cleanup tests - create existing dataset

tests/.gitignore

@@ -0,0 +1,2 @@
+#dataset copied for tests, similar to existing_dataset
+test_dataset

tests/__init__.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Nov  7 12:20:55 2022
+
+@author: lpeurey
+"""
+
+

tests/existing_dataset/annotations/acoustic/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,33 @@
+segment_onset,segment_offset,speaker_type,recording_filename,mean_pitch_semitone,median_pitch_semitone,p5_pitch_semitone,p95_pitch_semitone,pitch_range_semitone,raw_filename
+716,1091,OCH,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,29.492868065520707,30.138642702884987,20.92657938524721,38.043171039925696,17.116591654678484,ACOUSTIC_VTC_20220103.csv
+788,1335,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,29.21464342185676,33.11085884127924,8.643340281901134,37.13355658578659,28.49021630388546,ACOUSTIC_VTC_20220103.csv
+969,2473,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,29.298045163512683,32.88547138489501,16.117759395143267,36.702404352700434,20.584644957557167,ACOUSTIC_VTC_20220103.csv
+1939,2354,OCH,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,30.428308088316903,34.61281831343323,15.920787817807724,37.36111941428427,21.440331596476543,ACOUSTIC_VTC_20220103.csv
+3086,4515,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.555790687873063,25.43977444107606,9.468522269335493,38.91392066067757,29.44539839134208,ACOUSTIC_VTC_20220103.csv
+4703,4887,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,33.291505212128094,33.965485866935126,29.417243345500275,36.839583257883376,7.422339912383101,ACOUSTIC_VTC_20220103.csv
+5505,6600,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,25.238233859752956,25.98407828936643,8.463363614308186,36.31506800615161,27.851704391843427,ACOUSTIC_VTC_20220103.csv
+7341,13185,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.37067866410465,27.750854514520757,8.341604446398945,35.09095086550627,26.74934641910733,ACOUSTIC_VTC_20220103.csv
+12083,12444,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,29.956301863760103,28.88535975974367,28.714569368207133,34.608363509762654,5.893794141555521,ACOUSTIC_VTC_20220103.csv
+12590,13373,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,30.885068902158533,32.25262782345649,15.867153956619152,37.06109220660275,21.1939382499836,ACOUSTIC_VTC_20220103.csv
+14342,16227,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,27.09942525284052,30.1316705155409,4.900098987854256,36.36432738460256,31.464228396748297,ACOUSTIC_VTC_20220103.csv
+16544,19425,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.81333654410509,29.79400943252938,6.3135133339207385,35.052483607526085,28.738970273605347,ACOUSTIC_VTC_20220103.csv
+19011,20491,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,29.44086771482358,31.30927236046787,14.25502037838229,35.78714023878623,21.532119860403935,ACOUSTIC_VTC_20220103.csv
+19043,19185,OCH,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,32.98295998189534,32.584870544859385,32.48382047902467,33.98404020556487,1.5002197265401946,ACOUSTIC_VTC_20220103.csv
+19565,19676,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,33.23750268763251,32.63508196392748,31.840505612731988,35.47788877572007,3.63738316298808,ACOUSTIC_VTC_20220103.csv
+19992,20350,MAL,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,23.984203441734014,29.978572686536808,10.764177536575712,30.938970827336167,20.17479329076045,ACOUSTIC_VTC_20220103.csv
+20819,21492,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,25.97211091302584,27.786858031123916,11.930542688627892,34.3079964640147,22.377453775386805,ACOUSTIC_VTC_20220103.csv
+21371,22532,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,28.63344638844196,28.605046698194336,18.85412445160436,38.6102602617787,19.75613581017434,ACOUSTIC_VTC_20220103.csv
+22341,22489,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.353878009435352,27.44041358276357,7.962495806926718,37.03103765999722,29.068541853070503,ACOUSTIC_VTC_20220103.csv
+23011,32954,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,25.77530730000921,26.83477640238156,8.893634420293438,37.358931057908656,28.465296637615214,ACOUSTIC_VTC_20220103.csv
+31303,31511,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,28.0041265711964,27.788575894455448,27.13021350366272,29.700172038814195,2.569958535151475,ACOUSTIC_VTC_20220103.csv
+33289,35014,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.25148665734396,28.7330051925927,9.870414118088515,31.4329577243406,21.562543606252085,ACOUSTIC_VTC_20220103.csv
+34493,34922,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,23.198844317955512,29.349953897341493,6.124320718231403,31.32871567051676,25.204394952285355,ACOUSTIC_VTC_20220103.csv
+35669,44992,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,24.46009596997296,27.40269404244497,6.9129786644071,35.560134764118054,28.647156099710955,ACOUSTIC_VTC_20220103.csv
+35675,36011,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,27.16001249135059,31.49551718224296,6.488738913265618,33.956207690162906,27.467468776897288,ACOUSTIC_VTC_20220103.csv
+45529,48388,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,22.117398461823168,23.810606492436005,3.250495971994742,38.30354993900844,35.053053967013696,ACOUSTIC_VTC_20220103.csv
+47920,48511,MAL,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,26.125592094398705,28.040180683789984,20.538702480546277,32.325854178371884,11.78715169782561,ACOUSTIC_VTC_20220103.csv
+48406,48742,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,27.901054926890676,28.90405869303639,20.20725812088503,33.8977663740024,13.690508253117372,ACOUSTIC_VTC_20220103.csv
+49012,49992,CHI,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,25.59386252867044,28.882693615369817,7.193311347719939,32.0764799883201,24.883168640600164,ACOUSTIC_VTC_20220103.csv
+49969,53843,FEM,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,23.456682357930745,24.408714876975008,5.961750903820473,36.933893811282246,30.972142907461773,ACOUSTIC_VTC_20220103.csv
+49994,50402,MAL,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,16.573881119136608,20.800023048270496,4.888311023727557,24.879314465853824,19.991003442126267,ACOUSTIC_VTC_20220103.csv
+50785,50991,MAL,13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,13.751972351457695,9.010613171850022,8.798760436188962,27.3952530848442,18.59649264865524,ACOUSTIC_VTC_20220103.csv

