U g{jyo@sdZddlmZddlZddlZddlZddlZddlmZddl m Z m Z m Z m Z mZmZddlmZddlmZmZmZmZmZmZmZdd lmZmZmZmZmZm Z dd l!m"Z"m#Z#m$Z$m%Z%m&Z&dd l'm(Z(m)Z)m*Z*m+Z+m,Z,m-Z-dd l.m/Z/m0Z0m1Z1m2Z2dd l3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:ddlm;Z;e;<dddddddddddddddddd d!d"d#d$gZ=d7d.dZ>d8d3dZ?d&d&d-d&d'd(d4d'iif d5dZ@d9d6d$ZAdS):z main module for HeartPy. )datetimeN)UnivariateSpline)butterfiltfiltwelch periodogram resample_polyresample) exceptions)get_dataget_samplerate_mstimerget_samplerate_datetime rolling_meanoutliers_iqr_methodoutliers_modified_zload_exampledata) scale_datascale_sectionsinterpolate_clipping flip_signal enhance_peaksenhance_ecg_peaks) filter_signal hampel_filterhampel_correcterremove_baseline_wander smooth_signal) make_windows append_dict fit_peaks check_peakscheck_binary_qualityinterpolate_peaks)plottersegment_plotter plot_poincareplot_breathing)calc_rrcalc_rr_segmentclean_rr_intervalscalc_ts_measurescalc_fd_measurescalc_breathing calc_poincare)configrrr r rrrrr$r'r&process process_rrprocess_segmentwiserrrrr%rr run_tests?Fr(@@quotient-filtercCs |dkr i}|dkri}tjddkr>tjddkr>t}nt}t|jdks^td|r|| rnt |}t ||| d}| rt |}t ||}t |d}|dkr|t|}||d<||d <t|||}t|||| | |d }|rt||d |||d }t|d ||d }t|d|d |d||d }|r>t||d}t|d|d|d||d\}}t|d|d||d}zt|d|||d\}}Wntj|d<YnX|rt|d|||d\}}|rtjddkrtjddkrtdt|ntdt|||fS)a~processes passed heart rate data. Processes the passed heart rate data. Returns measures{} dict containing results. Parameters ---------- hrdata : 1d array or list array or list containing heart rate data to be analysed sample_rate : int or float the sample rate with which the heart rate data is sampled windowsize : int or float the window size in seconds to use in the calculation of the moving average. Calculated as windowsize * sample_rate default : 0.75 report_time : bool whether to report total processing time of algorithm default : False calc_freq : bool whether to compute frequency domain measurements default : False freq_method : str method used to extract the frequency spectrum. Available: 'fft' (Fourier Analysis), 'periodogram', and 'welch' (Welch's method). default : 'welch' welch_wsize : float Size of window (in sec) when welch method used to compute the spectrogram. This choice is based on a trade-off btw temporal res and freq res of the resulting spectrum 60 sec may seem reasonable, but this would greatly limit frequency resolution! 1/60 s = 0.017 Hz, so you would only have 2 points in the VLF band Therefore, the default is 4 min (9 points in the VLF band) default : 240 freq_square : bool whether to square the power spectrum returned when computing frequency measures default : False interp_clipping : bool whether to detect and interpolate clipping segments of the signal default : False clipping_scale : bool whether to scale the data prior to clipping detection. Can correct errors if signal amplitude has been affected after digitization (for example through filtering). Not recommended by default. default : False interp_threshold : int or float threshold to use to detect clipping segments. Recommended to be a few datapoints below the sensor or ADC's maximum value (to account for slight data line noise). default : 1020, 4 below max of 1024 for 10-bit ADC hampel_correct : bool whether to reduce noisy segments using large median filter. Disabled by default due to computational complexity and (small) distortions induced into output measures. Generally it is not necessary. default : False bpmmin : int or float minimum value to see as likely for BPM when fitting peaks default : 40 bpmmax : int or float maximum value to see as likely for BPM when fitting peaks default : 180 reject_segmentwise : bool whether to reject segments with more than 30% rejected beats. By default looks at segments of 10 beats at a time. default : False high_precision : bool whether to estimate peak positions by upsampling signal to sample rate as specified in high_precision_fs default : False high_precision_fs : int or float the sample rate to which to upsample for more accurate peak position estimation default : 1000 Hz breathing_method : str method to use for estimating breathing rate, should be 'welch' or 'fft' default : welch clean_rr : bool if true, the RR_list is further cleaned with an outlier rejection pass default : False clean_rr_method: str how to find and reject outliers. Available