-
Notifications
You must be signed in to change notification settings - Fork 108
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
added marginal flag to segment.nce #227
Changes from 5 commits
07646c1
9a77c73
fce5e3e
a9d652b
db4e1f0
dae4dd5
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -28,21 +28,48 @@ | |
|
||
* :func:`mir_eval.segment.detection`: An estimated boundary is considered | ||
correct if it falls within a window around a reference boundary | ||
[#turnbull2007]_ | ||
* :func:`mir_eval.segment.deviation`: Computes the median absolute time | ||
difference from a reference boundary to its nearest estimated boundary, and | ||
vice versa | ||
vice versa [#turnbull2007]_ | ||
* :func:`mir_eval.segment.pairwise`: For classifying pairs of sampled time | ||
instants as belonging to the same structural component | ||
instants as belonging to the same structural component [#levy2008]_ | ||
* :func:`mir_eval.segment.rand_index`: Clusters reference and estimated | ||
annotations and compares them by the Rand Index | ||
* :func:`mir_eval.segment.ari`: Computes the Rand index, adjusted for chance | ||
* :func:`mir_eval.segment.nce`: Interprets sampled reference and estimated | ||
labels as samples of random variables :math:`Y_R, Y_E` from which the | ||
conditional entropy of :math:`Y_R` given :math:`Y_E` (Under-Segmentation) and | ||
:math:`Y_E` given :math:`Y_R` (Over-Segmentation) are estimated | ||
[#lukashevich2008]_ | ||
* :func:`mir_eval.segment.mutual_information`: Computes the standard, | ||
normalized, and adjusted mutual information of sampled reference and | ||
estimated segments | ||
* :func:`mir_eval.segment.vmeasure`: Computes the V-Measure, which is similar | ||
to the conditional entropy metrics, but uses the marginal distributions | ||
as normalization rather than the maximum entropy distribution | ||
[#rosenberg2007]_ | ||
|
||
|
||
References | ||
---------- | ||
.. [#turnbull2007] Turnbull, D., Lanckriet, G. R., Pampalk, E., | ||
& Goto, M. A Supervised Approach for Detecting Boundaries in Music | ||
Using Difference Features and Boosting. In ISMIR (pp. 51-54). | ||
|
||
.. [#levy2008] Levy, M., & Sandler, M. | ||
Structural segmentation of musical audio by constrained clustering. | ||
IEEE transactions on audio, speech, and language processing, 16(2), | ||
318-326. | ||
|
||
.. [#lukashevich2008] Lukashevich, H. M. | ||
Towards Quantitative Measures of Evaluating Song Segmentation. | ||
In ISMIR (pp. 375-380). | ||
|
||
.. [#rosenberg2007] Rosenberg, A., & Hirschberg, J. | ||
V-Measure: A Conditional Entropy-Based External Cluster Evaluation | ||
Measure. | ||
In EMNLP-CoNLL (Vol. 7, pp. 410-420). | ||
''' | ||
|
||
import collections | ||
|
@@ -912,7 +939,7 @@ def mutual_information(reference_intervals, reference_labels, | |
|
||
|
||
def nce(reference_intervals, reference_labels, estimated_intervals, | ||
estimated_labels, frame_size=0.1, beta=1.0): | ||
estimated_labels, frame_size=0.1, beta=1.0, marginal=False): | ||
"""Frame-clustering segmentation: normalized conditional entropy | ||
|
||
Computes cross-entropy of cluster assignment, normalized by the | ||
|
@@ -958,16 +985,27 @@ def nce(reference_intervals, reference_labels, estimated_intervals, | |
beta for F-measure | ||
(Default value = 1.0) | ||
|
||
marginal : bool | ||
If `False`, normalize conditional entropy by uniform entropy. | ||