tests/existing_dataset/annotations/acoustic/raw/ACOUSTIC_VTC_20220103.csv

@@ -0,0 +1,33 @@
+"segment_onset","segment_offset","speaker_type","recording_filename","mean_pitch_semitone","median_pitch_semitone","p5_pitch_semitone","p95_pitch_semitone","pitch_range_semitone"
+716,1091,"OCH","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",29.492868065520707,30.138642702884987,20.926579385247212,38.043171039925696,17.116591654678484
+788,1335,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",29.214643421856756,33.11085884127924,8.643340281901134,37.13355658578659,28.49021630388546
+969,2473,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",29.298045163512683,32.88547138489501,16.117759395143267,36.702404352700434,20.584644957557167
+1939,2354,"OCH","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",30.428308088316903,34.61281831343323,15.920787817807724,37.36111941428427,21.440331596476543
+3086,4515,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.555790687873063,25.43977444107606,9.468522269335491,38.91392066067757,29.445398391342078
+4703,4887,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",33.291505212128094,33.965485866935126,29.417243345500275,36.839583257883376,7.4223399123831015
+5505,6600,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",25.238233859752953,25.98407828936643,8.463363614308186,36.31506800615161,27.851704391843427
+7341,13185,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.370678664104652,27.750854514520753,8.341604446398945,35.09095086550627,26.749346419107326
+12083,12444,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",29.956301863760103,28.88535975974367,28.714569368207133,34.608363509762654,5.893794141555521
+12590,13373,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",30.885068902158533,32.25262782345649,15.867153956619152,37.06109220660275,21.1939382499836
+14342,16227,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",27.099425252840522,30.1316705155409,4.900098987854256,36.364327384602554,31.464228396748297
+16544,19425,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.813336544105095,29.79400943252938,6.3135133339207385,35.052483607526085,28.738970273605347
+19011,20491,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",29.44086771482358,31.30927236046787,14.25502037838229,35.78714023878623,21.532119860403938
+19043,19185,"OCH","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",32.98295998189534,32.584870544859385,32.48382047902467,33.98404020556487,1.5002197265401946
+19565,19676,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",33.23750268763251,32.635081963927476,31.840505612731988,35.47788877572007,3.6373831629880797
+19992,20350,"MAL","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",23.984203441734014,29.978572686536808,10.764177536575712,30.938970827336167,20.174793290760455
+20819,21492,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",25.972110913025837,27.786858031123913,11.930542688627893,34.3079964640147,22.377453775386805
+21371,22532,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",28.63344638844196,28.605046698194336,18.85412445160436,38.6102602617787,19.75613581017434
+22341,22489,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.353878009435352,27.440413582763572,7.962495806926718,37.031037659997224,29.068541853070506
+23011,32954,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",25.77530730000921,26.83477640238156,8.893634420293438,37.358931057908656,28.465296637615218
+31303,31511,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",28.0041265711964,27.788575894455448,27.13021350366272,29.700172038814195,2.569958535151475
+33289,35014,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.25148665734396,28.7330051925927,9.870414118088517,31.4329577243406,21.562543606252085
+34493,34922,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",23.198844317955512,29.349953897341493,6.124320718231403,31.328715670516758,25.204394952285355
+35669,44992,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",24.460095969972958,27.402694042444974,6.9129786644071,35.560134764118054,28.647156099710955
+35675,36011,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",27.16001249135059,31.49551718224296,6.488738913265618,33.956207690162906,27.467468776897288
+45529,48388,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",22.117398461823168,23.810606492436005,3.250495971994742,38.30354993900844,35.053053967013696
+47920,48511,"MAL","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",26.125592094398705,28.040180683789984,20.538702480546274,32.325854178371884,11.78715169782561
+48406,48742,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",27.901054926890673,28.90405869303639,20.20725812088503,33.8977663740024,13.690508253117372
+49012,49992,"CHI","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",25.59386252867044,28.882693615369817,7.193311347719939,32.0764799883201,24.883168640600164
+49969,53843,"FEM","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",23.456682357930745,24.408714876975008,5.961750903820473,36.933893811282246,30.972142907461773
+49994,50402,"MAL","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",16.573881119136608,20.800023048270496,4.888311023727557,24.879314465853824,19.991003442126267
+50785,50991,"MAL","13980101/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",13.751972351457697,9.010613171850022,8.798760436188962,27.3952530848442,18.596492648655236

tests/existing_dataset/annotations/alice/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,18 @@
+phonemes,syllables,words,segment_onset,segment_offset,raw_filename
+17.53,8.46,5.44,969,2473,ALICE_20220103.txt
+15.11,7.24,4.83,3086,4515,ALICE_20220103.txt
+13.88,6.96,4.26,4703,4887,ALICE_20220103.txt
+15.52,7.43,4.8,5505,6600,ALICE_20220103.txt
+50.68,25.91,17.27,7341,13185,ALICE_20220103.txt
+27.79,13.52,8.98,16544,19425,ALICE_20220103.txt
+10.43,5.12,3.1,19565,19676,ALICE_20220103.txt
+10.13,4.91,3.04,19992,20350,ALICE_20220103.txt
+10.95,4.82,3.4,21371,22532,ALICE_20220103.txt
+85.32,42.92,28.97,23011,32954,ALICE_20220103.txt
+8.95,4.18,2.61,34493,34922,ALICE_20220103.txt
+87.29,43.17,28.83,35669,44992,ALICE_20220103.txt
+29.29,15.03,9.79,45529,48388,ALICE_20220103.txt
+13.68,6.69,4.16,47920,48511,ALICE_20220103.txt
+34.25,17.26,11.57,49969,53843,ALICE_20220103.txt
+10.86,5.26,3.29,49994,50402,ALICE_20220103.txt
+12.0,5.99,3.64,50785,50991,ALICE_20220103.txt

tests/existing_dataset/annotations/alice/raw/ALICE_20220103.txt

@@ -0,0 +1,17 @@
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00009690_00024730.wav	17.53	8.46	5.44
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00030860_00045150.wav	15.11	7.24	4.83
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00047030_00048870.wav	13.88	6.96	4.26
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00055050_00066000.wav	15.52	7.43	4.80
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00073410_00131850.wav	50.68	25.91	17.27
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00165440_00194250.wav	27.79	13.52	8.98
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00195650_00196760.wav	10.43	5.12	3.10
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00199920_00203500.wav	10.13	4.91	3.04
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00213710_00225320.wav	10.95	4.82	3.40
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00230110_00329540.wav	85.32	42.92	28.97
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00344930_00349220.wav	8.95	4.18	2.61
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00356690_00449920.wav	87.29	43.17	28.83
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00455290_00483880.wav	29.29	15.03	9.79
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00479200_00485110.wav	13.68	6.69	4.16
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00499690_00538430.wav	34.25	17.26	11.57
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00499940_00504020.wav	10.86	5.26	3.29
+/home/ubuntu/ALICE/tmp_data/short/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_00507850_00509910.wav	12.00	5.99	3.64

