U f{jcE @sddlmZddlmZddlZddlmZddlm Z ddl m Z m Z ddl mZmZmZmZdd lmZmZmZdd d Zd d ZedddZdddZdddZddZddZdS) ) isgenerator) namedtupleN)SourceEstimate) BaseEpochs)Evoked EvokedArray)logger_reject_data_segmentswarnfill_doc) pick_types pick_info _picks_to_idxc s|dkr ddt|jdD}ttrtjddddddddgd }fd d|Djkrhtd d }}t t |jddjj }nxt rd }t}t |jgd dD}nFttrtdtrd}d}t ddD}ntdt|dt |jddt|ft|||}tdd}i} |D]nfdd|D} t| D]@\} } |} t| ttfstd| | jdd<| | | <qt|| | <qVtd| S)uFit Ordinary Least Squares (OLS) regression. Parameters ---------- inst : instance of Epochs | iterable of SourceEstimate The data to be regressed. Contains all the trials, sensors, and time points for the regression. For Source Estimates, accepts either a list or a generator object. design_matrix : ndarray, shape (n_observations, n_regressors) The regressors to be used. Must be a 2d array with as many rows as the first dimension of the data. The first column of this matrix will typically consist of ones (intercept column). names : array-like | None Optional parameter to name the regressors (i.e., the columns in the design matrix). If provided, the length must correspond to the number of columns present in design matrix (including the intercept, if present). Otherwise, the default names are ``'x0'``, ``'x1'``, ``'x2', …, 'x(n-1)'`` for ``n`` regressors. Returns ------- results : dict of namedtuple For each regressor (key), a namedtuple is provided with the following attributes: - ``beta`` : regression coefficients - ``stderr`` : standard error of regression coefficients - ``t_val`` : t statistics (``beta`` / ``stderr``) - ``p_val`` : two-sided p-value of t statistic under the t distribution - ``mlog10_p_val`` : -log₁₀-transformed p-value. The tuple members are numpy arrays. The shape of each numpy array is the shape of the data minus the first dimension; e.g., if the shape of the original data was ``(n_observations, n_channels, n_timepoints)``, then the shape of each of the arrays will be ``(n_channels, n_timepoints)``. NcSsg|] }d|qS)zx%i.0irrS/var/www/html/bwave/python/venv/lib/python3.8/site-packages/mne/stats/regression.py =sz%linear_regression..TFZbads)ZmegZeegZref_megZstimZeogZecgZemgexcludecsg|]}j|qSr)ch_namesrp)instrrrCsz?Fitting linear model to non-data or bad channels. Check pickingzFitting linear model to epochsz:Fitting linear model to source estimates (generator input)cSsg|] }|jqSrdatarrrrrLsrz5Fitting linear model to source estimates (list input)cSsg|] }|jqSrrrrrrrPsz4Input must be epochs or iterable of source estimatesz, (%s targets, %s regressors)lmz$beta stderr t_val p_val mlog10_p_valcsg|] }|qSrrr)namerrrZszInvalid container.Done)rangeshape isinstancerr inforr get_datarnpZzerostminrnextarrayrlistr ValueErrorr productlen_fit_lmr enumeratecopyr RuntimeError_data)r design_matrixnamespicksmsgroutZ lm_paramsrZlm_fits parametersiivalueZout_r)rrrlinear_regressionsR'  "    r;cCsXddlm}m}t|}t|jdd}|jdkr>td|j\}}||krXtd|t|krltdt |||f} |j || d \} } } } ||} t | |  |jdd}| t |j|}t t|}ttjj}d d td D\}}}}}t| ||D]4\}}}| |jdd||<||||<t||||<t||||<||dk}||dk}|||||||||<|jt|||| }td |d|d |||<||@}tjt||||||<||||<||@}d|||<d |||<t|| ||<q|||||fS)z Aux function.r)statslinalgrNrz Design matrix must be a 2d arrayzGNumber of rows in design matrix must be equal to number of observationszLNumber of regressor names must be equal to number of column in design matrix)abcss|] }tVqdS)N)dict)r_rrr ~sz_fit_lm..?g@)scipyr<r=r-r&r,r"ndimr+ZreshapeZlstsqsqrtinvdotTZdiagZfinfoZfloat64tinyr!zipZ empty_liketcdfabsZclipinfsignlog10)rr3r4r<r= n_samplesZ n_featuresZn_rowsZ n_predictorsyZbetasZresid_sum_squaresrAZdfZsqrt_noise_varZ design_invcovZunscaled_stderrsrKbetastderrZt_valZp_valZ mlog10_p_valxZunscaled_stderrZ predictorZ stderr_posZbeta_posrNmaskrrrr.fsL              r.