Commit 483f75aa authored by Paul Primus's avatar Paul Primus
Browse files

add final submission package

parent dfebc6ca
......@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 23,
"outputs": [],
"source": [
"from pymongo import MongoClient\n",
......@@ -90,12 +90,12 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 24,
"outputs": [
{
"name": "stdout",
"text": [
"Loaded 563 runs.\n"
"Loaded 572 runs.\n"
],
"output_type": "stream"
}
......@@ -115,7 +115,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 25,
"outputs": [
{
"name": "stdout",
......@@ -143,7 +143,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 26,
"outputs": [],
"source": [
"# Extract Results\n",
......@@ -172,7 +172,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 27,
"outputs": [
{
"name": "stdout",
......@@ -181,8 +181,8 @@
"Best Model for Machine Type 1: [ 1 10 6 9 3 5 13 2 11 12 7 8 4 0]\n",
"Best Model for Machine Type 2: [10 5 12 1 11 3 2 13 9 6 4 8 7 0]\n",
"Best Model for Machine Type 3: [ 2 12 4 5 11 6 10 3 1 13 9 8 7 0]\n",
"Best Model for Machine Type 4: [13 3 12 11 10 9 7 6 8 4 5 2 0 1]\n",
"Best Model for Machine Type 5: [ 4 8 2 7 10 5 9 6 13 11 12 3 0 1]\n"
"Best Model for Machine Type 4: [13 3 12 11 10 9 7 6 8 4 5 2 1 0]\n",
"Best Model for Machine Type 5: [ 1 4 8 2 7 10 5 9 6 13 11 12 3 0]\n"
],
"output_type": "stream"
}
......@@ -209,18 +209,18 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 28,
"outputs": [
{
"name": "stdout",
"text": [
"0: ID-10 resnet_gridsearch_a_bit_larger_loose_1e-4_100_BCE\n",
"1: ID-5 resnet_gridsearch_a_bit_larger_loose_1e-4_100_AUC\n",
"2: ID-12 resnet_gridsearch_a_bit_larger_loose_1e-5_100_BCE\n",
"3: ID-2 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_BCE\n",
"4: ID-11 resnet_gridsearch_a_bit_larger_loose_1e-5_100_AUC\n",
"5: ID-6 resnet_gridsearch_normal_loose_1e-4_100_BCE\n",
"6: ID-1 resnet_gridsearch_2_a_bit_larger_loose_1e-4_0.99_100_BCE\n",
"0: ID-1 resnet_gridsearch_2_a_bit_larger_loose_1e-4_0.99_100_BCE\n",
"1: ID-10 resnet_gridsearch_a_bit_larger_loose_1e-4_100_BCE\n",
"2: ID-5 resnet_gridsearch_a_bit_larger_loose_1e-4_100_AUC\n",
"3: ID-12 resnet_gridsearch_a_bit_larger_loose_1e-5_100_BCE\n",
"4: ID-2 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_BCE\n",
"5: ID-11 resnet_gridsearch_a_bit_larger_loose_1e-5_100_AUC\n",
"6: ID-6 resnet_gridsearch_normal_loose_1e-4_100_BCE\n",
"7: ID-3 resnet_gridsearch_normal_loose_1e-5_100_BCE\n",
"8: ID-9 resnet_gridsearch_normal_loose_1e-4_100_AUC\n",
"9: ID-4 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_AUC\n",
......@@ -250,15 +250,15 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 29,
"outputs": [
{
"data": {
"text/plain": "[10, 5, 12, 2, 11, 6, 1, 3, 9, 4, 13, 7, 8, 0]"
"text/plain": "[1, 10, 5, 12, 2, 11, 6, 3, 9, 4, 13, 7, 8, 0]"
},
"metadata": {},
"output_type": "execute_result",
"execution_count": 20
"execution_count": 29
}
],
"source": [
......
This diff is collapsed.
