{"cells":[{"metadata":{},"cell_type":"markdown","source":"In this notebook I present the basic keypoints of my attempt to tackle the problem. I hope you all find it helpfull. The key-points are:\n* I choose a `np.log` version of `scipy.signal.spectrogram` to transform 1-D audio signal to 2-D imaging.\n* The model uses softmax activation function.\n* During training I select random 1-seconds parts from the audio signals (see `DataGenerator`).\n* I use a stratified version of k-fold based on the *first* class. That means that for stratification purposes I choose *one of the many classes* (see dictionary `first_labels_set`) \n* I calculate out-of-fold predictions (`oof_y`) which I use to estimate the lwlrap score.\n* The test set is evaluated and averaged `k=5` times. The evaluation is done using `TestDataGenerator` hence introducing some randomness and non-determinism (`res_Y = model.predict_generator(test_gen, verbose=1)`)\n* The training process is optimizing `categorical_crossentropy` and monitors `categorical_accuracy` for termination.\n* By using early stopping in each fold I implicitly introduce some overfitting on the validation set. I expect more stable estimation by using fixed number of iterations, but is is not my style :) \n* The whole kernel takes ~2 hours to train and a couple of minutes for inference if you use the pretrained weights I already attach. "},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nfrom os.path import isdir, join\nfrom pathlib import Path\nimport pandas as pd\nimport time\n\n# Math\nimport numpy as np\nfrom scipy.fftpack import fft\nfrom scipy import signal\nfrom scipy.io import wavfile\nimport librosa\n\nfrom sklearn.decomposition import PCA\n\n# Visualization\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport IPython.display as ipd\nimport librosa.display\n\nimport plotly.offline as py\npy.init_notebook_mode(connected=True)\nimport plotly.graph_objs as go\nimport plotly.tools as tls\nimport pandas as pd\n\n%matplotlib inline\nt1 = time.time()","execution_count":30,"outputs":[{"output_type":"display_data","data":{"text/html":"","text/vnd.plotly.v1+html":""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## Read necessary files and folders \ntrain_audio_path = '../input/freesound-audio-tagging-2019/train_curated/'\ntrain_files = os.listdir(train_audio_path)\ntrain_annot = pd.read_csv('../input/freesound-audio-tagging-2019/train_curated.csv')\ntest_audio_path = '../input/freesound-audio-tagging-2019/test/'\ntest_files = np.sort(os.listdir(test_audio_path))\nprint (test_files[:5])\n##\n## I 've created the weights in previous run. Just use them\nUSE_WEIGHTS = True\nlen(train_files), len(test_files)\n","execution_count":31,"outputs":[{"output_type":"stream","text":"['000ccb97.wav' '0012633b.wav' '001ed5f1.wav' '00294be0.wav'\n '003fde7a.wav']\n","name":"stdout"},{"output_type":"execute_result","execution_count":31,"data":{"text/plain":"(4970, 1120)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## Here we calculate unique labels (80) and create the necessary data structures\n## for binary encoding the multi-labeled input\n##\n## label_dict : dictionary with classes as keys and counts per classes as values\n## {'Bark': 74, 'Raindrop': 74, 'Finger_snapping': 74, 'Run': 74, 'Whispering': 74, .... }\n## classes: 80 sound classes \n## ['Bark', 'Raindrop', 'Finger_snapping', 'Run', 'Whispering', ...]\n## all_labels_set (size: 4970): List of sets. The same size as training sounds. Each set correspond to the classes of the i-th sound\n## [{'Bark'}, {'Raindrop'}, {'Finger_snapping'}, {'Run'}, {'Finger_snapping'}, {'Whispering'}, {'Acoustic_guitar', 'Strum'}, ...]\n## first_labels_set (size: 4970) : List containing only first class for each training pattern.. to be used as approximation stratification \n## ['Bark', 'Raindrop', 'Finger_snapping', 'Run', 'Finger_snapping', 'Whispering', 'Acoustic_guitar', ...]