tests/existing_dataset/annotations/alice_vtc/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,38 @@
+segment_onset,segment_offset,speaker_type,phonemes,syllables,words,raw_filename
+10,304,NA,NA,NA,NA,VTC_20220103.rttm
+511,5093,NA,NA,NA,NA,VTC_20220103.rttm
+716,1091,OCH,NA,NA,NA,VTC_20220103.rttm
+788,1335,CHI,NA,NA,NA,VTC_20220103.rttm
+969,2473,FEM,17.53,8.46,5.44,"VTC_20220103.rttm,ALICE_20220103.txt"
+1939,2354,OCH,NA,NA,NA,VTC_20220103.rttm
+3086,4515,FEM,15.11,7.24,4.83,"VTC_20220103.rttm,ALICE_20220103.txt"
+4703,4887,FEM,13.88,6.96,4.26,"VTC_20220103.rttm,ALICE_20220103.txt"
+5505,6600,FEM,15.52,7.43,4.8,"VTC_20220103.rttm,ALICE_20220103.txt"
+5506,6615,NA,NA,NA,NA,VTC_20220103.rttm
+7322,13446,NA,NA,NA,NA,VTC_20220103.rttm
+7341,13185,FEM,50.68,25.91,17.27,"VTC_20220103.rttm,ALICE_20220103.txt"
+12083,12444,CHI,NA,NA,NA,VTC_20220103.rttm
+12590,13373,CHI,NA,NA,NA,VTC_20220103.rttm
+14298,54030,NA,NA,NA,NA,VTC_20220103.rttm
+14342,16227,CHI,NA,NA,NA,VTC_20220103.rttm
+16544,19425,FEM,27.79,13.52,8.98,"VTC_20220103.rttm,ALICE_20220103.txt"
+19011,20491,CHI,NA,NA,NA,VTC_20220103.rttm
+19043,19185,OCH,NA,NA,NA,VTC_20220103.rttm
+19565,19676,FEM,10.43,5.12,3.1,"VTC_20220103.rttm,ALICE_20220103.txt"
+19992,20350,MAL,10.13,4.91,3.04,"VTC_20220103.rttm,ALICE_20220103.txt"
+20819,21492,CHI,NA,NA,NA,VTC_20220103.rttm
+21371,22532,FEM,10.95,4.82,3.4,"VTC_20220103.rttm,ALICE_20220103.txt"
+22341,22489,CHI,NA,NA,NA,VTC_20220103.rttm
+23011,32954,FEM,85.32,42.92,28.97,"VTC_20220103.rttm,ALICE_20220103.txt"
+31303,31511,CHI,NA,NA,NA,VTC_20220103.rttm
+33289,35014,CHI,NA,NA,NA,VTC_20220103.rttm
+34493,34922,FEM,8.95,4.18,2.61,"VTC_20220103.rttm,ALICE_20220103.txt"
+35669,44992,FEM,87.29,43.17,28.83,"VTC_20220103.rttm,ALICE_20220103.txt"
+35675,36011,CHI,NA,NA,NA,VTC_20220103.rttm
+45529,48388,FEM,29.29,15.03,9.79,"VTC_20220103.rttm,ALICE_20220103.txt"
+47920,48511,MAL,13.68,6.69,4.16,"VTC_20220103.rttm,ALICE_20220103.txt"
+48406,48742,CHI,NA,NA,NA,VTC_20220103.rttm
+49012,49992,CHI,NA,NA,NA,VTC_20220103.rttm
+49969,53843,FEM,34.25,17.26,11.57,"VTC_20220103.rttm,ALICE_20220103.txt"
+49994,50402,MAL,10.86,5.26,3.29,"VTC_20220103.rttm,ALICE_20220103.txt"
+50785,50991,MAL,12.0,5.99,3.64,"VTC_20220103.rttm,ALICE_20220103.txt"