methods are ' quotient-filter', 'iqr' (interquartile range), and 'z-score'. default : 'quotient-filter' measures : dict dictionary object used by heartpy to store computed measures. Will be created if not passed to function. working_data : dict dictionary object that contains all heartpy's working data (temp) objects. Will be created if not passed to function. Returns ------- working_data : dict dictionary object used to store temporary values. measures : dict dictionary object used by heartpy to store computed measures. Examples -------- There's example data included in HeartPy to help you get up to speed. Here are provided two examples of how to approach heart rate analysis. The first example contains noisy sections and comes with a timer column that counts miliseconds since start of recording. >>> import heartpy as hp >>> data, timer = hp.load_exampledata(1) >>> sample_rate = hp.get_samplerate_mstimer(timer) >>> '%.3f' %sample_rate '116.996' The sample rate is one of the most important characteristics during the heart rate analysis, as all measures are relative to this. With all data loaded and the sample rate determined, analysis is now easy: >>> wd, m = hp.process(data, sample_rate = sample_rate) The measures ('m') dictionary returned contains all determined measures >>> '%.3f' %m['bpm'] '62.376' >>> '%.3f' %m['rmssd'] '57.070' Using a slightly longer example: >>> data, timer = hp.load_exampledata(2) >>> print(timer[0]) 2016-11-24 13:58:58.081000 As you can see something is going on here: we have a datetime-based timer. HeartPy can accomodate this and determine sample rate nontheless: >>> sample_rate = hp.get_samplerate_datetime(timer, timeformat = '%Y-%m-%d %H:%M:%S.%f') >>> '%.3f' %sample_rate '100.420' Now analysis can proceed. Let's also compute frequency domain data and interpolate clipping. In this segment the clipping is visible around amplitude 980 so let's set that as well: >>> data, timer = hp.load_exampledata(1) >>> sample_rate = hp.get_samplerate_mstimer(timer) >>> wd, m = hp.process(data, sample_rate = sample_rate, calc_freq = True, ... interp_clipping = True, interp_threshold = 975) >>> '%.3f' %m['bpm'] '62.376' >>> '%.3f' %m['rmssd'] '57.070' >>> '%.3f' %m['lf/hf'] '1.090' High precision mode will upsample 200ms of data surrounding detected peak and attempt to estimate the peak's real position with higher accuracy. Use high_precision_fs to set the virtual sample rate to which the peak will be upsampled (e.g. 1000Hz gives an estimated 1ms accuracy) >>> wd, m = hp.process(data, sample_rate = sample_rate, calc_freq = True, ... high_precision = True, high_precision_fs = 1000.0) Finally setting reject_segmentwise will reject segments with more than 30% rejected beats See check_binary_quality in the peakdetection.py module. >>> wd, m = hp.process(data, sample_rate = sample_rate, calc_freq = True, ... reject_segmentwise = True) Final test for code coverage, let's turn all bells and whistles on that haven't been tested yet >>> wd, m = hp.process(data, sample_rate = 100.0, calc_freq = True, ... interp_clipping = True, clipping_scale = True, reject_segmentwise = True, clean_rr = True) Nrr zerror: multi-dimensional data passed to process() function. Please supply a 1d array or list containing heart rate signal data. Did you perhaps include an index column?) thresholdg?hr sample_rate)bpmminbpmmax working_datapeaklist)r>Zdesired_sample_raterA)rARR_listZybeat)method RR_list_corZRR_diffZ RR_sqdiff)measuresrA RR_masklistrDrFrA breathingrater5rD welch_wsizesquare_spectrumrFrAz Finished in %.8s sec)sys version_infotime perf_counterclocknpasarrayndimAssertionErrorrrrrZ percentileabsrr r#r(r!r*r+r.r-nanr,print)hrdatar>Z windowsizeZ report_time calc_freq freq_methodrKZ freq_squareZinterp_clippingZclipping_scaleZinterp_thresholdZhampel_correctr?r@Zreject_segmentwiseZhigh_precisionZhigh_precision_fsbreathing_methodclean_rrclean_rr_methodrFrAt1Zbl_valZrol_meanr`N/var/www/html/bwave/python/venv/lib/python3.8/site-packages/heartpy/heartpy.pyr07s~G            xiqrfullc Ksd|krdksntd|dks.tdi} i} t|||||} |dkr| D]\} } zzt|| | |f|\}}|D]}t| |||} q~|D]}t| |||} qt| d| | f} t| d| | f} WqRtjk rYqRXqRnF|dkr,t||f|\}}t|d }| D]\} } |t || k|| k@}|d t t ||dkdt t ||d kd d }t ||d }t ||\}}}t |||\}}|D]}t| |||} qt| d| | f} t| d| | f} t| d|} t| d|} t| d|} t| d |} q n