\n\n##\n## L = 1 * SAMPLE_RATE -> 1 second\n## L = 2 * SAMPLE_RATE -> 2 seconds ....\n\nSAMPLE_RATE = 44100\nL = 1 * SAMPLE_RATE\n\ndef create_unique_labels(all_labels):\n label_dict = {}\n all_labels_set = []\n first_labels_set = []\n for labs in all_labels:\n lab = labs.split(',')\n for l in lab:\n if l in label_dict:\n label_dict[l] = label_dict[l] + 1\n else:\n label_dict[l]= 0\n\n all_labels_set.append(set(lab))\n first_labels_set.append(lab[0])\n classes = list(label_dict.keys())\n \n return label_dict, classes, all_labels_set, first_labels_set","execution_count":32,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_dict, classes, all_labels_set, first_labels_set = create_unique_labels(train_annot.labels)\nfiles = train_annot.fname\nprint (len(files), len(train_files))","execution_count":33,"outputs":[{"output_type":"stream","text":"4970 4970\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## Y_split are the binary labels used for stratification\n## Y is the target\nfrom sklearn.preprocessing import MultiLabelBinarizer, LabelEncoder\nbinarize = MultiLabelBinarizer(classes=classes)\nencode = LabelEncoder()\nY_split = encode.fit_transform(first_labels_set)\nY = binarize.fit_transform(all_labels_set)","execution_count":34,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## Read all training files and keep them in memory\nfrom tqdm import tqdm_notebook\nX_raw = []\nfor f in tqdm_notebook(files):\n sample_rate, sample_ = wavfile.read(str(train_audio_path) + f)\n X_raw.append(sample_)","execution_count":35,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=4970), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"4a3ada87d7404633a72f06e596524628"}},"metadata":{}},{"output_type":"stream","text":"\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## Nice helper functions for padding, random sampling L samples\n\ndef pad_audio(samples):\n if len(samples) >= L: return samples\n else: return np.pad(samples, pad_width=(L - len(samples), 0), mode='constant', constant_values=(0, 0))\n\n# 150000 , 44100 -> [0, .,......., (150000-44100)]\ndef chop_audio(samples):\n beg = np.random.randint(0, len(samples) - L)\n return samples[beg: beg + L]\n \n \ndef log_specgram(audio, \n sample_rate, \n window_size=20,\n step_size=10, eps=1e-10):\n nperseg = int(round(window_size * sample_rate / 1e3))\n noverlap = int(round(step_size * sample_rate / 1e3))\n freqs, times, spec = signal.spectrogram(audio,\n fs=sample_rate,\n window='hann',\n nperseg=nperseg,\n noverlap=noverlap,\n detrend=False)\n return freqs, times, np.log(spec.astype(np.float32) + eps)","execution_count":36,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"##\n## DataGenerator based on keras.utils.Sequence. The nice thing about it is the random part selection that works like augmentation.\n## TestDataGenerator is bad software engineering from my part... Essentially the same generator used only for inference...\n\nimport numpy as np\nimport keras\n\nclass DataGenerator(keras.utils.Sequence):\n 'Generates data for Keras'\n def __init__(self, list_IDs, labels, batch_size=32, dim=(256,256,1), n_channels=1,\n n_classes=80, shuffle=True):\n 'Initialization'\n self.dim = dim\n self.batch_size = batch_size\n self.labels = labels\n self.list_IDs = list_IDs\n self.n_channels = n_channels\n self.n_classes = n_classes\n self.shuffle = shuffle\n self.on_epoch_end()\n\n def __len__(self):\n 'Denotes the number of batches per epoch'\n return int(np.ceil(len(self.list_IDs) / self.batch_size))\n\n def __getitem__(self, index):\n 'Generate one batch of data'\n # Generate indexes of the batch\n max_index = min((index+1)*self.batch_size, len(self.list_IDs))\n indexes = self.indexes[index*self.batch_size:max_index]\n\n # Find list of IDs\n list_IDs_temp = [self.list_IDs[k] for k in indexes]\n\n # Generate data\n X, y = self.