tests/existing_dataset/annotations/conversations/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,33 @@
+segment_onset,segment_offset,speaker_type,recording_filename,segment_duration,unit_index,inter_seq_index,conv_turn_index,fmt_inter_seq,is_start_unit,is_end_unit,is_prompt_to,is_response_to,is_self_prompt_to,is_self_response_to,raw_filename
+716,1091,OCH,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,375,2,,,(2) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+788,1335,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,547,3,1.0,1.0,(3) 1-1,True,False,4.0,,,,CONVERSATIONS_VTC_20220103.csv
+969,2473,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1504,4,1.0,2.0,(4) 1-2,False,False,,3.0,6.0,,CONVERSATIONS_VTC_20220103.csv
+1939,2354,OCH,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,415,5,,,(5) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+3086,4515,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1429,6,1.0,3.0,(6) 1-3,False,False,,,7.0,4.0,CONVERSATIONS_VTC_20220103.csv
+4703,4887,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,184,7,1.0,4.0,(7) 1-4,False,False,,,8.0,6.0,CONVERSATIONS_VTC_20220103.csv
+5505,6600,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1095,8,1.0,5.0,(8) 1-5,False,False,,,11.0,7.0,CONVERSATIONS_VTC_20220103.csv
+7341,13185,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,5844,11,1.0,6.0,(11) 1-6,False,False,12.0,,,8.0,CONVERSATIONS_VTC_20220103.csv
+12083,12444,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,361,12,1.0,7.0,(12) 1-7,False,False,,11.0,13.0,,CONVERSATIONS_VTC_20220103.csv
+12590,13373,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,783,13,1.0,8.0,(13) 1-8,False,False,,,15.0,12.0,CONVERSATIONS_VTC_20220103.csv
+14342,16227,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1885,15,1.0,9.0,(15) 1-9,False,False,16.0,,,13.0,CONVERSATIONS_VTC_20220103.csv
+16544,19425,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,2881,16,1.0,10.0,(16) 1-10,False,False,17.0,15.0,,,CONVERSATIONS_VTC_20220103.csv
+19011,20491,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1480,17,1.0,11.0,(17) 1-11,False,False,20.0,16.0,,,CONVERSATIONS_VTC_20220103.csv
+19043,19185,OCH,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,142,18,,,(18) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+19565,19676,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,111,19,,,(19) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+19992,20350,MAL,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,358,20,1.0,12.0,(20) 1-12,False,False,21.0,17.0,,,CONVERSATIONS_VTC_20220103.csv
+20819,21492,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,673,21,1.0,13.0,(21) 1-13,False,False,22.0,20.0,,,CONVERSATIONS_VTC_20220103.csv
+21371,22532,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1161,22,1.0,14.0,(22) 1-14,False,False,23.0,21.0,,,CONVERSATIONS_VTC_20220103.csv
+22341,22489,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,148,23,1.0,15.0,(23) 1-15,False,False,24.0,22.0,,,CONVERSATIONS_VTC_20220103.csv
+23011,32954,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,9943,24,1.0,16.0,(24) 1-16,False,False,25.0,23.0,,,CONVERSATIONS_VTC_20220103.csv
+31303,31511,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,208,25,1.0,17.0,(25) 1-17,False,True,,24.0,,,CONVERSATIONS_VTC_20220103.csv
+33289,35014,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,1725,26,2.0,1.0,(26) 2-1,True,False,27.0,,,,CONVERSATIONS_VTC_20220103.csv
+34493,34922,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,429,27,2.0,2.0,(27) 2-2,False,False,,26.0,28.0,,CONVERSATIONS_VTC_20220103.csv
+35669,44992,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,9323,28,2.0,3.0,(28) 2-3,False,False,,,30.0,27.0,CONVERSATIONS_VTC_20220103.csv
+35675,36011,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,336,29,,,(29) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+45529,48388,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,2859,30,2.0,4.0,(30) 2-4,False,False,32.0,,,28.0,CONVERSATIONS_VTC_20220103.csv
+47920,48511,MAL,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,591,31,,,(31) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+48406,48742,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,336,32,2.0,5.0,(32) 2-5,False,False,,30.0,33.0,,CONVERSATIONS_VTC_20220103.csv
+49012,49992,CHI,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,980,33,2.0,6.0,(33) 2-6,False,False,35.0,,,32.0,CONVERSATIONS_VTC_20220103.csv
+49969,53843,FEM,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,3874,34,,,(34) ,,,,,,,CONVERSATIONS_VTC_20220103.csv
+49994,50402,MAL,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,408,35,2.0,7.0,(35) 2-7,False,False,,33.0,36.0,,CONVERSATIONS_VTC_20220103.csv
+50785,50991,MAL,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,206,36,2.0,8.0,(36) 2-8,False,True,,,,35.0,CONVERSATIONS_VTC_20220103.csv

tests/existing_dataset/annotations/conversations/raw/CONVERSATIONS_VTC_20220103.csv

@@ -0,0 +1,33 @@
+"segment_onset","segment_offset","speaker_type","recording_filename","segment_duration","unit_index","inter_seq_index","conv_turn_index","fmt_inter_seq","is_start_unit","is_end_unit","is_prompt_to","is_response_to","is_self_prompt_to","is_self_response_to"
+716,1091,"OCH","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",375,2,"","","(2) ","","","","","",""
+788,1335,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",547,3,"1","1","(3) 1-1",True,False,"4","","",""
+969,2473,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1504,4,"1","2","(4) 1-2",False,False,"","3","6",""
+1939,2354,"OCH","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",415,5,"","","(5) ","","","","","",""
+3086,4515,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1429,6,"1","3","(6) 1-3",False,False,"","","7","4"
+4703,4887,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",184,7,"1","4","(7) 1-4",False,False,"","","8","6"
+5505,6600,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1095,8,"1","5","(8) 1-5",False,False,"","","11","7"
+7341,13185,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",5844,11,"1","6","(11) 1-6",False,False,"12","","","8"
+12083,12444,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",361,12,"1","7","(12) 1-7",False,False,"","11","13",""
+12590,13373,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",783,13,"1","8","(13) 1-8",False,False,"","","15","12"
+14342,16227,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1885,15,"1","9","(15) 1-9",False,False,"16","","","13"
+16544,19425,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",2881,16,"1","10","(16) 1-10",False,False,"17","15","",""
+19011,20491,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1480,17,"1","11","(17) 1-11",False,False,"20","16","",""
+19043,19185,"OCH","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",142,18,"","","(18) ","","","","","",""
+19565,19676,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",111,19,"","","(19) ","","","","","",""
+19992,20350,"MAL","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",358,20,"1","12","(20) 1-12",False,False,"21","17","",""
+20819,21492,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",673,21,"1","13","(21) 1-13",False,False,"22","20","",""
+21371,22532,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1161,22,"1","14","(22) 1-14",False,False,"23","21","",""
+22341,22489,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",148,23,"1","15","(23) 1-15",False,False,"24","22","",""
+23011,32954,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",9943,24,"1","16","(24) 1-16",False,False,"25","23","",""
+31303,31511,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",208,25,"1","17","(25) 1-17",False,True,"","24","",""
+33289,35014,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",1725,26,"2","1","(26) 2-1",True,False,"27","","",""
+34493,34922,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",429,27,"2","2","(27) 2-2",False,False,"","26","28",""
+35669,44992,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",9323,28,"2","3","(28) 2-3",False,False,"","","30","27"
+35675,36011,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",336,29,"","","(29) ","","","","","",""
+45529,48388,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",2859,30,"2","4","(30) 2-4",False,False,"32","","","28"
+47920,48511,"MAL","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",591,31,"","","(31) ","","","","","",""
+48406,48742,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",336,32,"2","5","(32) 2-5",False,False,"","30","33",""
+49012,49992,"CHI","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",980,33,"2","6","(33) 2-6",False,False,"35","","","32"
+49969,53843,"FEM","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",3874,34,"","","(34) ","","","","","",""
+49994,50402,"MAL","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",408,35,"2","7","(35) 2-7",False,False,"","33","36",""
+50785,50991,"MAL","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav",206,36,"2","8","(36) 2-8",False,True,"","","","35"