If `True`, normalize conditional entropy by the marginal entropy. | ||
(Default value = False) | ||
|
||
Returns | ||
------- | ||
S_over | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Should we change the math in this part of the docstring to note that it can be different according to the value of |
||
Over-clustering score: | ||
``1 - H(y_est | y_ref) / log(|y_est|)`` | ||
- For `marginal=False`, ``1 - H(y_est | y_ref) / log(|y_est|)`` | ||
- For `marginal=True`, ``1 - H(y_est | y_ref) / H(y_est)`` | ||
|
||
If `|y_est|==1`, then `S_over` will be 0. | ||
|
||
S_under | ||
Under-clustering score: | ||
``1 - H(y_ref | y_est) / log(|y_ref|)`` | ||
- For `marginal=False`, ``1 - H(y_ref | y_est) / log(|y_ref|)`` | ||
- For `marginal=True`, ``1 - H(y_ref | y_est) / H(y_ref)`` | ||
|
||
If `|y_ref|==1`, then `S_under` will be 0. | ||
|
||
S_F | ||
F-measure for (S_over, S_under) | ||
|
||
|
@@ -1009,25 +1047,104 @@ def nce(reference_intervals, reference_labels, estimated_intervals, | |
# sum_i P[true = i | estimated = j] log P[true = i | estimated = j] | ||
# entropy sums over axis=0, which is true labels | ||
|
||
# The following scipy.stats.entropy calls are equivalent to | ||
# scipy.stats.entropy(contingency, base=2) | ||
# However the `base` kwarg has only been introduced in scipy 0.14.0 | ||
true_given_est = p_est.dot(scipy.stats.entropy(contingency) / np.log(2)) | ||
pred_given_ref = p_ref.dot(scipy.stats.entropy(contingency.T) / np.log(2)) | ||
true_given_est = p_est.dot(scipy.stats.entropy(contingency, base=2)) | ||
pred_given_ref = p_ref.dot(scipy.stats.entropy(contingency.T, base=2)) | ||
|
||
if marginal: | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Add comment to the effect of There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. done below |
||
# Normalize conditional entropy by marginal entropy | ||
z_ref = scipy.stats.entropy(p_ref, base=2) | ||
z_est = scipy.stats.entropy(p_est, base=2) | ||
else: | ||
z_ref = np.log2(contingency.shape[0]) | ||
z_est = np.log2(contingency.shape[1]) | ||
|
||
score_under = 0.0 | ||
if contingency.shape[0] > 1: | ||
score_under = 1. - true_given_est / np.log2(contingency.shape[0]) | ||
if z_ref > 0: | ||
score_under = 1. - true_given_est / z_ref | ||
|
||
score_over = 0.0 | ||
if contingency.shape[1] > 1: | ||
score_over = 1. - pred_given_ref / np.log2(contingency.shape[1]) | ||
if z_est > 0: | ||
score_over = 1. - pred_given_ref / z_est | ||
|
||
f_measure = util.f_measure(score_over, score_under, beta=beta) | ||
|
||
return score_over, score_under, f_measure | ||
|
||
|
||
def vmeasure(reference_intervals, reference_labels, estimated_intervals, | ||
estimated_labels, frame_size=0.1, beta=1.0): | ||
"""Frame-clustering segmentation: v-measure | ||
|
||
Computes cross-entropy of cluster assignment, normalized by the | ||
marginal-entropy. | ||
|
||
This is equivalent to `nce(..., marginal=True)`. | ||
|
||
Examples | ||
-------- | ||
>>> (ref_intervals, | ||
... ref_labels) = mir_eval.io.load_labeled_intervals('ref.lab') | ||
>>> (est_intervals, | ||
... est_labels) = mir_eval.io.load_labeled_intervals('est.lab') | ||
>>> # Trim or pad the estimate to match reference timing | ||
>>> (ref_intervals, | ||
... ref_labels) = mir_eval.util.adjust_intervals(ref_intervals, | ||
... ref_labels, | ||
... t_min=0) | ||
>>> (est_intervals, | ||
... est_labels) = mir_eval.util.adjust_intervals( | ||