__data_generation(list_IDs_temp)\n\n return X, y\n\n def on_epoch_end(self):\n 'Updates indexes after each epoch'\n self.indexes = np.arange(len(self.list_IDs))\n if self.shuffle == True:\n np.random.shuffle(self.indexes)\n\n def __data_generation(self, list_IDs_temp):\n 'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)\n # Initialization\n X = []# np.empty((self.batch_size, *self.dim, self.n_channels))\n y = []# np.empty((self.batch_size), dtype=int)\n t1 = time.time()\n #print (list_IDs_temp)\n\n # Generate data\n for i, ID in enumerate(list_IDs_temp):\n #print (i, ID)\n # Store samplw\n xx = X_raw[ID].copy()\n \n xx = pad_audio(xx)\n if len(xx) > L:\n xx = chop_audio(xx)\n _, _, specgram = log_specgram(xx, sample_rate=SAMPLE_RATE, window_size=10, step_size=5)\n X.append(specgram)\n\n # Store class\n y.append(self.labels[ID, :])\n \n t2 = time.time()\n #print (t2-t1)\n y = np.array(y, dtype='float32')\n X = np.expand_dims(np.array(X), -1)\n return X, y\n\nclass TestDataGenerator(keras.utils.Sequence):\n 'Generates data for Keras'\n def __init__(self, test_files, test_base_path, batch_size=32, dim=(256,256,1), n_channels=1,\n n_classes=80):\n 'Initialization'\n self.dim = dim\n self.batch_size = batch_size\n self.test_base_path = test_base_path\n self.test_files = test_files\n self.n_channels = n_channels\n self.n_classes = n_classes\n self.on_epoch_end()\n\n def __len__(self):\n 'Denotes the number of batches per epoch'\n return int(np.ceil(len(self.test_files) / self.batch_size))\n\n def __getitem__(self, index):\n 'Generate one batch of data'\n # Generate indexes of the batch\n max_index = min((index+1)*self.batch_size, len(self.test_files))\n indexes = self.indexes[index*self.batch_size:max_index]\n\n # Find list of IDs\n list_IDs_temp = [self.test_files[k] for k in indexes]\n\n # Generate data\n X = self.__data_generation(list_IDs_temp)\n\n return X\n\n def on_epoch_end(self):\n 'Updates indexes after each epoch'\n self.indexes = np.arange(len(self.test_files))\n\n\n def __data_generation(self, list_IDs_temp):\n 'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)\n # Initialization\n X = []# np.empty((self.batch_size, *self.dim, self.n_channels))\n\n # Generate data\n for i, ID in enumerate(list_IDs_temp):\n # Store samplw\n sample_rate, xx = wavfile.read(str(self.test_base_path) + ID)\n xx = pad_audio(xx)\n if len(xx) > L:\n xx = chop_audio(xx)\n _, _, specgram = log_specgram(xx, sample_rate=SAMPLE_RATE, window_size=10, step_size=5)\n X.append(specgram)\n\n X = np.expand_dims(np.array(X), -1)\n return X","execution_count":37,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import (Convolution2D, GlobalAveragePooling2D, BatchNormalization, Flatten,\n GlobalMaxPool2D, MaxPool2D, concatenate, Activation, Input, Dense)\nfrom keras.utils import Sequence, to_categorical\nfrom keras.optimizers import Adam\nfrom keras.losses import categorical_crossentropy\nfrom keras.models import Model\nfrom keras import backend as K\n\ndef get_2d_conv_model(input_shape= (221, 198, 1), n_classes=80, learning_rate=0.001):\n \n nclass = n_classes\n \n inp = Input(shape=(input_shape[0],input_shape[1],1))\n x = Convolution2D(32, (4,10), padding=\"same\")(inp)\n x = BatchNormalization()(x)\n x = Activation(\"relu\")(x)\n x = MaxPool2D()(x)\n \n x = Convolution2D(32, (4,10), padding=\"same\")(x)\n x = BatchNormalization()(x)\n x = Activation(\"relu\")(x)\n x = MaxPool2D()(x)\n \n x = Convolution2D(32, (4,10), padding=\"same\")(x)\n x = BatchNormalization()(x)\n x = Activation(\"relu\")(x)\n x = MaxPool2D()(x)\n \n x = Convolution2D(32, (4,10), padding=\"same\")(x)\n x = BatchNormalization()(x)\n x = Activation(\"relu\")(x)\n x = MaxPool2D()(x)\n\n x = Flatten()(x)\n x = Dense(64)(x)\n x = BatchNormalization()(x)\n x = Activation(\"relu\")(x)\n out = Dense(nclass, activation='softmax')(x)\n\n model = Model(inputs=inp, outputs=out)\n opt = Adam(learning_rate)\n\n model.compile(optimizer=opt, loss=categorical_crossentropy, metrics=['categorical_accuracy'])\n return