TimeSeries¶

class nidmd.TimeSeries(data=None, filenames=None, sampling_time=None)[source]: Representation of time-series data.

Constructor¶

TimeSeries.__init__(data=None, filenames=None, sampling_time=None)[source]¶

TimeSeries Constructor.

Parameters

data (Array-like, optional) – Preprocessed time-series fMRI data. Can be a list of Array-like.
filenames (str, optional) – Filenames of .mat files containing data. Can be a list of str
sampling_time (float, optional) – Sampling time of time-series recording.

Methods¶

`TimeSeries.add`(data)	Add data
`TimeSeries.extract`(filename)	Extracts fMRI data from file.
`TimeSeries.split`(data[, normalize])	Split time-series into X: [1->T] and Y:[0->T-1].
`TimeSeries.normalize`(data[, direction, …])	Normalize a matrix
`TimeSeries.dmd`([normalize])	Returns a dictionary-like object containing Dynamic Mode Decomposition elements.
`TimeSeries.get_decomposition`(x, y)	Get dynamic modes by Least Squares optimization of Auto-regressive model.
`TimeSeries.match_modes`(tc, s, m)	Match modes using Time Series data of match group and eigenvectors of reference group.

API reference¶

class nidmd.TimeSeries(data=None, filenames=None, sampling_time=None)[source]¶

Representation of time-series data.

add(data)[source]¶

Add data

Parameters: data (Array-like) – Time-series data.

static adjust_phase(x)[source]¶

Adjust phase of matrix for orthogonalization of columns.

Parameters: x (Array-like) – data matrix
Returns: ox – data matrix with orthogonalized columns
Return type: Array-like

dmd(normalize=True)[source]¶

Returns a dictionary-like object containing Dynamic Mode Decomposition elements.

Parameters: normalize (boolean) – Normalize data before decomposition (default True)
Returns: dmd – Dynamic Mode Decomposition elements with keys: {values, vectors, indices, A, activity}
Return type: Dictionary-like

extract(filename)[source]¶

Extracts fMRI data from file. Supported formats are: { code:.mat }

Parameters: filename (str) – Path to file containing time-series data.
Raises: ImportError – If file does not contain matrix

get_decomposition(x, y)[source]¶

Get dynamic modes by Least Squares optimization of Auto-regressive model.

Parameters

x (Array-like) – data for t (1->T)
y (Array-like) – data for t (0->T-1)

Returns

eig_val (Array-like) – Eigenvalues of the eigen-decomposition of the Auto-regressive matrix
eig_vec (Array-like) – Eigenvectors of the eigen-decomposition of the Auto-regressive matrix
eig_idx (Array-like) – Indices that sort the eigenvalues in descending order
A (Array-like) – The Auto-regressive matrix.

static match_modes(tc, s, m)[source]¶

Match modes using Time Series data of match group and eigenvectors of reference group.

Parameters

tc (Array-like) – Raw time-series data from match group
s (Array-like) – Eigenvectors from the eigen-decomposition of the auto-regressive model of the reference group.
m (int) – number of modes analyzed for approximation

Returns

d – Approximation of the m first modes matched to the Reference group.

Return type

Array-like

Raises

AtlasError – If cortical parcellation is not supported.

static normalize(data, direction=1, demean=True, destandard=True)[source]¶

Normalize a matrix

Parameters

data (Array-like) – data matrix
direction (int, optional) – 0 for columns, 1 for rows (default), None for global
demean (boolean, optional) – Normalize mean (default true)
destandard (boolean, optional) – Normalize standard-deviation (default true)

Returns

x (Array-like) – Normalized matrix
mean (float) – Mean of original data.
std (float) – Standard deviation of original data.

static split(data, normalize=True)[source]¶

Split time-series into X: [1->T] and Y:[0->T-1].

Parameters

data (Array-like) – Time-series data. Can be list of Array-like.
normalize (boolean) – For normalization of the input data.

Returns

x (Array-like) – Time-series data from t:1->T
y (Array-like) – Time-series data from t:0->T-1

Raises

ValueError – If input is invalid