... est_intervals, est_labels, t_min=0, t_max=ref_intervals.max()) | ||
>>> V_precision, V_recall, V_F = mir_eval.structure.vmeasure(ref_intervals, | ||
... ref_labels, | ||
... est_intervals, | ||
... est_labels) | ||
|
||
Parameters | ||
---------- | ||
reference_intervals : np.ndarray, shape=(n, 2) | ||
reference segment intervals, in the format returned by | ||
:func:`mir_eval.io.load_labeled_intervals`. | ||
reference_labels : list, shape=(n,) | ||
reference segment labels, in the format returned by | ||
:func:`mir_eval.io.load_labeled_intervals`. | ||
estimated_intervals : np.ndarray, shape=(m, 2) | ||
estimated segment intervals, in the format returned by | ||
:func:`mir_eval.io.load_labeled_intervals`. | ||
estimated_labels : list, shape=(m,) | ||
estimated segment labels, in the format returned by | ||
:func:`mir_eval.io.load_labeled_intervals`. | ||
frame_size : float > 0 | ||
length (in seconds) of frames for clustering | ||
(Default value = 0.1) | ||
beta : float > 0 | ||
beta for F-measure | ||
(Default value = 1.0) | ||
|
||
Returns | ||
------- | ||
V_precision | ||
Over-clustering score: | ||
``1 - H(y_est | y_ref) / H(y_est)`` | ||
|
||
If `|y_est|==1`, then `V_over` will be 0. | ||
|
||
V_recall | ||
Under-clustering score: | ||
``1 - H(y_ref | y_est) / H(y_ref)`` | ||
|
||
If `|y_ref|==1`, then `V_under` will be 0. | ||
|
||
V_F | ||
F-measure for (V_precision, V_recall) | ||
|
||
""" | ||
|
||
return nce(reference_intervals, reference_labels, | ||
estimated_intervals, estimated_labels, | ||
frame_size=frame_size, beta=beta, | ||
marginal=True) | ||
|
||
|
||
def evaluate(ref_intervals, ref_labels, est_intervals, est_labels, **kwargs): | ||
"""Compute all metrics for the given reference and estimated annotations. | ||
|
||
|
@@ -1122,4 +1239,9 @@ def evaluate(ref_intervals, ref_labels, est_intervals, est_labels, **kwargs): | |
util.filter_kwargs(nce, ref_intervals, ref_labels, est_intervals, | ||
est_labels, **kwargs) | ||
|
||
# V-measure metrics | ||
scores['V Precision'], scores['V Recall'], scores['V-measure'] = \ | ||
util.filter_kwargs(vmeasure, ref_intervals, ref_labels, est_intervals, | ||
est_labels, **kwargs) | ||
|
||
return scores |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.3333333333333333, "Recall@0.5": 0.6, "F-measure@0.5": 0.42857142857142855, "Precision@3.0": 0.5, "Recall@3.0": 0.9, "F-measure@3.0": 0.6428571428571429, "Ref-to-est deviation": 0.39899999999999958, "Est-to-ref deviation": 2.8474999999999997, "Pairwise Precision": 0.87442744102258263, "Pairwise Recall": 0.48068285131997418, "Pairwise F-measure": 0.6203513883678935, "Rand Index": 0.82890773118312333, "Adjusted Rand Index": 0.52166883969499556, "Mutual Information": 1.1375211793868052, "Adjusted Mutual Information": 0.58737925867857188, "Normalized Mutual Information": 0.6939260940391484, "NCE Over": 0.61991743813038624, "NCE Under": 0.85694667760167753, "NCE F-measure": 0.71941105933073668} | ||
