o s·¯iã@sBdZddlZddlmZddlZdZdd„Zd d d „Zd d „ZdS)aç The goal of an onset detection algorithm is to automatically determine when notes are played in a piece of music. The primary method used to evaluate onset detectors is to first determine which estimated onsets are "correct", where correctness is defined as being within a small window of a reference onset. Based in part on this script: https://github.com/CPJKU/onset_detection/blob/master/onset_evaluation.py Conventions ----------- Onsets should be provided in the form of a 1-dimensional array of onset times in seconds in increasing order. Metrics ------- * :func:`mir_eval.onset.f_measure`: Precision, Recall, and F-measure scores based on the number of estimated onsets which are sufficiently close to reference onsets. éNé)ÚutilgLÝ@cCsF|jdkr t d¡|jdkrt d¡||fD]}t |t¡qdS)a:Check that the input annotations to a metric look like valid onset time arrays, and throws helpful errors if not. Parameters ---------- reference_onsets : np.ndarray reference onset locations, in seconds estimated_onsets : np.ndarray estimated onset locations, in seconds rzReference onsets are empty.zEstimated onsets are empty.N)ÚsizeÚwarningsÚwarnrÚvalidate_eventsÚMAX_TIME)Úreference_onsetsÚestimated_onsetsÚonsets©r úB/home/ubuntu/.local/lib/python3.10/site-packages/mir_eval/onset.pyÚvalidate#s    ÿrçš™™™™™©?cCsjt||ƒ|jdks|jdkrdSt |||¡}tt|ƒƒt|ƒ}tt|ƒƒt|ƒ}t ||¡||fS)aµCompute the F-measure of correct vs incorrectly predicted onsets. "Correctness" is determined over a small window. Examples -------- >>> reference_onsets = mir_eval.io.load_events('reference.txt') >>> estimated_onsets = mir_eval.io.load_events('estimated.txt') >>> F, P, R = mir_eval.onset.f_measure(reference_onsets, ... estimated_onsets) Parameters ---------- reference_onsets : np.ndarray reference onset locations, in seconds estimated_onsets : np.ndarray estimated onset locations, in seconds window : float Window size, in seconds (Default value = .05) Returns ------- f_measure : float 2*precision*recall/(precision + recall) precision : float (# true positives)/(# true positives + # false positives) recall : float (# true positives)/(# true positives + # false negatives) r)çrr)rrrÚ match_eventsÚfloatÚlenÚ f_measure)r r ÚwindowÚmatchingÚ precisionÚrecallr r r r8s rcKs4t ¡}tjt||fi|¤Ž\|d<|d<|d<|S)aNCompute all metrics for the given reference and estimated annotations. Examples -------- >>> reference_onsets = mir_eval.io.load_events('reference.txt') >>> estimated_onsets = mir_eval.io.load_events('estimated.txt') >>> scores = mir_eval.onset.evaluate(reference_onsets, ... estimated_onsets) Parameters ---------- reference_onsets : np.ndarray reference onset locations, in seconds estimated_onsets : np.ndarray estimated onset locations, in seconds **kwargs Additional keyword arguments which will be passed to the appropriate metric or preprocessing functions. Returns ------- scores : dict Dictionary of scores, where the key is the metric name (str) and the value is the (float) score achieved. z F-measureÚ PrecisionÚRecall)Ú collectionsÚ OrderedDictrÚ filter_kwargsr)r r ÚkwargsÚscoresr r r Úevaluateesÿÿr )r) Ú__doc__rÚrrrrrr r r r r Ús   -