tests/existing_dataset/annotations/vcm/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,38 @@
+segment_onset,segment_offset,speaker_type,vcm_type,raw_filename
+10,304,NA,NA,VCM_20220103.vcm
+511,5093,NA,NA,VCM_20220103.vcm
+716,1091,OCH,NA,VCM_20220103.vcm
+788,1335,CHI,N,VCM_20220103.vcm
+969,2473,FEM,NA,VCM_20220103.vcm
+1939,2354,OCH,NA,VCM_20220103.vcm
+3086,4515,FEM,NA,VCM_20220103.vcm
+4703,4887,FEM,NA,VCM_20220103.vcm
+5505,6600,FEM,NA,VCM_20220103.vcm
+5506,6615,NA,NA,VCM_20220103.vcm
+7322,13446,NA,NA,VCM_20220103.vcm
+7341,13185,FEM,NA,VCM_20220103.vcm
+12083,12444,CHI,N,VCM_20220103.vcm
+12590,13373,CHI,N,VCM_20220103.vcm
+14298,54030,NA,NA,VCM_20220103.vcm
+14342,16227,CHI,N,VCM_20220103.vcm
+16544,19425,FEM,NA,VCM_20220103.vcm
+19011,20491,CHI,C,VCM_20220103.vcm
+19043,19185,OCH,NA,VCM_20220103.vcm
+19565,19676,FEM,NA,VCM_20220103.vcm
+19992,20350,MAL,NA,VCM_20220103.vcm
+20819,21492,CHI,N,VCM_20220103.vcm
+21371,22532,FEM,NA,VCM_20220103.vcm
+22341,22489,CHI,N,VCM_20220103.vcm
+23011,32954,FEM,NA,VCM_20220103.vcm
+31303,31511,CHI,N,VCM_20220103.vcm
+33289,35014,CHI,C,VCM_20220103.vcm
+34493,34922,FEM,NA,VCM_20220103.vcm
+35669,44992,FEM,NA,VCM_20220103.vcm
+35675,36011,CHI,C,VCM_20220103.vcm
+45529,48388,FEM,NA,VCM_20220103.vcm
+47920,48511,MAL,NA,VCM_20220103.vcm
+48406,48742,CHI,N,VCM_20220103.vcm
+49012,49992,CHI,N,VCM_20220103.vcm
+49969,53843,FEM,NA,VCM_20220103.vcm
+49994,50402,MAL,NA,VCM_20220103.vcm
+50785,50991,MAL,NA,VCM_20220103.vcm

tests/existing_dataset/annotations/vcm/raw/VCM_20220103.vcm

@@ -0,0 +1,37 @@
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.010 0.294 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.511 4.582 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.716 0.375 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.788 0.547 <NA> <NA> NCS 0.72 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.969 1.504 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 1.939 0.415 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 3.086 1.429 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 4.703 0.184 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 5.505 1.095 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 5.506 1.109 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 7.322 6.124 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 7.341 5.844 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 12.083 0.361 <NA> <NA> NCS 0.76 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 12.590 0.783 <NA> <NA> NCS 0.52 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 14.298 39.732 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 14.342 1.885 <NA> <NA> NCS 0.60 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 16.544 2.881 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.011 1.480 <NA> <NA> CNS 0.55 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.043 0.142 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.565 0.111 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.992 0.358 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 20.819 0.673 <NA> <NA> NCS 0.76 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 21.371 1.161 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 22.341 0.148 <NA> <NA> NCS 0.87 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 23.011 9.943 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 31.303 0.208 <NA> <NA> NCS 0.84 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 33.289 1.725 <NA> <NA> CNS 0.58 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 34.493 0.429 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 35.669 9.323 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 35.675 0.336 <NA> <NA> CNS 0.50 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 45.529 2.859 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 47.920 0.591 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 48.406 0.336 <NA> <NA> NCS 0.96 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.012 0.980 <NA> <NA> NCS 0.79 <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.969 3.874 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.994 0.408 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 50.785 0.206 <NA> <NA> MAL <NA> <NA>

tests/existing_dataset/annotations/vtc/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv

@@ -0,0 +1,38 @@
+segment_onset,segment_offset,speaker_type,raw_filename
+10,304,NA,VTC_20220103.rttm
+511,5093,NA,VTC_20220103.rttm
+716,1091,OCH,VTC_20220103.rttm
+788,1335,CHI,VTC_20220103.rttm
+969,2473,FEM,VTC_20220103.rttm
+1939,2354,OCH,VTC_20220103.rttm
+3086,4515,FEM,VTC_20220103.rttm
+4703,4887,FEM,VTC_20220103.rttm
+5505,6600,FEM,VTC_20220103.rttm
+5506,6615,NA,VTC_20220103.rttm
+7322,13446,NA,VTC_20220103.rttm
+7341,13185,FEM,VTC_20220103.rttm
+12083,12444,CHI,VTC_20220103.rttm
+12590,13373,CHI,VTC_20220103.rttm
+14298,54030,NA,VTC_20220103.rttm
+14342,16227,CHI,VTC_20220103.rttm
+16544,19425,FEM,VTC_20220103.rttm
+19011,20491,CHI,VTC_20220103.rttm
+19043,19185,OCH,VTC_20220103.rttm
+19565,19676,FEM,VTC_20220103.rttm
+19992,20350,MAL,VTC_20220103.rttm
+20819,21492,CHI,VTC_20220103.rttm
+21371,22532,FEM,VTC_20220103.rttm
+22341,22489,CHI,VTC_20220103.rttm
+23011,32954,FEM,VTC_20220103.rttm
+31303,31511,CHI,VTC_20220103.rttm
+33289,35014,CHI,VTC_20220103.rttm
+34493,34922,FEM,VTC_20220103.rttm
+35669,44992,FEM,VTC_20220103.rttm
+35675,36011,CHI,VTC_20220103.rttm
+45529,48388,FEM,VTC_20220103.rttm
+47920,48511,MAL,VTC_20220103.rttm
+48406,48742,CHI,VTC_20220103.rttm
+49012,49992,CHI,VTC_20220103.rttm
+49969,53843,FEM,VTC_20220103.rttm
+49994,50402,MAL,VTC_20220103.rttm
+50785,50991,MAL,VTC_20220103.rttm