model","execution_count":38,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nmodelname = 'custom-v1-'\ntest_gen = TestDataGenerator(test_files, test_audio_path, batch_size=32)","execution_count":39,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":false},"cell_type":"code","source":"from sklearn.model_selection import StratifiedKFold\noof_y = np.zeros_like(Y, dtype='float32')\ntest_Y = np.zeros((len(test_files), 80), dtype='float32')\n\nkfold = StratifiedKFold(5)\nifold = 0\nfor train_index, valid_index in kfold.split(X_raw, Y_split):\n print(\"TRAIN:\", train_index[:5], \"TEST:\", valid_index[:5])\n print(np.sum(Y[train_index, :], axis=0))\n print(np.sum(Y[valid_index, :], axis=0))\n print(\"--------------------------------------------\")\n \n checkpoint = ModelCheckpoint(modelname + str(ifold) + '.hdf5', monitor='val_categorical_accuracy', verbose=1, \n save_best_only=True, save_weights_only=True, mode='auto', period=1)\n early = EarlyStopping(monitor='val_categorical_accuracy', min_delta=0.001, patience=10, verbose=1, mode='auto', restore_best_weights=True)\n \n reduce_lr = ReduceLROnPlateau(monitor='val_categorical_accuracy', factor=0.5, patience=5, verbose=1)\n\n model = get_2d_conv_model()\n train_gen = DataGenerator(train_index, Y, batch_size=32, n_classes=80, shuffle=True)\n valid_gen = DataGenerator(valid_index, Y, batch_size=32, n_classes=80, shuffle=False)\n \n\n if USE_WEIGHTS == True:\n print ('Loading from ', '../input/custom-cnn-1-sec/' + modelname + str(ifold) + '.hdf5')\n model.load_weights('../input/custom-cnn-1-sec/' + modelname + str(ifold) + '.hdf5')\n else:\n model.fit_generator(train_gen, epochs=100, verbose=0, callbacks=[checkpoint, early, reduce_lr], validation_data=valid_gen)\n \n res = model.predict_generator(valid_gen, verbose=1)\n res_Y = model.predict_generator(test_gen, verbose=1)\n oof_y[valid_index, ] = res\n test_Y = test_Y + res_Y\n ifold = ifold + 1\n \n \ntest_Y = test_Y / 5 \n","execution_count":40,"outputs":[{"output_type":"stream","text":"TRAIN: [614 624 639 644 670] TEST: [0 1 2 3 4]\n[60 60 60 60 60 60 58 60 61 60 57 50 60 60 61 60 60 59 60 59 45 60 60 60\n 60 59 58 37 60 60 60 60 60 60 44 60 60 52 60 60 60 43 60 60 60 62 60 61\n 59 58 60 40 60 60 58 44 59 60 59 50 58 53 60 60 60 44 60 59 60 58 39 37\n 62 57 57 58 60 56 60 60]\n[15 15 15 15 15 15 17 15 14 15 18 13 15 15 14 15 15 16 15 16 12 15 15 15\n 15 16 17 10 15 15 15 15 15 15 12 15 15 13 15 15 15 10 15 15 15 13 15 14\n 16 17 15 10 15 15 17 12 16 15 16 13 17 14 15 15 15 12 15 16 15 17 10 11\n 13 18 15 17 15 19 15 15]\n--------------------------------------------\nLoading from ../input/custom-cnn-1-sec/custom-v1-0.hdf5\n32/32 [==============================] - 3s 109ms/step\n35/35 [==============================] - 4s 124ms/step\nTRAIN: [0 1 2 3 4] TEST: [614 624 639 644 670]\n[60 60 60 61 58 60 60 60 58 62 59 50 60 60 59 60 60 60 60 60 45 60 60 60\n 59 61 60 37 60 60 60 59 59 60 44 60 60 51 60 60 60 41 61 60 60 61 60 60\n 61 61 59 40 60 60 60 44 60 60 60 50 62 53 60 60 60 45 59 58 60 60 39 39\n 60 59 57 61 60 60 61 60]\n[15 15 15 14 17 15 15 15 17 13 16 13 15 15 16 15 15 15 15 15 12 15 15 15\n 16 14 15 10 15 15 15 16 16 15 12 15 15 14 15 15 15 12 14 15 15 14 15 15\n 14 14 16 10 15 15 15 12 15 15 15 13 13 14 15 15 15 11 16 17 15 15 10 9\n 15 16 15 14 15 15 14 15]\n--------------------------------------------\nLoading from ../input/custom-cnn-1-sec/custom-v1-1.hdf5\n32/32 [==============================] - 4s 112ms/step\n35/35 [==============================] - 4s 124ms/step\nTRAIN: [0 1 2 3 4] TEST: [1464 1505 1525 1539 1579]\n[60 60 60 60 61 60 59 59 59 60 60 50 60 60 61 60 60 59 60 60 46 60 60 59\n 61 58 58 38 60 59 60 60 58 60 45 60 60 54 60 60 60 42 57 60 60 59 60 56\n 56 60 61 40 60 60 60 45 62 60 59 50 62 54 60 60 60 45 59 56 60 60 39 39\n 59 63 58 60 59 59 58 60]\n[15 15 15 15 14 15 16 16 16 15 15 13 15 15 14 15 15 16 15 15 11 15 15 16\n 14 17 17 9 15 16 15 15 