|
|
@@ -1,3 +1,4 @@
|
|
|
+from numpy import mod
|
|
|
import pandas as pd
|
|
|
from ChildProject.projects import ChildProject
|
|
|
from ChildProject.annotations import AnnotationManager
|
|
|
@@ -9,11 +10,12 @@ def compare_vandam(set1: str, set2: str) :
|
|
|
speakers = ['CHI', 'OCH', 'FEM', 'MAL']
|
|
|
project = ChildProject('vandam-data')
|
|
|
am = AnnotationManager(project)
|
|
|
- am.read()
|
|
|
+ #am.read()
|
|
|
|
|
|
#get segments that intercept between two annotations
|
|
|
intersection = AnnotationManager.intersection(am.annotations, [set1, set2])
|
|
|
|
|
|
+ #output directory
|
|
|
dirName = "outputs/compare/" + set1.replace("/","") + "-" + set2.replace("/","")
|
|
|
try:
|
|
|
# Create target Directory
|
|
|
@@ -22,6 +24,7 @@ def compare_vandam(set1: str, set2: str) :
|
|
|
except FileExistsError:
|
|
|
print("Directory " , dirName , " already exists")
|
|
|
|
|
|
+ #opens output file
|
|
|
file= open("{0}/{1}-{2}.txt".format(dirName, set1.replace("/",""), set2.replace("/","")),"a")
|
|
|
|
|
|
for speaker in speakers:
|
|
|
@@ -30,28 +33,30 @@ def compare_vandam(set1: str, set2: str) :
|
|
|
segments = am.get_collapsed_segments(intersection)
|
|
|
segments = segments[segments['speaker_type'].isin(pd.Series(speaker))]
|
|
|
|
|
|
- # set1_segm = segments_to_grid(segments[segments['set'] == set1], 0, segments['segment_offset'].max(), 100, 'speaker_type', speakers)
|
|
|
- # set2_segm = segments_to_grid(segments[segments['set'] == set2], 0, segments['segment_offset'].max(), 100, 'speaker_type', speakers)
|
|
|
-
|
|
|
-
|
|
|
ref = segments_to_annotation(segments[segments['set'] == set1], 'speaker_type')
|
|
|
hyp = segments_to_annotation(segments[segments['set'] == set2], 'speaker_type')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
+
|
|
|
+ #compute metrics
|
|
|
from pyannote.metrics.detection import DetectionPrecisionRecallFMeasure
|
|
|
metric = DetectionPrecisionRecallFMeasure()
|
|
|
|
|
|
detail = metric.compute_components(ref, hyp)
|
|
|
precision, recall, f = metric.compute_metrics(detail)
|
|
|
|
|
|
-
|
|
|
- # metric_output = str(f'{precision:.2f}/{recall:.2f}/{f:.2f}')
|
|
|
+ #saves metrics to output file
|
|
|
metric_output = "precision: {0} / recall : {1} / f: {2}\n".format(precision, recall, f)
|
|
|
file.write(speaker + ": " + metric_output)
|
|
|
print("Metrics [precision & recall & f] saved! for {0}".format(speaker))
|
|
|
file.close
|
|
|
-
|
|
|
|
|
|
+ #generates segments
|
|
|
+ set1_segm = segments_to_grid(segments[segments['set'] == set1], 0, segments['segment_offset'].max(), 100, 'speaker_type', speakers)
|
|
|
+ set2_segm = segments_to_grid(segments[segments['set'] == set2], 0, segments['segment_offset'].max(), 100, 'speaker_type', speakers)
|
|
|
+ matrix_df = pd.DataFrame(conf_matrix(set1_segm, set2_segm))
|
|
|
+ matrix_df.to_csv("{0}/{1}-{2}-confusion-matrix.csv".format(dirName, set1.replace("/",""), set2.replace("/","")), mode = "x", index=False)
|
|
|
+ print("Confusion matrix saved for {0} and {1}!".format(set1, set2))
|
|
|
|
|
|
compare_vandam('eaf', 'cha')
|
|
|
compare_vandam('eaf', 'cha/aligned')
|