{"Precision@0.5": 0.3333333333333333, "Recall@0.5": 0.6, "F-measure@0.5": 0.42857142857142855, "Precision@3.0": 0.5, "Recall@3.0": 0.9, "F-measure@3.0": 0.6428571428571429, "Ref-to-est deviation": 0.3989999999999996, "Est-to-ref deviation": 2.8474999999999997, "Pairwise Precision": 0.8744274410225826, "Pairwise Recall": 0.4806828513199742, "Pairwise F-measure": 0.6203513883678935, "Rand Index": 0.8289077311831233, "Adjusted Rand Index": 0.5216688396951437, "Mutual Information": 1.1375211793868052, "Adjusted Mutual Information": 0.587379258678572, "Normalized Mutual Information": 0.6939260940391484, "NCE Over": 0.6199174381303865, "NCE Under": 0.8569466776016775, "NCE F-measure": 0.719411059330737, "V Precision": 0.590037137766286, "V Recall": 0.8161069755903478, "V-measure": 0.6848991073026666} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.5454545454545454, "Recall@0.5": 0.4, "F-measure@0.5": 0.4615384615384615, "Precision@3.0": 0.5454545454545454, "Recall@3.0": 0.4, "F-measure@3.0": 0.4615384615384615, "Ref-to-est deviation": 13.036000000000001, "Est-to-ref deviation": 0.33599999999999852, "Pairwise Precision": 0.49939016579260981, "Pairwise Recall": 0.61221319846233357, "Pairwise F-measure": 0.55007615218121908, "Rand Index": 0.75410460884145092, "Adjusted Rand Index": 0.38328718826533731, "Mutual Information": 0.82985003780999334, "Adjusted Mutual Information": 0.54769702660154485, "Normalized Mutual Information": 0.57269506013770199, "NCE Over": 0.71234956156918239, "NCE Under": 0.61984178395916567, "NCE F-measure": 0.66288378847027396} | ||
{"Precision@0.5": 0.5454545454545454, "Recall@0.5": 0.4, "F-measure@0.5": 0.4615384615384615, "Precision@3.0": 0.5454545454545454, "Recall@3.0": 0.4, "F-measure@3.0": 0.4615384615384615, "Ref-to-est deviation": 13.036000000000001, "Est-to-ref deviation": 0.3359999999999985, "Pairwise Precision": 0.4993901657926098, "Pairwise Recall": 0.6122131984623336, "Pairwise F-measure": 0.5500761521812191, "Rand Index": 0.7541046088414509, "Adjusted Rand Index": 0.383287188265407, "Mutual Information": 0.8298500378099933, "Adjusted Mutual Information": 0.5476970266015448, "Normalized Mutual Information": 0.572695060137702, "NCE Over": 0.7123495615691824, "NCE Under": 0.6198417839591657, "NCE F-measure": 0.662883788470274, "V Precision": 0.59718972940023, "V Recall": 0.5492050779833786, "V-measure": 0.572193156831662} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.08333333333333333, "Recall@0.5": 0.18181818181818182, "F-measure@0.5": 0.1142857142857143, "Precision@3.0": 0.20833333333333334, "Recall@3.0": 0.45454545454545453, "F-measure@3.0": 0.28571428571428575, "Ref-to-est deviation": 2.4509999999999934, "Est-to-ref deviation": 7.9399999999999995, "Pairwise Precision": 0.26723175107093661, "Pairwise Recall": 0.81680356275045607, "Pairwise F-measure": 0.40270984454432168, "Rand Index": 0.53199299824956237, "Adjusted Rand Index": 0.15746191367526505, "Mutual Information": 0.5875580090173057, "Adjusted Mutual Information": 0.31916695064697315, "Normalized Mutual Information": 0.45897667736089354, "NCE Over": 0.84069380192324406, "NCE Under": 0.4364389820106126, "NCE F-measure": 0.57458637302198445} | ||
{"Precision@0.5": 0.08333333333333333, "Recall@0.5": 0.18181818181818182, "F-measure@0.5": 0.1142857142857143, "Precision@3.0": 0.20833333333333334, "Recall@3.0": 0.45454545454545453, "F-measure@3.0": 0.28571428571428575, "Ref-to-est deviation": 2.4509999999999934, "Est-to-ref deviation": 7.9399999999999995, "Pairwise Precision": 0.2672317510709366, "Pairwise Recall": 0.8168035627504561, "Pairwise F-measure": 0.4027098445443217, "Rand Index": 0.5319929982495624, "Adjusted Rand Index": 0.15746191367518272, "Mutual Information": 0.5875580090173058, "Adjusted Mutual Information": 0.31916695064697315, "Normalized Mutual