17 15 11 15 15 11 15 15 15 11 18 15 15 16 15 19\n 19 15 14 10 15 15 15 11 13 15 16 13 13 13 15 15 15 11 16 19 15 15 10 9\n 16 12 14 15 16 16 17 15]\n--------------------------------------------\nLoading from ../input/custom-cnn-1-sec/custom-v1-2.hdf5\n32/32 [==============================] - 3s 106ms/step\n35/35 [==============================] - 4s 122ms/step\nTRAIN: [0 1 2 3 4] TEST: [2273 2279 2328 2339 2436]\n[60 60 60 59 60 60 61 60 61 57 62 51 60 60 57 60 60 61 59 60 46 60 60 60\n 61 60 62 38 60 61 60 60 62 61 46 60 60 50 60 60 60 42 62 61 60 60 60 61\n 64 61 60 40 60 60 62 45 57 60 61 51 58 54 60 60 60 45 61 63 60 61 39 39\n 56 61 58 59 61 63 60 60]\n[15 15 15 16 15 15 14 15 14 18 13 12 15 15 18 15 15 14 16 15 11 15 15 15\n 14 15 13 9 15 14 15 15 13 14 10 15 15 15 15 15 15 11 13 14 15 15 15 14\n 11 14 15 10 15 15 13 11 18 15 14 12 17 13 15 15 15 11 14 12 15 14 10 9\n 19 14 14 16 14 12 15 15]\n--------------------------------------------\nLoading from ../input/custom-cnn-1-sec/custom-v1-3.hdf5\n31/31 [==============================] - 3s 109ms/step\n35/35 [==============================] - 4s 124ms/step\nTRAIN: [0 1 2 3 4] TEST: [3401 3414 3463 3586 3590]\n[60 60 60 60 61 60 62 61 61 61 62 51 60 60 62 60 60 61 61 61 46 60 60 61\n 59 62 62 38 60 60 60 61 61 59 45 60 60 53 60 60 60 44 60 59 60 58 60 62\n 60 60 60 40 60 60 60 46 62 60 61 51 60 54 60 60 60 45 61 64 60 61 40 38\n 63 60 58 62 60 62 61 60]\n[15 15 15 15 14 15 13 14 14 14 13 12 15 15 13 15 15 14 14 14 11 15 15 14\n 16 13 13 9 15 15 15 14 14 16 11 15 15 12 15 15 15 9 15 16 15 17 15 13\n 15 15 15 10 15 15 15 10 13 15 14 12 15 13 15 15 15 11 14 11 15 14 9 10\n 12 15 14 13 15 13 14 15]\n--------------------------------------------\nLoading from ../input/custom-cnn-1-sec/custom-v1-4.hdf5\n31/31 [==============================] - 4s 124ms/step\n35/35 [==============================] - 5s 135ms/step\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":false,"trusted":true},"cell_type":"code","source":"import numpy as np\nimport sklearn.metrics\n# Core calculation of label precisions for one test sample.\n\ndef _one_sample_positive_class_precisions(scores, truth):\n \"\"\"Calculate precisions for each true class for a single sample.\n \n Args:\n scores: np.array of (num_classes,) giving the individual classifier scores.\n truth: np.array of (num_classes,) bools indicating which classes are true.\n\n Returns:\n pos_class_indices: np.array of indices of the true classes for this sample.\n pos_class_precisions: np.array of precisions corresponding to each of those\n classes.\n \"\"\"\n num_classes = scores.shape[0]\n pos_class_indices = np.flatnonzero(truth > 0)\n # Only calculate precisions if there are some true classes.\n if not len(pos_class_indices):\n return pos_class_indices, np.zeros(0)\n # Retrieval list of classes for this sample. \n retrieved_classes = np.argsort(scores)[::-1]\n # class_rankings[top_scoring_class_index] == 0 etc.\n class_rankings = np.zeros(num_classes, dtype=np.int)\n class_rankings[retrieved_classes] = range(num_classes)\n # Which of these is a true label?\n retrieved_class_true = np.zeros(num_classes, dtype=np.bool)\n retrieved_class_true[class_rankings[pos_class_indices]] = True\n # Num hits for every truncated retrieval list.\n retrieved_cumulative_hits = np.cumsum(retrieved_class_true)\n # Precision of retrieval list truncated at each hit, in order of pos_labels.\n precision_at_hits = (\n retrieved_cumulative_hits[class_rankings[pos_class_indices]] / \n (1 + class_rankings[pos_class_indices].astype(np.float)))\n return pos_class_indices, precision_at_hits\n\n# All-in-one calculation of per-class lwlrap.\n\ndef calculate_per_class_lwlrap(truth, scores):\n \"\"\"Calculate label-weighted label-ranking average precision.\n \n Arguments:\n truth: np.array of (num_samples, num_classes) giving boolean ground-truth\n of presence of that class in that sample.