......@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 22,
"execution_count": 144,
"outputs": [],
"source": [
"from pymongo import MongoClient\n",
......@@ -93,12 +93,12 @@
},
{
"cell_type": "code",
"execution_count": 124,
"execution_count": 145,
"outputs": [
{
"name": "stdout",
"text": [
"Loaded 563 runs.\n"
"Loaded 572 runs.\n"
],
"output_type": "stream"
}
......@@ -118,7 +118,7 @@
},
{
"cell_type": "code",
"execution_count": 125,
"execution_count": 146,
"outputs": [
{
"name": "stdout",
......@@ -145,19 +145,19 @@
},
{
"cell_type": "code",
"execution_count": 126,
"execution_count": 147,
"outputs": [
{
"name": "stdout",
"text": [
"Loaded 12 distinct experiments, without reruns.\n"
"Loaded 13 distinct experiments, without reruns.\n"
],
"output_type": "stream"
}
],
"source": [
"descriptors = [d for d in descriptors if d.split('_')[-1] != 'rerun']\n",
"descriptors = [d for d in descriptors if d.split('_')[2] != '2']\n",
"# descriptors = [d for d in descriptors if d.split('_')[2] != '2']\n",
"# for descriptor in descriptors:\n",
"# print(descriptor)\n",
" \n",
......@@ -173,7 +173,7 @@
},
{
"cell_type": "code",
"execution_count": 127,
"execution_count": 148,
"outputs": [],
"source": [
"# Extract Results\n",
......@@ -202,30 +202,31 @@
},
{
"cell_type": "code",
"execution_count": 130,
"execution_count": 149,
"outputs": [
{
"name": "stdout",
"text": [
"Best Model for Machine Type 0: [ 2 9 1 5 6 10 4 8 7 12 11 3 0]\n",
"Best Model for Machine Type 1: [ 4 2 6 8 9 12 10 5 1 7 3 11 0]\n",
"Best Model for Machine Type 2: [ 4 9 1 5 8 10 12 6 2 11 3 7 0]\n",
"Best Model for Machine Type 3: [10 1 11 9 5 2 4 8 12 6 3 7 0]\n",
"Best Model for Machine Type 4: [12 8 1 5 4 6 7 2 3 11 9 10 0]\n",
"Best Model for Machine Type 5: [11 3 10 7 4 9 6 2 12 5 1 8 0]\n",
"Best Model for Machine Type 0: [ 8 2 10 1 5 6 11 4 9 7 13 12 3 0]\n",
"Best Model for Machine Type 1: [ 8 4 2 6 9 10 13 11 5 1 7 3 12 0]\n",
"Best Model for Machine Type 2: [ 4 10 1 8 5 9 11 13 6 2 12 3 7 0]\n",
"Best Model for Machine Type 3: [11 1 12 10 5 2 4 9 8 13 6 3 7 0]\n",
"Best Model for Machine Type 4: [13 9 1 5 4 6 7 2 3 12 10 11 8 0]\n",
"Best Model for Machine Type 5: [ 8 12 3 11 7 4 10 6 2 13 5 1 9 0]\n",
"00: ID-04 resnet_gridsearch_a_bit_larger_loose_1e-4_100_BCE\n",
"01: ID-09 resnet_gridsearch_a_bit_larger_loose_1e-4_100_AUC\n",
"02: ID-01 resnet_gridsearch_a_bit_larger_loose_1e-5_100_BCE\n",
"03: ID-10 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_BCE\n",
"04: ID-05 resnet_gridsearch_a_bit_larger_loose_1e-5_100_AUC\n",
"05: ID-02 resnet_gridsearch_normal_loose_1e-4_100_BCE\n",
"06: ID-08 resnet_gridsearch_normal_loose_1e-5_100_BCE\n",
"07: ID-06 resnet_gridsearch_normal_loose_1e-4_100_AUC\n",
"08: ID-12 resnet_gridsearch_normal_loose_1e-5_100_AUC\n",