Information": 0.4589766773608936, "NCE Over": 0.840693801923244, "NCE Under": 0.4364389820106126, "NCE F-measure": 0.5745863730219845, "V Precision": 0.6546216709365502, "V Recall": 0.32180356947221267, "V-measure": 0.4314914888375012} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.18181818181818182, "Recall@0.5": 0.15384615384615385, "F-measure@0.5": 0.16666666666666669, "Precision@3.0": 0.5454545454545454, "Recall@3.0": 0.46153846153846156, "F-measure@3.0": 0.4999999999999999, "Ref-to-est deviation": 2.8320000000000078, "Est-to-ref deviation": 1.6999999999999957, "Pairwise Precision": 0.79542476842193111, "Pairwise Recall": 0.20372577015066376, "Pairwise F-measure": 0.32437258908988192, "Rand Index": 0.61716466119017321, "Adjusted Rand Index": 0.17206814668514248, "Mutual Information": 0.70699805971863017, "Adjusted Mutual Information": 0.32288437024230487, "Normalized Mutual Information": 0.47183488839912169, "NCE Over": 0.36093183448445643, "NCE Under": 0.79892409459630565, "NCE F-measure": 0.49722923657425966} | ||
{"Precision@0.5": 0.18181818181818182, "Recall@0.5": 0.15384615384615385, "F-measure@0.5": 0.16666666666666669, "Precision@3.0": 0.5454545454545454, "Recall@3.0": 0.46153846153846156, "F-measure@3.0": 0.4999999999999999, "Ref-to-est deviation": 2.832000000000008, "Est-to-ref deviation": 1.6999999999999957, "Pairwise Precision": 0.7954247684219311, "Pairwise Recall": 0.20372577015066376, "Pairwise F-measure": 0.3243725890898819, "Rand Index": 0.6171646611901732, "Adjusted Rand Index": 0.17206814668546003, "Mutual Information": 0.7069980597186302, "Adjusted Mutual Information": 0.3228843702423049, "Normalized Mutual Information": 0.4718348883991217, "NCE Over": 0.36093183448445665, "NCE Under": 0.7989240945963056, "NCE F-measure": 0.4972292365742599, "V Precision": 0.32453331344779024, "V Recall": 0.6859947890878926, "V-measure": 0.44061745804392516} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.2, "Recall@0.5": 0.5, "F-measure@0.5": 0.28571428571428575, "Precision@3.0": 0.3, "Recall@3.0": 0.75, "F-measure@3.0": 0.4285714285714285, "Ref-to-est deviation": 0.28300000000000125, "Est-to-ref deviation": 5.5510000000000055, "Pairwise Precision": 0.92595043607953142, "Pairwise Recall": 0.35218495476813033, "Pairwise F-measure": 0.51028367539674546, "Rand Index": 0.76348025201081549, "Adjusted Rand Index": 0.39329787297570201, "Mutual Information": 0.97537746604020625, "Adjusted Mutual Information": 0.46809981616245017, "Normalized Mutual Information": 0.65315661235201594, "NCE Over": 0.49896823783207223, "NCE Under": 0.91017263905977475, "NCE F-measure": 0.64457322228326619} | ||
{"Precision@0.5": 0.2, "Recall@0.5": 0.5, "F-measure@0.5": 0.28571428571428575, "Precision@3.0": 0.3, "Recall@3.0": 0.75, "F-measure@3.0": 0.4285714285714285, "Ref-to-est deviation": 0.28300000000000125, "Est-to-ref deviation": 5.5510000000000055, "Pairwise Precision": 0.9259504360795314, "Pairwise Recall": 0.35218495476813033, "Pairwise F-measure": 0.5102836753967455, "Rand Index": 0.7634802520108155, "Adjusted Rand Index": 0.3932978729758545, "Mutual Information": 0.9753774660402063, "Adjusted Mutual Information": 0.46809981616245017, "Normalized Mutual Information": 0.6531566123520159, "NCE Over": 0.4989682378320722, "NCE Under": 0.9101726390597747, "NCE F-measure": 0.6445732222832662, "V Precision": 0.4697768990421939, "V Recall": 