\n scores: np.array of (num_samples, num_classes) giving the classifier-under-\n test's real-valued score for each class for each sample.\n \n Returns:\n per_class_lwlrap: np.array of (num_classes,) giving the lwlrap for each \n class.\n weight_per_class: np.array of (num_classes,) giving the prior of each \n class within the truth labels. Then the overall unbalanced lwlrap is \n simply np.sum(per_class_lwlrap * weight_per_class)\n \"\"\"\n assert truth.shape == scores.shape\n num_samples, num_classes = scores.shape\n # Space to store a distinct precision value for each class on each sample.\n # Only the classes that are true for each sample will be filled in.\n precisions_for_samples_by_classes = np.zeros((num_samples, num_classes))\n for sample_num in range(num_samples):\n pos_class_indices, precision_at_hits = (\n _one_sample_positive_class_precisions(scores[sample_num, :], \n truth[sample_num, :]))\n precisions_for_samples_by_classes[sample_num, pos_class_indices] = (\n precision_at_hits)\n labels_per_class = np.sum(truth > 0, axis=0)\n weight_per_class = labels_per_class / float(np.sum(labels_per_class))\n # Form average of each column, i.e. all the precisions assigned to labels in\n # a particular class.\n per_class_lwlrap = (np.sum(precisions_for_samples_by_classes, axis=0) / \n np.maximum(1, labels_per_class))\n # overall_lwlrap = simple average of all the actual per-class, per-sample precisions\n # = np.sum(precisions_for_samples_by_classes) / np.sum(precisions_for_samples_by_classes > 0)\n # also = weighted mean of per-class lwlraps, weighted by class label prior across samples\n # = np.sum(per_class_lwlrap * weight_per_class)\n return per_class_lwlrap, weight_per_class\n\n# Calculate the overall lwlrap using sklearn.metrics function.\n\ndef calculate_overall_lwlrap_sklearn(truth, scores):\n \"\"\"Calculate the overall lwlrap using sklearn.metrics.lrap.\"\"\"\n # sklearn doesn't correctly apply weighting to samples with no labels, so just skip them.\n sample_weight = np.sum(truth > 0, axis=1)\n nonzero_weight_sample_indices = np.flatnonzero(sample_weight > 0)\n overall_lwlrap = sklearn.metrics.label_ranking_average_precision_score(\n truth[nonzero_weight_sample_indices, :] > 0, \n scores[nonzero_weight_sample_indices, :], \n sample_weight=sample_weight[nonzero_weight_sample_indices])\n return overall_lwlrap\n\n\n# Accumulator object version.\n\nclass lwlrap_accumulator(object):\n \"\"\"Accumulate batches of test samples into per-class and overall lwlrap.\"\"\" \n\n def __init__(self):\n self.num_classes = 0\n self.total_num_samples = 0\n \n def accumulate_samples(self, batch_truth, batch_scores):\n \"\"\"Cumulate a new batch of samples into the metric.\n \n Args:\n truth: np.array of (num_samples, num_classes) giving boolean\n ground-truth of presence of that class in that sample for this batch.\n scores: np.array of (num_samples, num_classes) giving the \n classifier-under-test's real-valued score for each class for each\n sample.\n \"\"\"\n assert batch_scores.shape == batch_truth.shape\n num_samples, num_classes = batch_truth.shape\n if not self.num_classes:\n self.num_classes = num_classes\n self._per_class_cumulative_precision = np.zeros(self.num_classes)\n self._per_class_cumulative_count = np.zeros(self.num_classes, \n dtype=np.int)\n assert num_classes == self.num_classes\n for truth, scores in zip(batch_truth, batch_scores):\n pos_class_indices, precision_at_hits = (\n _one_sample_positive_class_precisions(scores, truth))\n self._per_class_cumulative_precision[pos_class_indices] += (\n precision_at_hits)\n self._per_class_cumulative_count[pos_class_indices] += 1\n self.total_num_samples += num_samples\n\n def per_class_lwlrap(self):\n \"\"\"Return a vector of the per-class lwlraps for the accumulated samples.\"\"\"\n return (self._per_class_cumulative_precision / \n np.maximum(1, self._per_class_cumulative_count))\n\n def per_class_weight(self):\n \"\"\"Return a normalized weight vector for the contributions of each class.