"09: ID-11 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_AUC\n",
"10: ID-07 resnet_gridsearch_a_bit_smaller_loose_1e-5_100_AUC\n",
"11: ID-03 resnet_gridsearch_a_bit_smaller_loose_1e-5_100_BCE\n",
"12: ID-00 baseline\n"
"01: ID-08 resnet_gridsearch_2_a_bit_larger_loose_1e-4_0.99_100_BCE\n",
"02: ID-10 resnet_gridsearch_a_bit_larger_loose_1e-4_100_AUC\n",
"03: ID-01 resnet_gridsearch_a_bit_larger_loose_1e-5_100_BCE\n",
"04: ID-11 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_BCE\n",
"05: ID-05 resnet_gridsearch_a_bit_larger_loose_1e-5_100_AUC\n",
"06: ID-02 resnet_gridsearch_normal_loose_1e-4_100_BCE\n",
"07: ID-09 resnet_gridsearch_normal_loose_1e-5_100_BCE\n",
"08: ID-06 resnet_gridsearch_normal_loose_1e-4_100_AUC\n",
"09: ID-12 resnet_gridsearch_a_bit_smaller_loose_1e-4_100_AUC\n",
"10: ID-13 resnet_gridsearch_normal_loose_1e-5_100_AUC\n",
"11: ID-07 resnet_gridsearch_a_bit_smaller_loose_1e-5_100_AUC\n",
"12: ID-03 resnet_gridsearch_a_bit_smaller_loose_1e-5_100_BCE\n",
"13: ID-00 baseline\n"
],
"output_type": "stream"
}
......@@ -264,7 +265,7 @@
},
{
"cell_type": "code",
"execution_count": 131,
"execution_count": 156,
"outputs": [],
"source": [
"import sklearn\n",
......@@ -287,7 +288,7 @@
},
{
"cell_type": "code",
"execution_count": 132,
"execution_count": 157,
"outputs": [],
"source": [
"# Create Submission 1"
......@@ -302,7 +303,7 @@
},
{
"cell_type": "code",
"execution_count": 133,
"execution_count": 158,
"outputs": [],
"source": [
"for machine_type in range(6):\n",
......@@ -324,7 +325,7 @@
},
{
"cell_type": "code",
"execution_count": 134,
"execution_count": 159,
"outputs": [
{
"name": "stdout",
......@@ -375,7 +376,7 @@
},
{
"cell_type": "code",
"execution_count": 135,
"execution_count": 160,
"outputs": [],
"source": [
"\n",
......@@ -392,7 +393,7 @@
},
{
"cell_type": "code",
"execution_count": 136,
"execution_count": 161,
"outputs": [],
"source": [
"for machine_type, idxes in enumerate(best_idxes):\n",
......@@ -470,7 +471,7 @@
},
{
"cell_type": "code",
"execution_count": 138,
"execution_count": 162,
"outputs": [],
"source": [
"# Create Submission 3 # median ensemble"
......@@ -485,14 +486,14 @@
},
{
"cell_type": "code",
"execution_count": 139,
"execution_count": 168,
"outputs": [],
"source": [
"for machine_type, idxes in enumerate(best_idxes):\n",
" for machine_id in EVALUATION_ID_MAP[machine_type]:\n",
" file_names = []\n",
" scores = []\n",
" for idx in idxes[:12]:\n",
" for idx in idxes[:5]:\n",
" best_model_folder = run_ids[idx]\n",
" src_path = os.path.join('..', 'experiment_logs', best_model_folder)\n",
" src = os.path.join(src_path, f'anomaly_score_{INVERSE_CLASS_MAP[machine_type]}_id_{machine_id}_mean.csv')\n",
......@@ -515,29 +516,29 @@
},
{
"cell_type": "code",
"execution_count": 140,
"execution_count": 169,
"outputs": [
{
"name": "stdout",