tests/existing_dataset/annotations/vtc/raw/VTC_20220103.rttm

@@ -0,0 +1,37 @@
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.010 0.294 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.511 4.582 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.716 0.375 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.788 0.547 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 0.969 1.504 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 1.939 0.415 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 3.086 1.429 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 4.703 0.184 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 5.505 1.095 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 5.506 1.109 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 7.322 6.124 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 7.341 5.844 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 12.083 0.361 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 12.590 0.783 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 14.298 39.732 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 14.342 1.885 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 16.544 2.881 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.011 1.480 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.043 0.142 <NA> <NA> CHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.565 0.111 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 19.992 0.358 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 20.819 0.673 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 21.371 1.161 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 22.341 0.148 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 23.011 9.943 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 31.303 0.208 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 33.289 1.725 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 34.493 0.429 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 35.669 9.323 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 35.675 0.336 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 45.529 2.859 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 47.920 0.591 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 48.406 0.336 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.012 0.980 <NA> <NA> KCHI <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.969 3.874 <NA> <NA> FEM <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 49.994 0.408 <NA> <NA> MAL <NA> <NA>
+SPEAKER 14T_Audio-1-familia-14T-CP-2020-02_20220103_000000 1 50.785 0.206 <NA> <NA> MAL <NA> <NA>

tests/existing_dataset/annotations/vtc/raw/VTC_20220124.rttm

@@ -0,0 +1,53 @@
+SPEAKER B0_xxx_13980101_000000 1 7.308 0.121 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 7.025 0.048 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 7.106 0.015 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 7.434 1.780 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 7.493 0.085 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 7.041 1.095 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 8.111 0.038 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 8.765 0.437 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 9.446 1.714 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 9.492 0.871 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 9.259 0.038 <NA> <NA> MAL <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 9.461 0.017 <NA> <NA> MAL <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 10.065 0.040 <NA> <NA> MAL <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 10.872 0.140 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 10.486 0.506 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 10.010 0.089 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 10.379 0.031 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.712 0.078 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.138 0.259 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.992 0.151 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.943 3.252 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.971 1.217 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.289 0.024 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 11.492 0.052 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 12.656 0.092 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 12.917 0.065 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.003 0.056 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.265 0.437 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.993 0.051 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.798 0.242 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.464 0.116 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 13.272 0.323 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.455 0.039 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.991 0.245 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.657 0.135 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.011 0.150 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.992 0.217 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.331 0.029 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.991 0.081 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.176 0.107 <NA> <NA> KCHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.218 0.068 <NA> <NA> CHI <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.222 0.011 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 14.195 0.121 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.797 0.076 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.800 0.081 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.035 0.010 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.281 0.218 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.425 0.055 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.491 0.072 <NA> <NA> MAL <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.731 0.026 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.494 0.300 <NA> <NA> SPEECH <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.542 0.074 <NA> <NA> FEM <NA> <NA>
+SPEAKER B0_xxx_13980101_000000 1 15.019 0.053 <NA> <NA> MAL <NA> <NA>

tests/existing_dataset/extra/messages/definition/metrics_messages.yaml

@@ -0,0 +1,50 @@
+# Messages
+
+voc_chi_ph:
+  true: "tu hijo habló más"
+  false: "probá dejar más espacio para que tu hijo hable, por ejemplo haciendo preguntas"
+
+chi_adu_turn_transitions:
+  true: "hubo mas ida y vuelta"
+  false: "podrías practicar que haya más ida y vuelta, por ejemplo preguntando cosas"
+
+
+_default: "Qué bueno que hayas tomado un rato para conversar con tu hijo"
+
+# Old messages (/!\ do NOT uncomment those)
+
+#mean_mean_pitch_fem:
+#  true: "modulaste más esta vez, este ayuda a tu hijo a entenderte mejor"
+#  false: "proba modular más cuando hablás"
+
+
+# Templates (TODO: use liquid templates)
+_True_True: 'Esta vez #1 y #2. Muy bien!'
+_True_False: '#1, muy bien! La proxima vez #2.'
+_False_True: '#2, muy bien! La proxima vez #1.'
+_False_False: '#default! La proxima vez #1.'
+
+
+#
+#   Tentative messages
+#
+
+#MENSAJE 1: si todo empeoro: "qué bueno que hayas tomado un rato para conversar con tu hijo!"
+#    "la proxima podrias practicar que haya mas ida y vuelta, por ejemplo preguntando cosas"
+#
+#MENSAJE 2: si todo empeoro: "qué bueno que hayas tomado un rato para conversar con tu hijo!"
+#    "la proxima vez proba dejar mas espacio para que tu hijo hable, por ejemplo haciendo preguntas"
+#
+#
+#MENSAJE 3: CHI increased, TC decreased
+#    "tu hijo hablo mas esta vez, muy bien"
+#    "la proxima podrias practicar que haya mas ida y vuelta, por ejemplo preguntando cosas"
+#
+#
+#MENSAJE 4: TC increased, CHI decreased
+#    "esta vez hubo mas ida y vuelta, muy bien"
+#    "la proxima vez proba dejar mas espacio para que tu hijo hable, por ejemplo haciendo preguntas"
+#
+#
+#MENSAJE 5: both increased
+#    "tu hijo hablo mas esta vez, y hubo mas ida y vuelta,  muy bien"

tests/existing_dataset/extra/messages/generated/messages_20220103.csv

@@ -0,0 +1,2 @@
+"recording_filename";"message"
+"14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav";"Qué bueno que hayas tomado un rato para conversar con tu hijo"

tests/existing_dataset/extra/metrics/metrics.csv

@@ -0,0 +1,2 @@
+recording_filename,child_id,duration_acoustic,mean_pitch_range_fem,mean_mean_pitch_chi,mean_mean_pitch_fem,mean_pitch_range_chi,duration_alice_vtc,mlup_fem,mlus_fem,mluw_fem,pc_fem_ph,sc_fem_ph,wc_fem_ph,avg_wr_pm_fem,avg_sr_pm_fem,avg_pr_pm_fem,duration_conversations,chi_adu_turn_transitions,duration_vcm,cp_dur,cp_n,lp_dur,avg_non_can_voc_dur_chi,non_can_voc_dur_chi_ph,non_can_voc_chi_ph,avg_can_voc_dur_chi,can_voc_dur_chi_ph,can_voc_chi_ph,avg_cry_voc_dur_chi,cry_voc_dur_chi_ph,cry_voc_chi_ph,lp_n,duration_vtc,avg_voc_dur_chi,avg_voc_dur_fem,voc_dur_chi_ph,voc_dur_fem_ph,voc_chi_ph,voc_fem_ph
+14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,chi_14T,60000,24.04061291408368,27.81940327111273,26.803605201172502,20.849495032754373,60000,31.306923076923077,15.540000000000001,10.296153846153846,24419.4,12121.2,8031.0,415.2094566207961,660.5086208495603,1345.1232870330582,60000,10,60000,0.37423377721411966,0.25,1.0,657.8888888888889,355260.0,540.0,1180.3333333333333,212460.0,180.0,0,0.0,0.0,1.0,60000,788.5,3125.923076923077,567720.0,2438220.0,720.0,780.0