td||r|dkr|| D]$}|dkrTt| |\| |<}qTn<|dkr| D]$}|dkrt| |\| |<}q| | fS)aprocesses passed heart rate data with a windowed function Analyses a long heart rate data array by running a moving window over the data, computing measures in each iteration. Both the window width and the overlap with the previous window location are settable. Parameters ---------- hrdata : 1d array or list array or list containing heart rate data to be analysed sample_rate : int or float the sample rate with which the heart rate data is sampled segment_width : int or float width of segments in seconds default : 120 segment_overlap: float overlap fraction of adjacent segments. Needs to be 0 <= segment_overlap < 1. default : 0 (no overlap) segment_min_size : int often a tail end of the data remains after segmenting into segments. segment_min_size indicates the minimum length (in seconds) the tail end needs to be in order to be included in analysis. It is discarded if it's shorter. default : 20 replace_outliers : bool whether to detct and replace outliers in the segments. Will iterate over all computed measures and evaluate each. outlier_method : str what method to use to detect outlers. Available are 'iqr', which uses the inter-quartile range, and 'z-score', which uses the modified z-score approach. mode : str 'full' or 'fast' Keyword arguments: ------------------ hrdata -- 1-dimensional numpy array or list containing heart rate data sample_rate -- the sample rate of the heart rate data segment_width -- the width of the segment, in seconds, within which all measures will be computed. segment_overlap -- the fraction of overlap of adjacent segments, needs to be 0 <= segment_overlap < 1 segment_min_size -- After segmenting the data, a tail end will likely remain that is shorter than the specified segment_size. segment_min_size sets the minimum size for the last segment of the generated series of segments to still be included. Default = 20. replace_outliers -- bool, whether to replace outliers (likely caused by peak fitting errors on one or more segments) with the median. outlier_method -- which method to use to detect outliers. Available are the 'interquartile-range' ('iqr') and the 'modified z-score' ('z-score') methods. Returns ------- working_data : dict dictionary object used to store temporary values. measures : dict dictionary object used by heartpy to store computed measures. Examples -------- Given one of the included example datasets we can demonstrate this function: >>> import heartpy as hp >>> data, timer = hp.load_exampledata(2) >>> sample_rate = hp.get_samplerate_datetime(timer, timeformat = '%Y-%m-%d %H:%M:%S.%f') >>> wd, m = hp.process_segmentwise(data, sample_rate, segment_width=120, segment_overlap=0.5) >>> len(m['bpm']) 11 The function has split the data into 11 segments and analysed each one. Every key in the measures (m) dict now contains a list of that measure for each segment. >>> [round(x, 1) for x in m['bpm']] [100.0, 96.8, 97.2, 97.9, 97.0, 96.8, 96.8, 95.0, 92.9, 96.7, 99.2] Specifying mode = 'fast' will run peak detection once and use detections to compute measures over each segment. Useful for speed ups, but typically the full mode has better results. >>> wd, m = hp.process_segmentwise(data, sample_rate, segment_width=120, segment_overlap=0.5, ... mode = 'fast', replace_outliers = True) You can specify the outlier detection method ('iqr' - interquartile range, or 'z-score' for modified z-score approach). >>> wd, m = hp.process_segmentwise(data, sample_rate, segment_width=120, segment_overlap=0.5, ... mode = 'fast', replace_outliers = True, outlier_method = 'z-score') rg?zDvalue error: segment_overlap needs to be 0 <= segment_overlap < 1.0!)rdz-scorezIUnknown outlier detection method specified, use either 'iqr' or 'z-score'resegment_indicesfastrBZbinary_peaklistr r9rr_listrr_diff rr_sqdiffzDmode not understood! Needs to be either 'fast' or 'full', passed: %srd)Znn20Znn50Zinterp_rr_functionZinterp_rr_linspacergrf)rUrr0keysrr ZBadSignalWarningrRrSwhereintdiffr)r+ ValueErrorlowerrr)rYr>Z segment_widthZsegment_overlapZsegment_min_sizeZreplace_outliersZoutlier_methodmodekwargsZ s_measuresZs_working_dataZ slice_indicesiiirArFkrBZpksZpks_brjrkrl_tmpr`r`rar2Ks^d              Tc s|| d<|rt|} d| dkr*| dn | d| d| dkrJ| dn | d| fdd|D} fdd|D} | | d<| | d<|rt| |d } |s|s|| d<d dtt|D| d<tt|}t|d }n