"text": [
"\tfan:\n",
"\t\taveraged_auc: 0.922963162623858\n",
"\t\taveraged_pauc: 0.8295933163510599\n",
"\t\taveraged_auc: 0.9281888985937587\n",
"\t\taveraged_pauc: 0.8283523606556178\n",
"\tpump:\n",
"\t\taveraged_auc: 0.9124607229813113\n",
"\t\taveraged_pauc: 0.8666248189235806\n",
"\t\taveraged_auc: 0.9209936334730452\n",
"\t\taveraged_pauc: 0.8705862272890137\n",
"\tslider:\n",
"\t\taveraged_auc: 0.9807724719101123\n",
"\t\taveraged_pauc: 0.9061945594322887\n",
"\t\taveraged_auc: 0.9858871722846442\n",
"\t\taveraged_pauc: 0.9268061304947763\n",
"\tToyCar:\n",
"\t\taveraged_auc: 0.9510095360614229\n",
"\t\taveraged_pauc: 0.8885660226896572\n",
"\t\taveraged_auc: 0.9547106714040676\n",
"\t\taveraged_pauc: 0.8913650442572985\n",
"\tToyConveyor:\n",
"\t\taveraged_auc: 0.838146460887509\n",
"\t\taveraged_pauc: 0.7153167654318638\n",
"\t\taveraged_auc: 0.8514805262648587\n",
"\t\taveraged_pauc: 0.7374989794507775\n",
"\tvalve:\n",
"\t\taveraged_auc: 0.9348333333333334\n",
"\t\taveraged_pauc: 0.8771929824561403\n"
"\t\taveraged_auc: 0.9696039915966386\n",
"\t\taveraged_pauc: 0.9118411838419578\n"
],
"output_type": "stream"
}
......@@ -550,7 +551,7 @@
" for machine_id in TRAINING_ID_MAP[machine_type]:\n",
" file_names = []\n",
" scores = []\n",
" for idx in idxes[:12]:\n",
" for idx in idxes[:5]:\n",
" best_model_folder = run_ids[idx]\n",
" src_path = os.path.join('..', 'experiment_logs', best_model_folder)\n",
" src = os.path.join(src_path, f'anomaly_score_{INVERSE_CLASS_MAP[machine_type]}_id_{machine_id}_mean.csv')\n",
......@@ -575,7 +576,7 @@
},
{
"cell_type": "code",
"execution_count": 141,
"execution_count": 165,
"outputs": [],
"source": [
"# Create Submission 4 # mean ensemble"
......@@ -590,21 +591,21 @@
},
{
"cell_type": "code",
"execution_count": 142,
"execution_count": 175,
"outputs": [],
"source": [
"for machine_type, idxes in enumerate(best_idxes):\n",
" for machine_id in EVALUATION_ID_MAP[machine_type]:\n",
" file_names = []\n",
" scores = []\n",
" for idx in idxes[:12]:\n",
" for idx in idxes[:13]:\n",
" best_model_folder = run_ids[idx]\n",
" src_path = os.path.join('..', 'experiment_logs', best_model_folder)\n",
" src = os.path.join(src_path, f'anomaly_score_{INVERSE_CLASS_MAP[machine_type]}_id_{machine_id}_mean.csv')\n",
" scores.append(pd.read_csv(src, names=['file_name', 'score'], index_col=False).to_numpy()[:, 1])\n",
" file_names.append(pd.read_csv(src, names=['file_name', 'score'], index_col=False).to_numpy()[:, 0])\n",
" \n",
" scores = list(np.array(scores).T.mean(axis=-1).reshape(-1))\n",
" scores = list(np.median(np.array(scores).T, axis=-1).reshape(-1))\n",
" dst_path = os.path.join('..', 'submission_package', 'task2', 'Primus_CP-JKU_task2_4')\n",
" dst = os.path.join(dst_path, f'anomaly_score_{INVERSE_CLASS_MAP[machine_type]}_id_{machine_id:02d}.csv')\n",