tests/existing_dataset/metadata/annotations.csv

@@ -0,0 +1,7 @@
+set,recording_filename,time_seek,range_onset,range_offset,raw_filename,format,filter,annotation_filename,imported_at,package_version,error,merged_from
+vtc,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,VTC_20220103.rttm,vtc_rttm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 13:59:55,0.0.7,,
+alice,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,ALICE_20220103.txt,alice,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 14:46:56,0.0.7,,
+vcm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,VCM_20220103.vcm,vcm_rttm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 14:48:11,0.0.7,,
+conversations,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,CONVERSATIONS_VTC_20220103.csv,filtered_csv,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 15:15:42,0.0.7,,
+acoustic,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,ACOUSTIC_VTC_20220103.csv,filtered_csv,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 15:22:46,0.0.7,,
+alice_vtc,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,"VTC_20220103.rttm,ALICE_20220103.txt",,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 15:54:30,0.0.7,,"vtc,alice"

tests/existing_dataset/metadata/readme.md

@@ -0,0 +1 @@
+annotations in raw are not real, they were taken randomly from a sample (VTC and VCM are taken from the same rec for the same time, and alice acoustic and conversations being derived from it, they all kind of refer to the same recording passsage).

tests/test_computeAnnotations.py

@@ -11,12 +11,19 @@ import pandas as pd
 fpath = os.path.join(os.path.dirname(__file__),'..', 'compute_annotations')
 sys.path.append(fpath)
 
-import utils
-import annotations_functions as af
-import compute_derived_annotations as cda
-import conversational_settings as cs
-import utils_annotations as uan
-import utils_audio as uau
+try:
+    sys.modules.pop('utils') #need to do this to avoid utils conflict of importation
+except:
+    pass
+
+import compute_annotations.utils as ca_utils
+import compute_annotations.annotations_functions as af
+import compute_annotations.compute_derived_annotations as cda
+import compute_annotations.conversational_settings as cs
+import compute_annotations.utils_annotations as uan
+import compute_annotations.utils_audio as uau
+
+sys.path.remove(fpath)
 
 ################ utils ###################
 
@@ -24,6 +31,13 @@ import utils_audio as uau
 
 ######## annotations_functions ###########
 
+def test_conversations_annotations():
+    pass
+
+# no test for now, see utils_annotations section
+#def test_acoustic_annotations():
+#    pass
+
 ##########################################
 
 ##### compute_derived_annotations ########
@@ -32,14 +46,24 @@ import utils_audio as uau
 
 
 ######## conversational_settings #########
+    
+#just a list of settings to use for conversation
+#no test to conduct
 
 ##########################################
 
 
 ########## utils_annotations #############
 
+#acoustic annotation require the audio to be present
+#to integrate with a proper audio used
+
+#TODO find a suitable, short audio to put into
+#the test folder, to run the analysis on
+
 ##########################################
 
 ############# utils_audio ################
 
-##########################################
+##########################################
+    

tests/test_computeMetrics.py

@@ -12,8 +12,8 @@ import pandas as pd
 fpath = os.path.join(os.path.dirname(__file__),'..', 'compute_metrics')
 sys.path.append(fpath)
 
-import metrics as met
-import metrics_functions as mf
+import compute_metrics.metrics as met
+import compute_metrics.metrics_functions as mf
 
 ############### metrics ##################
 
@@ -21,4 +21,5 @@ import metrics_functions as mf
 
 ########## metrics_functions #############
 
-##########################################
+##########################################
+

tests/test_dataset/metadata/annotations.csv

@@ -0,0 +1,4 @@
+set,recording_filename,time_seek,range_onset,range_offset,raw_filename,format,filter,annotation_filename,imported_at,package_version,error,merged_from
+vtc,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,VTC_20220103.rttm,vtc_rttm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 13:59:55,0.0.7,,
+alice,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,ALICE_20220103.txt,alice,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 14:46:56,0.0.7,,
+vcm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav,0,0,60000,VCM_20220103.vcm,vcm_rttm,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000,14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv,2022-11-07 14:48:11,0.0.7,,

tests/test_dataset/metadata/recordings.csv

@@ -1,3 +1,3 @@
 "experiment","experiment_stage","child_id","date_iso","start_time","recording_device_type","recording_filename","session_id","duration","imported_at"
 "test","Audio-1-familia-14T-CP-2020-02","chi_14T","2022-01-03","00:00:00","unknown","14T_Audio-1-familia-14T-CP-2020-02_20220103_000000.wav","chi_14T_20220103",60000,"2022-09-08 18:10:10"
-"test","Audio-3-familia-23T-lectura-01","chi_23T","2022-01-24","00:00:00","lena","23T_Audio-3-familia-23T-lectura-01_20220124_000000.wav","chi_23T_20220124",0,"2022-11-04 17:01:43"
+"test","Audio-3-familia-23T-lectura-01","chi_23T","2022-01-24","00:00:00","lena","23T_Audio-3-familia-23T-lectura-01_20220124_000000.wav","chi_23T_20220124",0,"2022-11-07 14:54:19"

tests/test_generateMessages.py

@@ -12,8 +12,9 @@ import pandas as pd
 fpath = os.path.join(os.path.dirname(__file__),'..', 'generate_messages')
 sys.path.append(fpath)
 
-import generate_messages as gm
+import generate_messages.messages as msg
 
 ########## generate_messages #############
 
-##########################################
+##########################################
+

tests/test_importData.py

@@ -12,12 +12,20 @@ import pandas as pd
 fpath = os.path.join(os.path.dirname(__file__),'..', 'import_data')
 sys.path.append(fpath)
 
