – If provided, other parameters can be specified as string for items in
validate (int) – Number of segments in validation dataset (currently has to be 1).
test (int) – By default (
test=0), the boosting algorithm uses all available data to estimate the kernel. Set
test=1to perform k-fold cross- validation instead (with k =
partitions): Each partition is used as test dataset in turn, while the remaining
k-1partitions are used to estimate the kernel. The resulting model fit metrics reflect the re-combination of all partitions, each one predicted from the corresponding, independent training set.
selective_stopping (int) – By default, the boosting algorithm stops when the testing error stops decreasing. With
selective_stopping=True, boosting continues but excludes the predictor (one time-series in
x) that caused the increase in testing error, and continues until all predictors are stopped. The integer value of
selective_stoppingdetermines after how many steps with error increases each predictor is excluded.
partition_results (bool) – Keep results (TRFs and model evaluation) for each test-partition. This is disabled by default to reduce file size when saving results.
debug (bool) – Add additional attributes to the returned result.
- Return type
preview data partitions for cross-validation
The boosting algorithm is described in 1.
In order to predict data, use the
>>> ds = datasets.get_uts() >>> data['a1'] = epoch_impulse_predictor('uts', 'A=="a1"', ds=data) >>> data['a0'] = epoch_impulse_predictor('uts', 'A=="a0"', ds=data) >>> res = boosting('uts', ['a0', 'a1'], 0, 0.5, partitions=10, model='A', data=data) >>> y_pred = convolve(res.h_scaled, ['a0', 'a1'], ds=data) >>> y = data['uts'] >>> plot.UTS([y-y.mean('time'), y_pred], '.case')
David, S. V., Mesgarani, N., & Shamma, S. A. (2007). Estimating sparse spectro-temporal receptive fields with natural stimuli. Network: Computation in Neural Systems, 18(3), 191-212. 10.1080/09548980701609235.