\"\"\"\n return (self._per_class_cumulative_count / \n float(np.sum(self._per_class_cumulative_count)))\n\n def overall_lwlrap(self):\n \"\"\"Return the scalar overall lwlrap for cumulated samples.\"\"\"\n return np.sum(self.per_class_lwlrap() * self.per_class_weight())\n","execution_count":41,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"truth = Y\nscores = oof_y\nprint(\"lwlrap from sklearn.metrics =\", calculate_overall_lwlrap_sklearn(truth, scores))","execution_count":42,"outputs":[{"output_type":"stream","text":"lwlrap from sklearn.metrics = 0.6498104964891118\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"So we can see the out-of-fold metric scores around 0.65. We expect as submission that scores at least 0.45 on the public leaderboard."},{"metadata":{"trusted":true},"cell_type":"code","source":"\nsort_idx = np.argsort(classes).astype(int)\nsample_sub = pd.read_csv('../input/freesound-audio-tagging-2019/sample_submission.csv')\ntest_Y_sort = test_Y[:, sort_idx]\nsample_sub.iloc[:, 1:] = test_Y_sort\nsample_sub.to_csv('submission.csv', index=False)\n\nt2 = time.time()\nprint ('Total time: ', (t2-t1))","execution_count":43,"outputs":[{"output_type":"stream","text":"Total time: 52.201056480407715\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub.head()","execution_count":44,"outputs":[{"output_type":"execute_result","execution_count":44,"data":{"text/plain":" fname ... Zipper_(clothing)\n0 000ccb97.wav ... 0.001443\n1 0012633b.wav ... 0.014082\n2 001ed5f1.wav ... 0.011119\n3 00294be0.wav ... 0.009517\n4 003fde7a.wav ... 0.000016\n5 0040ccc9.wav ... 0.001096\n6 0046b732.wav ... 0.081312\n7 004f3bbc.wav ... 0.005014\n8 00526050.wav ... 0.000150\n9 00559da4.wav ... 0.167180\n10 00582bbe.wav ... 0.014790\n11 0064aedf.wav ... 0.129515\n12 0065512b.wav ... 0.130989\n13 006a91d2.wav ... 0.008649\n14 006ea9ee.wav ... 0.001273\n15 006f9dca.wav ... 0.066992\n16 007450dc.wav ... 0.000296\n17 00979c8a.wav ... 0.115068\n18 00992464.wav ... 0.010349\n19 00b44a8a.wav ... 0.000816\n20 00bfaaaf.wav ... 0.011089\n21 00cf9680.wav ... 0.012323\n22 00eae94d.wav ... 0.004880\n23 011ec5b8.wav ... 0.034261\n24 013200dc.wav ... 0.007325\n25 01440c2e.wav ... 0.000914\n26 01567a3d.wav ... 0.011832\n27 0163d203.wav ... 0.051107\n28 017c24b2.wav ... 0.011569\n29 01a992c5.wav ... 0.004163\n... ... ... ...\n1090 406306b6.wav ... 0.006316\n1091 406a1cc1.wav ... 0.073884\n1092 406ade5e.wav ... 0.000271\n1093 4093913f.wav ... 0.005274\n1094 40957335.wav ... 0.002213\n1095 4098028d.wav ... 0.005985\n1096 40afd1b3.wav ... 0.000464\n1097 40c1ed87.wav ... 0.003541\n1098 40c50046.wav ... 0.004456\n1099 40d0726d.wav ... 0.002886\n1100 40dd1274.wav ... 0.011626\n1101 40e25750.wav ... 0.001371\n1102 410837eb.wav ... 0.036582\n1103 410c2138.wav ... 0.000834\n1104 411993fd.wav ... 0.000339\n1105 413b5427.wav ... 0.000007\n1106 41522a65.wav ... 0.000632\n1107 415f4c8f.wav ... 0.000013\n1108 41759973.wav ... 0.002662\n1109 419271cc.wav ... 0.000098\n1110 4195cb1a.wav ... 0.000011\n1111 41af688a.wav ... 0.083611\n1112 41c60bba.wav ... 0.019773\n1113 41cfee6d.wav ... 0.000020\n1114 41f16193.wav ... 0.032800\n1115 41f1ea4a.wav ... 0.001630\n1116 41f86bc4.wav ... 0.168439\n1117 4215309a.wav ... 0.002794\n1118 4248d196.wav ... 0.000186\n1119 42542036.wav ... 0.002288\n\n[1120 rows x 81 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
fnameAccelerating_and_revving_and_vroomAccordionAcoustic_guitarApplauseBarkBass_drumBass_guitarBathtub_(filling_or_washing)Bicycle_bellBurping_and_eructationBusBuzzCar_passing_byCheeringChewing_and_masticationChild_speech_and_kid_speakingChink_and_clinkChirp_and_tweetChurch_bellClappingComputer_keyboardCrackleCricketCrowdCupboard_open_or_closeCutlery_and_silverwareDishes_and_pots_and_pansDrawer_open_or_closeDripElectric_guitarFartFemale_singingFemale_speech_and_woman_speakingFill_(with_liquid)Finger_snappingFrying_(food)GaspGlockenspielGong...HarmonicaHi-hatHissKeys_janglingKnockMale_singingMale_speech_and_man_speakingMarimba_and_xylophoneMechanical_fanMeowMicrowave_ovenMotorcyclePrinterPurrRace_car_and_auto_racingRaindropRunScissorsScreamingShatterSighSink_(filling_or_washing)SkateboardSlamSneezeSqueakStreamStrumTapTick-tockToilet_flushTraffic_noise_and_roadway_noiseTrickle_and_dribbleWalk_and_footstepsWater_tap_and_faucetWaves_and_surfWhisperingWritingYellZipper_(clothing)
