o si7Y@sdZddlZddlZddlZddlZddlZddlm Z ddlm Z ddlm Z ej ddZ d(d d Zd(d dZd(ddZd(ddZd(ddZd(ddZddZe jdddd)ddZd(dd Zd(d!d"Zd(d#d$Zed d%d fd&d'ZdS)*zBFunctions for loading annotations from files in different formats.N)util)key)tempoc kst|dr |VdSz t|fi| }|VWdWdS1s$wYWdSty?}ztd||d}~ww)zEither open a file handle, or use an existing file-like object. If `file_or_path` has the `read` attribute, it will return `file_or_path`. Otherwise, it will attempt to open the file at the specified location. readNzInvalid file-or-path object: )hasattropen TypeErrorIOError) file_or_pathkwargs file_descexcr?/home/ubuntu/.local/lib/python3.10/site-packages/mir_eval/io.py_opens  &r\s+#cCs6t|}tddt|D}t|}|durd}ntd|}t|dd`}t|dD]R\} } |dur=|| r=q/|| |d} |t| krZt d |t| || | t | ||D] \} } }z|| }Wnt d | |j || | | |q`q/Wdn1swY|dkr|d S|S) a^Load data from an annotation file where columns are delimited. The number of columns is inferred from the length of the provided converters list. Examples -------- >>> # Load in a one-column list of event times (floats) >>> load_delimited('events.txt', [float]) >>> # Load in a list of labeled events, separated by commas >>> load_delimited('labeled_events.csv', [float, str], ',') Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file converters : list of functions Each entry in column ``n`` of the file will be cast by the function ``converters[n]``. delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- columns : tuple of lists Each list in this tuple corresponds to values in one of the columns in the file. css|]}tVqdS)N)list).0_rrr Fsz!load_delimited..N^rmoderz+Expected {} columns, got {} at {}:{:d}: {}8Couldn't convert value {} using {} found at {}:{:d}: {}r)lentuplerangerecompiler enumeratematchsplitstrip ValueErrorformatzip__name__append)filename converters delimitercomment n_columnscolumnssplitter commenter input_filerowlinedatavaluecolumn converterconverted_valuerrrload_delimited sB%     r;c Csdt|tg||d}t|}zt|W|Sty1}zt|j dWYd}~|Sd}~ww)aImport time-stamp events from an annotation file. The file should consist of a single column of numeric values corresponding to the event times. This is primarily useful for processing events which lack duration, such as beats or onsets. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- event_times : np.ndarray array of event times (float) r-r.rN) r;floatnparrayrvalidate_eventsr&warningswarnargs)r+r-r.eventserrorrrr load_events{s  rFc Csrt|ttg||d\}}t|}z t|W||fSty8}zt |j dWYd}~||fSd}~ww)aImport labeled time-stamp events from an annotation file. The file should consist of two columns; the first having numeric values corresponding to the event times and the second having string labels for each event. This is primarily useful for processing labeled events which lack duration, such as beats with metric beat number or onsets with an instrument label. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- event_times : np.ndarray array of event times (float) labels : list of str list of labels r<rN) r;r=strr>r?rr@r&rArBrC)r+r-r.rDlabelsrErrrload_labeled_eventss   rIc Cspt|ttg||d\}}t||gj}zt|W|Sty7}zt |j dWYd}~|Sd}~ww)a;Import intervals from an annotation file. The file should consist of two columns of numeric values corresponding to start and end time of each interval. This is primarily useful for processing events which span a duration, such as segmentation, chords, or instrument activation. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- intervals : np.ndarray, shape=(n_events, 2) array of event start and end times r<rN r;r=r>r?Trvalidate_intervalsr&rArBrC)r+r-r.startsends intervalsrErrrload_intervalss   rPc Cs|t|tttg||d\}}}t||gj}z t|W||fSty=}zt |j dWYd}~||fSd}~ww)aImport labeled intervals from an annotation file. The file should consist of three columns: Two consisting of numeric values corresponding to start and end time of each interval and a third corresponding to the label of each interval. This is primarily useful for processing events which span a duration, such as segmentation, chords, or instrument activation. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- intervals : np.ndarray, shape=(n_events, 2) array of event start and end time labels : list of str list of labels r<rN) r;r=rGr>r?rKrrLr&rArBrC)r+r-r.rMrNrHrOrErrrload_labeled_intervalss  rQcCs4t|ttg||d\}}t|}t|}||fS)aImport a time series from an annotation file. The file should consist of two columns of numeric values corresponding to the time and value of each sample of the time series. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- times : np.ndarray array of timestamps (float) values : np.ndarray array of corresponding numeric values (float) r<)r;r=r>r?)r+r-r.timesvaluesrrrload_time_series%s    rTcCsg}g}g}t|ddk}|D]C}d|vr.|gkr |||gkr)||g}g}qd|vr>|gkr;||g}q|d}t|dt|df}||q|gkr^|||gkro||Wd|SWd|S1szwY|S) aLoad the patterns contained in the filename and puts them into a list of patterns, each pattern being a list of occurrence, and each occurrence being a list of (onset, midi) pairs. The input file must be formatted as described in MIREX 2013: http://www.music-ir.org/mirex/wiki/2013:Discovery_of_Repeated_Themes_%26_Sections Parameters ---------- filename : str or `os.Pathlike` The input file path containing the patterns of a given piece using the MIREX 2013 format. Returns ------- pattern_list : list The list of patterns, containing all their occurrences, using the following format:: onset_midi = (onset_time, midi_number) occurrence = [onset_midi1, ..., onset_midiO] pattern = [occurrence1, ..., occurrenceM] pattern_list = [pattern1, ..., patternN] where ``N`` is the number of patterns, ``M[i]`` is the number of occurrences of the ``i`` th pattern, and ``O[j]`` is the number of onsets in the ``j``'th occurrence. E.g.:: occ1 = [(0.5, 67.0), (1.0, 67.0), (1.5, 67.0), (2.0, 64.0)] occ2 = [(4.5, 65.0), (5.0, 65.0), (5.5, 65.0), (6.0, 62.0)] pattern1 = [occ1, occ2] occ1 = [(10.5, 67.0), (11.0, 67.0), (11.5, 67.0), (12.0, 64.0), (12.5, 69.0), (13.0, 69.0), (13.5, 69.0), (14.0, 67.0), (14.5, 76.0), (15.0, 76.0), (15.5, 76.0), (16.0, 72.0)] occ2 = [(18.5, 67.0), (19.0, 67.0), (19.5, 67.0), (20.0, 62.0), (20.5, 69.0), (21.0, 69.0), (21.5, 69.0), (22.0, 67.0), (22.5, 77.0), (23.0, 77.0), (23.5, 77.0), (24.0, 74.0)] pattern2 = [occ1, occ2] pattern_list = [pattern1, pattern2] rrpattern occurrence,rrN)r readlinesr*r$r=)r+ pattern_listrUrVr3r5 string_values onset_midirrr load_patternsKs@,          r\z0.8.1z0.9.0)versionversion_removedTcCstjj|\}}|jdkr|td}n |jdkr!|td}n|jdkr-|td}ntd|j|rB|jdkrB|j dd }||fS) aLoad a .wav file as a numpy array using ``scipy.io.wavfile``. .. warning:: This function is deprecatred in mir_eval 0.8.1 and will be removed in 0.9.0. We recommend using a dedicated audio IO library such as `soundfile` instead. Parameters ---------- path : str or `os.Pathlike` Path to a .wav file mono : bool If the provided .wav has more than one channel, it will be converted to mono if ``mono=True``. (Default value = True) Returns ------- audio_data : np.ndarray Array of audio samples, normalized to the range [-1., 1.] fs : int Sampling rate of the audio data int8int16iint32iz Got unexpected .wav data type {}r)axis) scipyiowavfilerdtyper=r&r'ndimmean)pathmonofs audio_datarrrload_wavs    rnc Cst|tttg||d\}}}t||gj}zt|Wnty7}zt |j dWYd}~nd}~wwt|}||fS)aImport valued intervals from an annotation file. The file should consist of three columns: Two consisting of numeric values corresponding to start and end time of each interval and a third, also of numeric values, corresponding to the value of each interval. This is primarily useful for processing events which span a duration and have a numeric value, such as piano-roll notes which have an onset, offset, and a pitch value. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- intervals : np.ndarray, shape=(n_events, 2) Array of event start and end times values : np.ndarray, shape=(n_events,) Array of values r<rNrJ)r+r-r.rMrNrSrOrErrrload_valued_intervalss   roc Cst|ttg||d\}}t|dkrtd|d|d}}|d|}zt|W|StyI}zt|jdWYd}~|Sd}~ww)aLoad key labels from an annotation file. The file should consist of two string columns: One denoting the key scale degree (semitone), and the other denoting the mode (major or minor). The file should contain only one row. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- key : str Key label, in the form ``'(key) (mode)'`` r<rz&Key file should contain only one line.r N) r;rGrr&r validate_keyrArBrC)r+r-r.scaler key_stringrErrrload_keys   rtc Cst|tttg||d\}}}|d}t||g}t|dkr#tdzt|WntyD}zt |j dWYd}~nd}~wwd|krOdksWntd|||fS)aLoad tempo estimates from an annotation file in MIREX format. The file should consist of three numeric columns: the first two correspond to tempo estimates (in beats-per-minute), and the third denotes the relative confidence of the first value compared to the second (in the range [0, 1]). The file should contain only one row. Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- tempi : np.ndarray, non-negative The two tempo estimates weight : float [0, 1] The relative importance of ``tempi[0]`` compared to ``tempi[1]`` r<rrz(Tempo file should contain only one line.NzInvalid weight: ) r;r=r> concatenaterr&rvalidate_tempirArBrC)r+r-r.t1t2weighttempirErrr load_tempos   r{Fc Cshg}g}t|}|durd}ntd|}|rd} nd} t|dd} t| | D]r\} } |dur9|| r9q+|| } zt| d}Wntt fye}zt d | dtj || | |d}~ww| |z t j| dd|d}Wntt fy}zt d | dd|j || | |d}~ww| |q+Wdn1swYt ||fS) aLoad data from a delimited time series annotation file with a variable number of columns. This function assumes that column 0 contains time stamps and columns 1 through n contain values. n may be variable from time stamp to time stamp. Examples -------- >>> # Load a ragged list of tab-delimited multi-f0 midi notes >>> times, vals = load_ragged_time_series('multif0.txt', dtype=int, delimiter='\t') >>> # Load a raggled list of space delimited multi-f0 values with a header >>> times, vals = load_ragged_time_series('labeled_events.csv', header=True) Parameters ---------- filename : str or `os.Pathlike` Path to the annotation file dtype : function Data type to apply to values columns. delimiter : str Separator regular expression. By default, lines will be split by any amount of whitespace. header : bool Indicates whether a header row is present or not. By default, assumes no header is present. comment : str or None Comment regular expression. Any lines beginning with this string or pattern will be ignored. Setting to `None` disables comments. Returns ------- times : np.ndarray array of timestamps (float) values : list of np.ndarray list of arrays of corresponding values Nrrrrrr)rg)r r!rr"r#r$r%r=r r&r'r)r*r>r?)r+rgr-headerr.rRrSr1r2 start_rowr3r4r5r6converted_timeexer:rrrload_ragged_time_seriesRsZ2    r)rr)T)__doc__ contextlibnumpyr>r rAscipy.io.wavfilerdrrrcontextmanagerrr;rFrIrPrQrTr\ deprecatedrnrortr{r=rrrrrs2      [ ' , * -& M  ' 1 -5