"\n",
......@@ -620,29 +621,29 @@
},
{
"cell_type": "code",
"execution_count": 143,
"execution_count": 176,
"outputs": [
{
"name": "stdout",
"text": [
"\tfan:\n",
"\t\taveraged_auc: 0.9250862155990746\n",
"\t\taveraged_pauc: 0.8256360162889946\n",
"\t\taveraged_auc: 0.9230309586203593\n",
"\t\taveraged_pauc: 0.8285210664235381\n",
"\tpump:\n",
"\t\taveraged_auc: 0.9109113160157278\n",
"\t\taveraged_pauc: 0.8682161756465161\n",
"\t\taveraged_auc: 0.9146627457465693\n",
"\t\taveraged_pauc: 0.8678065821022478\n",
"\tslider:\n",
"\t\taveraged_auc: 0.9786540262172283\n",
"\t\taveraged_pauc: 0.8951434062684802\n",
"\t\taveraged_auc: 0.9822893258426966\n",
"\t\taveraged_pauc: 0.9108762073723635\n",
"\tToyCar:\n",
"\t\taveraged_auc: 0.9526391101037327\n",
"\t\taveraged_pauc: 0.8904420678626239\n",
"\t\taveraged_auc: 0.9504648370497427\n",
"\t\taveraged_pauc: 0.8890240180210388\n",
"\tToyConveyor:\n",
"\t\taveraged_auc: 0.8460375767354439\n",
"\t\taveraged_pauc: 0.7258267906077309\n",
"\t\taveraged_auc: 0.8254031447576784\n",
"\t\taveraged_pauc: 0.7026976317730064\n",
"\tvalve:\n",
"\t\taveraged_auc: 0.9449583333333333\n",
"\t\taveraged_pauc: 0.8856359649122807\n"
"\t\taveraged_auc: 0.93825\n",
"\t\taveraged_pauc: 0.8792763157894736\n"
],
"output_type": "stream"
}
......@@ -655,14 +656,14 @@
" for machine_id in TRAINING_ID_MAP[machine_type]:\n",
" file_names = []\n",
" scores = []\n",
" for idx in idxes[:12]:\n",
" for idx in idxes[:13]:\n",
" best_model_folder = run_ids[idx]\n",
" src_path = os.path.join('..', 'experiment_logs', best_model_folder)\n",
" src = os.path.join(src_path, f'anomaly_score_{INVERSE_CLASS_MAP[machine_type]}_id_{machine_id}_mean.csv')\n",
" scores.append(pd.read_csv(src, names=['file_name', 'score'], index_col=False).to_numpy()[:, 1])\n",
" file_names.append(pd.read_csv(src, names=['file_name', 'score'], index_col=False).to_numpy()[:, 0])\n",
" \n",
" scores = list(np.array(scores).T.mean(axis=-1).reshape(-1))\n",
" scores = list(np.median(np.array(scores).T, axis=-1).reshape(-1))\n",
" file_names = np.array([1 if name.split('_')[0] == 'anomaly' else 0 for name in file_names[0]]) \n",
" a, p = sklearn.metrics.roc_auc_score(file_names, scores), sklearn.metrics.roc_auc_score(file_names, scores, max_fpr=0.1)\n",
" auc.append(a)\n",
......
......@@ -102,7 +102,7 @@ system:
# In case of ensemble approaches, add up parameters for all subsystems.
# In case embeddings are used, add up parameter count of the embedding extraction networks and classification network.
# Use numerical value.
total_parameters: 9600000
total_parameters: 1000000
# List of external datasets used in the submission.
# Development dataset is used here only as an example, list only external datasets
......
......@@ -102,7 +102,7 @@ system:
# In case of ensemble approaches, add up parameters for all subsystems.
# In case embeddings are used, add up parameter count of the embedding extraction networks and classification network.
# Use numerical value.
total_parameters: 9600000
total_parameters: 12000000
# List of external datasets used in the submission.
# Development dataset is used here only as an example, list only external datasets
......@@ -146,6 +146,3 @@ results:
valve:
averaged_auc: 0.9776656162464985
averaged_pauc: 0.9357400855078873
id_01_00000000.wav,1.1210983991622925
id_01_00000001.wav,1.1466665267944336
id_01_00000002.wav,0.8824521899223328
id_01_00000003.wav,1.0552852153778076
id_01_00000004.wav,-1.183948278427124
id_01_00000005.wav,0.6197622418403625
id_01_00000006.wav,-1.167053461074829
id_01_00000007.wav,-1.1847805976867676
id_01_00000008.wav,0.9049229621887207
id_01_00000009.wav,-1.1753199100494385
id_01_00000010.wav,0.5300949811935425
id_01_00000011.wav,0.5063624978065491
id_01_00000012.wav,1.0821229219436646
id_01_00000013.wav,-1.1448915004730225
id_01_00000014.wav,-1.1791231632232666
id_01_00000015.wav,0.3743613362312317
id_01_00000016.wav,-1.100714087486267
id_01_00000017.wav,-1.1817433834075928
id_01_00000018.wav,0.6172735691070557
id_01_00000019.wav,1.1466976404190063
id_01_00000020.wav,-0.5077235698699951
id_01_00000021.wav,-1.1287075281143188
id_01_00000022.wav,0.5645463466644287
id_01_00000023.wav,1.1332900524139404
id_01_00000024.wav,-1.1781843900680542
id_01_00000025.wav,-1.1658868789672852
id_01_00000026.wav,0.8868559002876282
id_01_00000027.wav,-1.161880373954773
id_01_00000028.wav,-1.1402015686035156
id_01_00000029.wav,0.7164785861968994
id_01_00000030.wav,1.0656511783599854
id_01_00000031.wav,-1.1550978422164917
id_01_00000032.wav,-1.178971767425537
id_01_00000033.wav,-0.30746325850486755
id_01_00000034.wav,1.1352827548980713
id_01_00000035.wav,1.099847674369812
id_01_00000036.wav,-1.1172916889190674
id_01_00000037.wav,0.45853546261787415
id_01_00000038.wav,1.1095504760742188
id_01_00000039.wav,1.1442252397537231
id_01_00000040.wav,-1.1692746877670288
id_01_00000041.wav,1.1507630348205566
id_01_00000042.wav,-1.173393964767456
id_01_00000043.wav,1.123020887374878
id_01_00000044.wav,-1.1788341999053955
id_01_00000045.wav,0.13773688673973083
id_01_00000046.wav,0.15781493484973907
id_01_00000047.wav,0.34982699155807495
id_01_00000048.wav,0.9027346968650818
id_01_00000049.wav,-1.1752989292144775
id_01_00000050.wav,0.8768077492713928
id_01_00000051.wav,0.0644167959690094
id_01_00000052.wav,0.3088078200817108
id_01_00000053.wav,1.1015907526016235
id_01_00000054.wav,-1.1432387828826904
id_01_00000055.wav,-1.1430590152740479
id_01_00000056.wav,0.46344777941703796
id_01_00000057.wav,-1.1683828830718994
id_01_00000058.wav,1.1428948640823364
id_01_00000059.wav,1.1397424936294556
id_01_00000060.wav,1.0901395082473755
id_01_00000061.wav,1.1470683813095093
id_01_00000062.wav,1.0901858806610107
id_01_00000063.wav,0.4991740584373474
id_01_00000064.wav,-1.1865298748016357
id_01_00000065.wav,-1.1721925735473633
id_01_00000066.wav,0.48920905590057373
id_01_00000067.wav,-1.1768007278442383
id_01_00000068.wav,1.0746567249298096
id_01_00000069.wav,-1.010432481765747
id_01_00000070.wav,1.145697832107544
id_01_00000071.wav,1.135191559791565