tt| d}t|d }t| d||| | d \} } t | d| d| | d } |rTt |d|| | d\} } zt | d|| | d\} } Wntj | d<YnX| | fS)aM process rr-list Function that takes and processes a list of peak-peak intervals (tachogram). Computes all measures as computed by the regular process() function, and sets up all dicts required for plotting poincare plots. Note: This method assumes ms-based tachogram Several filtering methods are available as well. Parameters ---------- rr_list : 1d array or list list or array containing peak-peak intervals (in ms). threshold_rr : bool if true, the peak-peak intervals are cleaned using a threshold filter, which rejects all intervals that differ 30% from the mean peak-peak interval, with a minimum of 300ms. default : false clean_rr : bool if true, the RR_list is further cleaned with an outlier rejection pass. This pass is performed after threshold_rr, if that is specified. default : false clean_rr_method: str how to find and reject outliers. Available methods are 'quotient-filter', 'iqr' (interquartile range), and 'z-score'. default : 'quotient-filter' calc_freq : bool whether to compute time-series measurements default : False freq_method : str method used to extract the frequency spectrum. Available: 'fft' (Fourier Analysis), 'periodogram', and 'welch' (Welch's method). default : 'welch' welch_wsize : float Size of window (in sec) when welch method used to compute the spectrogram. This choice is based on a trade-off btw temporal res and freq res of the resulting spectrum 60 sec may seem reasonable, but this would greatly limit frequency resolution! 1/60 s = 0.017 Hz, so you would only have 2 points in the VLF band Therefore, the default is 4 min (9 points in the VLF band) default : 240 square_spectrum : bool whether to square the power spectrum returned. default : true measures : dict dictionary object used by heartpy to store computed measures. Will be created if not passed to function. working_data : dict dictionary object that contains all heartpy's working data (temp) objects. will be created if not passed to function Returns ------- working_data : dict dictionary object used to store temporary values. measures : dict dictionary object used by heartpy to store computed measures. Examples -------- Let's generate an RR-list first. >>> import heartpy as hp >>> data, timer = hp.load_exampledata(2) >>> sample_rate = hp.get_samplerate_datetime(timer, timeformat = '%Y-%m-%d %H:%M:%S.%f') >>> wd, m = hp.process(data, sample_rate) >>> rr_list = wd['RR_list'] Using only the RR-list (in ms!) we can now call this function, and let's put the results into a differently named container so we're sure all measures are unique: >>> wd2, m2 = process_rr(rr_list, threshold_rr = True, clean_rr = True, calc_freq = True) >>> '%.3f' %m2['rmssd'] '45.641' If you want to, you can turn off all filters and rejection features: >>> wd2, m2 = process_rr(rr_list, threshold_rr = False, clean_rr = False) >>> '%.3f' %m2['rmssd'] '162.645' In this case it seems the filtering was necessary: without the RMSSD lies outside the range expected in healthy humans. rCg333333?i,cs g|]}|kr|kr|qSr`r`.0xZlower_thresholdZupper_thresholdr`ra Uszprocess_rr..cs$g|]}|ks|krdndqS)r rr`rzr}r`rar~VsrErG)rArDcSsg|]}dqS)rr`)r{rur`r`rar~`s)rjrkrlrFrA)rjrr_maskrFrAr5rJrHrI) rRZmeanr*rangelenrVrppowerr+r.r,r-rW)rjZ threshold_rrr]r^rZr[rKrLr\rFrAZmean_rrZ rr_list_corrrkrlr`r}rar1sPa         c Csddlm}m}m}m}m}m}m}ddl}d} t d|j ||d} | j dkr`t d| d7} t d|j ||d} | j dkrt d| d7} t d |j ||d} | j dkrt d| d7} t d |j ||d} | j dkrt d| d7} t d |j ||d} | j dkr"t d| d7} t d |j ||d} | j dkrTt d| d7} t d |j ||d} | j dkrt d| d7} t dddlm } |j | |d} | j dkrt d| d7} | dkrt dnt ddS)z3 function to run doctest on all of HeartPy r )analysis datautils filtering peakdetection preprocessingvisualizeutilsr/rNztesting config)verbosezsuccess!ztesting analysisztesting datautilsztesting filteringztesting peakdetectionztesting preprocessingztesting visualization utilsz testing main processing pipeline)heartpyzall tests passed, ready to go!zsome tests failed...) rrrrrrr/doctestrXtestmodZfailedr) rrrrrrrr/rZ succeededresultsZhptesterr`r`rar3}s^$           )r4FFrr5FFFr6Fr7r8FFr9rFr:NN)rbrrcFrdre)r)B__doc__rrOosrMnumpyrRZscipy.interpolaterZ scipy.signalrrrrrr rr rr r rrrrrrrrrrrrrrrrrrrrrr r!r"r#rr$r%r&r'rr(r)r*r+r,r-r.r/init__all__r0r2r1r3r`r`r`ras    $  $   #