皙rrDcholeskyc  sddlmt| trB| dkr,td| | dkrTfdd} nt| rLntdt||| | d \} } }|d krd d t |d d d fD}t | j d| d|||||d\}}}}}t || ||| | |\}} | || j }|j d| j dkrtdt|||||| }|S)aSEstimate regression-based evoked potentials/fields by linear modeling. This models the full M/EEG time course, including correction for overlapping potentials and allowing for continuous/scalar predictors. Internally, this constructs a predictor matrix X of size n_samples * (n_conds * window length), solving the linear system ``Y = bX`` and returning ``b`` as evoked-like time series split by condition. See :footcite:`SmithKutas2015`. Parameters ---------- raw : instance of Raw A raw object. Note: be very careful about data that is not downsampled, as the resulting matrices can be enormous and easily overload your computer. Typically, 100 Hz sampling rate is appropriate - or using the decim keyword (see below). events : ndarray of int, shape (n_events, 3) An array where the first column corresponds to samples in raw and the last to integer codes in event_id. event_id : dict | None As in Epochs; a dictionary where the values may be integers or iterables of integers, corresponding to the 3rd column of events, and the keys are condition names. If None, uses all events in the events array. tmin : float | dict If float, gives the lower limit (in seconds) for the time window for which all event types' effects are estimated. If a dict, can be used to specify time windows for specific event types: keys correspond to keys in event_id and/or covariates; for missing values, the default (-.1) is used. tmax : float | dict If float, gives the upper limit (in seconds) for the time window for which all event types' effects are estimated. If a dict, can be used to specify time windows for specific event types: keys correspond to keys in event_id and/or covariates; for missing values, the default (1.) is used. covariates : dict-like | None If dict-like (e.g., a pandas DataFrame), values have to be array-like and of the same length as the rows in ``events``. Keys correspond to additional event types/conditions to be estimated and are matched with the time points given by the first column of ``events``. If None, only binary events (from event_id) are used. reject : None | dict For cleaning raw data before the regression is performed: set up rejection parameters based on peak-to-peak amplitude in continuously selected subepochs. If None, no rejection is done. If dict, keys are types ('grad' | 'mag' | 'eeg' | 'eog' | 'ecg') and values are the maximal peak-to-peak values to select rejected epochs, e.g.:: reject = dict(grad=4000e-12, # T / m (gradiometers) mag=4e-11, # T (magnetometers) eeg=40e-5, # V (EEG channels) eog=250e-5 # V (EOG channels)) flat : None | dict For cleaning raw data before the regression is performed: set up rejection parameters based on flatness of the signal. If None, no rejection is done. If a dict, keys are ('grad' | 'mag' | 'eeg' | 'eog' | 'ecg') and values are minimal peak-to-peak values to select rejected epochs. tstep : float Length of windows for peak-to-peak detection for raw data cleaning. decim : int Decimate by choosing only a subsample of data points. Highly recommended for data recorded at high sampling frequencies, as otherwise huge intermediate matrices have to be created and inverted. %(picks_good_data)s solver : str | callable Either a function which takes as its inputs the sparse predictor matrix X and the observation matrix Y, and returns the coefficient matrix b; or a string. X is of shape (n_times, n_predictors * time_window_length). y is of shape (n_channels, n_times). If str, must be ``'cholesky'``, in which case the solver used is ``linalg.solve(dot(X.T, X), dot(X.T, y))``. Returns ------- evokeds : dict A dict where the keys correspond to conditions and the values are Evoked objects with the ER[F/P]s. These can be used exactly like any other Evoked object, including e.g. plotting or statistics. References ---------- .. footbibliography:: rr=>rZzNo such solver: {}rZcs*|j|}j||j|ddddjS)NposT)Zassume_aZ overwrite_aZ overwrite_b)rJZtoarrayZsolve)XrTr>r[rrsolvers z%linear_regression_raw..solverz'The solver must be a str or a callable.)r5decimNcSsi|]}t||qSr)str)rvrrr sz)linear_regression_raw..rrsfreq)rSrceventsevent_idr'tmax covariateszsolver output has unexcepted shape. Supply a function that returns coefficients in the form (n_targets, n_features), where targets == channels.)rEr=r#r`r+formatcallable TypeError_prepare_rerp_dataset_prepare_rerp_predsr"_clean_rerp_inputrJ _make_evokeds)rawrdrer'rfrgrejectflattstepr_r5r^rr$r]conds cond_lengthtmin_stmax_scoefsevokedsrr[rlinear_regression_raws:\    rzc Cst|j|}t|j|}t|}||d|<W5QRX|dd\}}||dd|f}tt|dddft|dddfkrtd|}|dddf|j 8<|dddf|<tt|dddft|dddfkr td|||fS)z?Prepare events and data, primarily for `linear_regression_raw`.rcNrzj`events` contains duplicate time points. Make sure all entries in the first column of `events` are unique.zAfter decimating, `events` contains duplicate time points. This means some events are too closely spaced for the requested decimation factor. Choose different events, drop close events, or choose a different decimation factor.) rr$rintZ_unlockr-rlr+r0Z first_samp)rprdr5r_r$rtimesrrrrks   ,.rkcsddlm}t|}|dk r(|t|7}tttfrLfdd|D} nfdd|D} tttfrfdd|D} nfdd|D} t} g} |D]8} | | | | }}t||}| |kr.t|| tr|| gn|| }|t|ddd f|df| }t t ||f}n|| }t |t |krZd | }t ||t |dkdf|d }t|t|t}t t ||f|ddtjf}t || | <| |j||f||fd q|| || | | fS) zBBuild predictor matrix and metadata (e.g. condition time windows).r)sparseNcsi|]}|ttqSrr{roundrcondrcr'rrrbDsz'_prepare_rerp_preds..c s&i|]}|tt|dqS)rYr{rgetrrrrrbFscs"i|]}|ttdqS)rr~rrcrfrrrbIsc s*i|]"}|tt|ddqS)rDrrrrrrrbLsrzFCondition {0} from ``covariates`` is not the same length as ``events``)r")rEr}r*r#floatr{r@r&Zin1dZonesr-rhr+whereZasarraynonzeroZastypeZnewaxisappendZ dia_matrixZhstack)rSrcrdrer'rfrgr}rtrvrwruZxsrtmin_tmax_Zn_lagsZidsZonsetsvaluesZcovserrorrar)rcrfr'rrm9sT          & $  rmc Csnt|d}|dk rRt|||d||d\}} | D]\} } t|t| | }q6|||dd|ffS)zDRemove empty and contaminated points from data & predictor matrices.rN)r_r$rs)r&uniquerr Z setdiff1dr!Ztocsr) r]rrqrrr_r$rsZhas_valrAZindst0t1rrrrnss   rnc Csvt}d}|D]b}||||} } t|dd||| | f||| t|d||dd||<|| | 7}q|S)zsCreate a dictionary of Evoked objects. These will be created from a coefs matrix and condition durations. rNrcZaverage)r$commentr'Znavekind)r@rr) rxrtrurvrwr$ryZcumulrrrrrrros ro)N) NrYrNNNrDrNrZ)Nr)NrYrN)inspectr collectionsrnumpyr&Zsource_estimaterZepochsrZevokedrrutilsr r r r Zio.pickr rrr;r.rzrkrmrnrorrrr s6     Q2   :