-import utils
+#from import_data.utils import get_raw_filename
+#from utils import get_raw_filename
+try:
+    sys.modules.pop('utils') #need to do this to avoid utils conflict of importation
+except:
+    pass
+
+import utils as id_utils
 import prepare_data_set as pds
 import import_recordings as ir
 import import_annotations as ia
 import custom_converters as cc
 
+
 CHILDREN_FILE = os.path.join('dataset-test','metadata','children.csv')
 DATASET_PATH = os.path.join('tests','existing_dataset') #dataset already existing, used for tests that don't change it
 RECS_PATH = os.path.join(DATASET_PATH,'metadata','recordings.csv')
@@ -44,16 +52,43 @@ def set_up_dataset():
 @pytest.mark.parametrize('file,result',
     [(CHILDREN_FILE, "children"),])
 def test_get_raw_filename(file, result):
-    assert utils.get_raw_filename(file) == result
+    assert id_utils.get_raw_filename(file) == result
+    #assert get_raw_filename(file) == result
     
 @pytest.mark.parametrize('path,ext,full_path,result',
-    [(DATASET_PATH, ["csv","rttm"], True,sorted([os.path.join(DATASET_PATH,'annotations/vtc/raw/rec1.rttm'), os.path.join(DATASET_PATH,'annotations/vtc/raw/rec2.rttm'), os.path.join(DATASET_PATH,'metadata/annotations.csv'), os.path.join(DATASET_PATH,'metadata/children.csv'), os.path.join(DATASET_PATH,'metadata/recordings.csv')])),
-     (DATASET_PATH, ["csv","rttm"], False,sorted(['annotations/vtc/raw/rec1.rttm', 'annotations/vtc/raw/rec2.rttm', 'metadata/annotations.csv', 'metadata/children.csv', 'metadata/recordings.csv'])),
-     (os.path.join(DATASET_PATH,'metadata'), [], False,sorted(['annotations.csv','children.csv','recordings.csv','readme.md'])),
-     (NON_EXISTING_PATH, ["csv","rttm"], False,[]),
-     (DATASET_PATH, "invented", True,[]),])
+    [(DATASET_PATH, ["csv","rttm"], True,
+      sorted([os.path.join(DATASET_PATH,'annotations/vtc/raw/VTC_20220103.rttm'),
+              os.path.join(DATASET_PATH,'annotations/vtc/raw/VTC_20220124.rttm'),
+              os.path.join(DATASET_PATH,'metadata/annotations.csv'),
+              os.path.join(DATASET_PATH,'metadata/children.csv'),
+              os.path.join(DATASET_PATH,'metadata/recordings.csv'),
+              os.path.join(DATASET_PATH,'annotations/vtc/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv'),
+              os.path.join(DATASET_PATH,'annotations/alice/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv'),
+              os.path.join(DATASET_PATH,'annotations/vcm/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv'),
+              ])),
+     (DATASET_PATH, ["csv","rttm"], False,
+      sorted(['annotations/vtc/raw/VTC_20220103.rttm',
+              'annotations/vtc/raw/VTC_20220124.rttm',
+              'metadata/annotations.csv',
+              'metadata/children.csv',
+              'metadata/recordings.csv',
+              'annotations/vtc/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv',
+              'annotations/alice/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv',
+              'annotations/vcm/converted/14T_Audio-1-familia-14T-CP-2020-02_20220103_000000_0_60000.csv',
+              ])),
+     (os.path.join(DATASET_PATH,'metadata'), [], False,
+      sorted(['annotations.csv',
+              'children.csv',
+              'recordings.csv',
+              'readme.md',
+              ])),
+     (NON_EXISTING_PATH, ["csv","rttm"], False,
+      []),
+     (DATASET_PATH, "invented", True,
+      []),
+      ])
 def test_walk_dir(path, ext, full_path, result):
-    r = utils.walk_dir(path, ext, full_path)
+    r = id_utils.walk_dir(path, ext, full_path)
     print(r)
     assert r == result
     
@@ -62,7 +97,23 @@ def test_walk_dir(path, ext, full_path, result):
 ############# prepare_data_set ###########
 
 #tree when creating a new empty dataset from the NEW_DATASET_PATH var
-CREATION_TREE = [(NEW_DATASET_PATH, ['metadata', 'extra', 'annotations', 'recordings'], []), (os.path.join(NEW_DATASET_PATH,'metadata'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'extra'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations'), ['vtc', 'acoustic', 'vcm', 'conversations', 'alice'], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations/vtc'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'annotations/vtc/raw'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations/acoustic'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'annotations/acoustic/raw'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations/vcm'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'annotations/vcm/raw'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations/conversations'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'annotations/conversations/raw'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'annotations/alice'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'annotations/alice/raw'), [], ['.gitkeep']), (os.path.join(NEW_DATASET_PATH,'recordings'), ['raw'], []), (os.path.join(NEW_DATASET_PATH,'recordings/raw'), [], ['.gitkeep'])]
+CREATION_TREE = [(NEW_DATASET_PATH, ['metadata', 'extra', 'annotations', 'recordings'], []),
+                 (os.path.join(NEW_DATASET_PATH,'metadata'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'extra'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'annotations'), ['vtc', 'acoustic', 'vcm', 'conversations', 'alice'], ['.gitkeep']),            
+                 (os.path.join(NEW_DATASET_PATH,'annotations/vtc'), ['raw'], []),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/vtc/raw'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/acoustic'), ['raw'], []), 
+                 (os.path.join(NEW_DATASET_PATH,'annotations/acoustic/raw'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/vcm'), ['raw'], []),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/vcm/raw'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/conversations'), ['raw'], []),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/conversations/raw'),[], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/alice'), ['raw'], []),
+                 (os.path.join(NEW_DATASET_PATH,'annotations/alice/raw'), [], ['.gitkeep']),
+                 (os.path.join(NEW_DATASET_PATH,'recordings'), ['raw'], []),
+                 (os.path.join(NEW_DATASET_PATH,'recordings/raw'), [], ['.gitkeep']),
+                 ]
 
 def test_create_child_project_directories():
     pds.create_child_project_directories(NEW_DATASET_PATH)
@@ -182,6 +233,5 @@ def test_filteredCsvConverter():
     
 
 ###################################################
-    
-    
+