vocalpy.metrics.segmentation.ir.find_hits

vocalpy.metrics.segmentation.ir.find_hits(hypothesis: ndarray[Any, dtype[_ScalarType_co]], reference: ndarray[Any, dtype[_ScalarType_co]], tolerance: float | int | None = None, decimals: int | None = None) → tuple[ndarray[Any, dtype[_ScalarType_co]], ndarray[Any, dtype[_ScalarType_co]], ndarray[Any, dtype[_ScalarType_co]]]

Find hits in arrays of event times.

This is a helper function used to compute information retrieval metrics. Specifically, this function is called by precision_recall_fscore().

An element in hypothesis, is considered a hit if its value \(t_h\) falls within an interval around any value in reference, \(t_0\), plus or minus tolerance

\(t_0 - \Delta t < t < t_0 + \Delta t\)

This function only allows there to be zero or one hit for each element in reference, but not more than one. If the condition \(|ref_i - hyp_j| < tolerance\) is true for multiple values \(hyp_j\) in hypothesis, then the value with the smallest difference from \(ref_i\) is considered a hit.

Both hypothesis and reference must be 1-dimensional arrays of non-negative, strictly increasing values. If you have two arrays onsets and offsets, you can concatenate those into a single valid array of boundary times using concat_starts_and_stops() that you can then pass to this function.

Parameters:

hypothesisnumpy.ndarray

Boundaries, e.g., onsets or offsets of segments, as computed by some method.

referencenumpy.ndarray

Ground truth boundaries that the hypothesized boundaries hypothesis are compared to.

metricstr

The name of the metric to compute. One of: {"precision", "recall", "fscore"}.

tolerancefloat or int

Tolerance, in seconds. Elements in hypothesis are considered a true positive if they are within a time interval around any reference boundary \(t_0\) in reference plus or minus the tolerance, i.e., if a hypothesized boundary \(t_h\) is within the interval \(t_0 - \Delta t < t < t_0 + \Delta t\). Default is None, in which case it is set to 0 (either float or int, depending on the dtype of hypothesis and reference). See notes for more detail.

decimals: int

The number of decimal places to round both hypothesis and reference to, using numpy.round(). This mitigates inflated error rates due to floating point error. Rounding is only applied if both hypothesis and reference are floating point values. To avoid rounding, e.g. to compute strict precision and recall, pass in the value False. Default is 3, which assumes that the values are in seconds and should be rounded to milliseconds.

Returns:

hits_refnumpy.ndarray

The indices of hits in reference.

hits_hypnumpy.ndarray

The indices of hits in hypothesis.

diffsnumpy.ndarray

Absolute differences \(|hit^{ref}_i - hit^{hyp}_i|\), i.e., np.abs(reference[hits_ref] - hypothesis[hits_hyp]).