id_01_00000072.wav,-1.1789177656173706
id_01_00000073.wav,-0.06152646243572235
id_01_00000074.wav,-0.698987603187561
id_01_00000075.wav,1.1356444358825684
id_01_00000076.wav,-1.1808600425720215
id_01_00000077.wav,-1.1729981899261475
id_01_00000078.wav,1.1425936222076416
id_01_00000079.wav,-0.9050460457801819
id_01_00000080.wav,0.2863955795764923
id_01_00000081.wav,-1.171536922454834
id_01_00000082.wav,-1.120895504951477
id_01_00000083.wav,0.846526563167572
id_01_00000084.wav,-1.1597867012023926
id_01_00000085.wav,-1.1841092109680176
id_01_00000086.wav,1.1394546031951904
id_01_00000087.wav,-1.1808483600616455
id_01_00000088.wav,-1.1033341884613037
id_01_00000089.wav,-1.1632386445999146
id_01_00000090.wav,-1.1632068157196045
id_01_00000091.wav,-1.0718916654586792
id_01_00000092.wav,-1.1615208387374878
id_01_00000093.wav,1.1423983573913574
id_01_00000094.wav,-1.1459507942199707
id_01_00000095.wav,-1.0351691246032715
id_01_00000096.wav,1.082133412361145
id_01_00000097.wav,0.8667988181114197
id_01_00000098.wav,-1.1827466487884521
id_01_00000099.wav,1.1107851266860962
id_01_00000100.wav,1.108077049255371
id_01_00000101.wav,1.1396456956863403
id_01_00000102.wav,1.0438084602355957
id_01_00000103.wav,-1.1649425029754639
id_01_00000104.wav,1.1483889818191528
id_01_00000105.wav,-1.036178708076477
id_01_00000106.wav,1.106369972229004
id_01_00000107.wav,-1.1436132192611694
id_01_00000108.wav,-1.1667519807815552
id_01_00000109.wav,-1.1723464727401733
id_01_00000110.wav,-1.1482722759246826
id_01_00000111.wav,1.1250252723693848
id_01_00000112.wav,0.9738894104957581
id_01_00000113.wav,0.9379087090492249
id_01_00000114.wav,-1.174261212348938
id_01_00000115.wav,-1.1712905168533325
id_01_00000116.wav,-1.1505290269851685
id_01_00000117.wav,-1.1500242948532104
id_01_00000118.wav,1.100522518157959
id_01_00000119.wav,0.9352900385856628
id_01_00000120.wav,-1.1525546312332153
id_01_00000121.wav,-1.1702985763549805
id_01_00000122.wav,1.1234592199325562
id_01_00000123.wav,-1.1647889614105225
id_01_00000124.wav,1.0996226072311401
id_01_00000125.wav,-1.168388843536377
id_01_00000126.wav,1.1437690258026123
id_01_00000127.wav,-1.1775683164596558
id_01_00000128.wav,0.5883982181549072
id_01_00000129.wav,1.1473851203918457
id_01_00000130.wav,-0.6323193907737732
id_01_00000131.wav,-1.0772969722747803
id_01_00000132.wav,0.40654638409614563
id_01_00000133.wav,0.9587719440460205
id_01_00000134.wav,-1.1418639421463013
id_01_00000135.wav,-1.1601704359054565
id_01_00000136.wav,-0.24380522966384888
id_01_00000137.wav,-1.167944073677063
id_01_00000138.wav,-1.1411216259002686
id_01_00000139.wav,1.0145479440689087
id_01_00000140.wav,0.26315295696258545
id_01_00000141.wav,-1.1628166437149048
id_01_00000142.wav,0.8987292051315308
id_01_00000143.wav,-1.159146785736084
id_01_00000144.wav,-1.1801259517669678
id_01_00000145.wav,0.6679368615150452
id_01_00000146.wav,-1.1616547107696533
id_01_00000147.wav,-0.9936201572418213
id_01_00000148.wav,-1.1777572631835938
id_01_00000149.wav,-1.1706324815750122
id_01_00000150.wav,1.14674973487854
id_01_00000151.wav,-1.1498751640319824
id_01_00000152.wav,-1.168291687965393
id_01_00000153.wav,1.1524287462234497
id_01_00000154.wav,0.3995632827281952
id_01_00000155.wav,0.14384670555591583
id_01_00000156.wav,-1.1312412023544312
id_01_00000157.wav,0.6268702745437622