0.9081194948686581, "V-measure": 0.619224438273351} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.38095238095238093, "Recall@0.5": 0.4444444444444444, "F-measure@0.5": 0.41025641025641024, "Precision@3.0": 0.47619047619047616, "Recall@3.0": 0.5555555555555556, "F-measure@3.0": 0.5128205128205129, "Ref-to-est deviation": 0.88450000000000273, "Est-to-ref deviation": 2.0920000000000414, "Pairwise Precision": 0.89361985851541192, "Pairwise Recall": 0.12923035832531626, "Pairwise F-measure": 0.22580591492517105, "Rand Index": 0.60576268180034554, "Adjusted Rand Index": 0.12775042299122708, "Mutual Information": 0.8118894611245796, "Adjusted Mutual Information": 0.28579555410413998, "Normalized Mutual Information": 0.4958259732497331, "NCE Over": 0.32765438933312696, "NCE Under": 0.90127193904104264, "NCE F-measure": 0.48059139102383153} | ||
{"Precision@0.5": 0.38095238095238093, "Recall@0.5": 0.4444444444444444, "F-measure@0.5": 0.41025641025641024, "Precision@3.0": 0.47619047619047616, "Recall@3.0": 0.5555555555555556, "F-measure@3.0": 0.5128205128205129, "Ref-to-est deviation": 0.8845000000000027, "Est-to-ref deviation": 2.0920000000000414, "Pairwise Precision": 0.8936198585154119, "Pairwise Recall": 0.12923035832531626, "Pairwise F-measure": 0.22580591492517105, "Rand Index": 0.6057626818003455, "Adjusted Rand Index": 0.12775042299090225, "Mutual Information": 0.8118894611245795, "Adjusted Mutual Information": 0.2857955541041399, "Normalized Mutual Information": 0.49582597324973304, "NCE Over": 0.32765438933312685, "NCE Under": 0.9012719390410426, "NCE F-measure": 0.48059139102383136, "V Precision": 0.28728701796701817, "V Recall": 0.8557414027572561, "V-measure": 0.43016147506335445} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
{"Precision@0.5": 0.6, "Recall@0.5": 0.5, "F-measure@0.5": 0.5454545454545454, "Precision@3.0": 0.9, "Recall@3.0": 0.75, "F-measure@3.0": 0.8181818181818182, "Ref-to-est deviation": 0.37199999999999966, "Est-to-ref deviation": 0.13499999999999779, "Pairwise Precision": 0.79309065091812692, "Pairwise Recall": 0.42685807583415836, "Pairwise F-measure": 0.55500225835591688, "Rand Index": 0.77792616886153987, "Adjusted Rand Index": 0.42429770750008716, "Mutual Information": 1.0358589237639091, "Adjusted Mutual Information": 0.55223481569673849, "Normalized Mutual Information": 0.66743178237377987, "NCE Over": 0.62388170665293718, "NCE Under": 0.85624576821215703, "NCE F-measure": 0.72182441074576342} | ||
{"Precision@0.5": 0.6, "Recall@0.5": 0.5, "F-measure@0.5": 0.5454545454545454, "Precision@3.0": 0.9, "Recall@3.0": 0.75, "F-measure@3.0": 0.8181818181818182, "Ref-to-est deviation": 0.37199999999999966, "Est-to-ref deviation": 0.1349999999999978, "Pairwise Precision": 0.7930906509181269, "Pairwise Recall": 0.42685807583415836, "Pairwise F-measure": 0.5550022583559169, "Rand Index": 0.7779261688615399, "Adjusted Rand Index": 0.4242977075000336, "Mutual Information": 1.035858923763909, "Adjusted Mutual Information": 0.5522348156967383, "Normalized Mutual Information": 0.6674317823737799, "NCE Over": 0.6238817066529372, "NCE Under": 0.856245768212157, "NCE F-measure": 0.7218244107457634, "V Precision": 0.5562329768516343, "V Recall": 0.8008607951366766, "V-measure": 0.6564987524332658} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add
(Default value = False)
for consistency within this docstring.