0000ccb97.wav0.0000012.147708e-081.852816e-061.297532e-050.0000061.029323e-032.897937e-071.338427e-040.0005127.906952e-060.0000020.0000584.497093e-079.045117e-060.0006020.0000040.0000140.0001210.0000101.232514e-032.764862e-045.680398e-046.035296e-041.002422e-050.0000471.010301e-020.0000540.0000576.691381e-048.644166e-070.0000362.347727e-051.467673e-040.0003692.119138e-020.0007682.738387e-049.521755e-053.315867e-05...4.219771e-040.0021990.0043283.548685e-023.268287e-052.761204e-060.0002808.771332e-068.778597e-070.0000240.0000700.0000020.0000882.349939e-056.592538e-078.440182e-040.0000539.076741e-010.0000450.0027071.140796e-050.0000092.390979e-050.0001700.0000410.0001431.863766e-051.445242e-064.902631e-044.153691e-050.0000290.0000120.0000030.0000290.0000801.908621e-060.0013512.679750e-030.0000370.001443
10012633b.wav0.0275364.540822e-042.035434e-032.414528e-040.0015933.905578e-042.866259e-032.815288e-020.0014891.247614e-030.0040720.1038991.408539e-031.200923e-040.0141170.0027300.0008510.0028270.0035098.127709e-054.518407e-041.829191e-035.949721e-038.741478e-040.0117471.616124e-030.0010920.0057751.722676e-041.958537e-030.0017381.481196e-031.560568e-030.0044112.225357e-050.1646246.848917e-049.069323e-051.874801e-04...2.516134e-030.0036500.1269235.597499e-041.338659e-042.108870e-030.0005592.100318e-045.538489e-030.0026280.0072600.0389990.0078093.619624e-025.939879e-043.520224e-050.0109075.093160e-040.0002510.0015084.155050e-020.0511543.685285e-050.0032580.0063450.0140223.114076e-031.617758e-034.785019e-053.110165e-030.0193540.0165360.0057830.0294050.0342223.892229e-020.0031371.327106e-020.0005470.014082
2001ed5f1.wav0.0003524.395279e-057.526755e-041.641128e-040.0008152.701451e-031.671568e-046.189311e-040.0012733.027332e-030.0000360.0027716.568373e-051.879679e-040.0078880.0006120.0020480.0012870.0014576.077341e-038.215838e-032.206624e-031.590203e-041.464545e-040.0078503.208557e-030.0011890.0152411.643555e-021.751458e-040.0008543.193971e-058.025806e-040.0006053.787647e-030.0004379.021877e-036.199606e-041.500817e-02...5.183880e-040.0004170.0015704.869492e-031.157281e-017.780032e-050.0101266.831183e-031.171480e-040.0254920.0321180.0001370.0010841.170986e-023.149346e-051.047635e-020.3537911.344571e-020.0048550.0062173.866610e-030.0012121.323462e-030.0457830.0530150.0238133.840879e-058.361518e-044.103336e-039.520108e-020.0012470.0001050.0001710.0306490.0011921.939494e-040.0002115.688083e-030.0020880.011119
300294be0.wav0.0000716.114840e-081.538012e-046.588295e-060.0006031.616218e-061.728436e-072.117982e-020.0000137.256118e-050.0000150.0397151.354943e-051.747087e-060.0062620.0000110.0001420.0028900.0000951.509136e-061.435445e-032.656461e-043.464552e-035.673289e-060.0000408.168146e-050.0001110.0004674.841320e-048.526970e-070.0000207.432284e-051.238275e-040.0010345.254296e-060.0007654.799234e-046.657184e-067.619913e-06...3.131136e-060.0000320.0056071.479541e-044.487369e-053.952979e-060.0000651.195573e-065.069101e-040.0016050.0000650.0007360.0026008.393927e-011.391830e-052.511220e-040.0000964.390248e-040.0000010.0000127.241964e-040.0094081.199260e-040.0000800.0000910.0008036.529688e-049.208063e-054.667569e-041.109213e-040.0201240.0000330.0013550.0008850.0104945.289278e-040.0013654.549758e-030.0000130.009517
4003fde7a.wav0.0000574.606808e-068.080957e-053.536260e-040.0000761.353680e-046.249314e-068.363231e-060.3805264.818141e-050.0014370.0000391.954283e-042.016910e-040.0000170.0000380.0742230.0011950.0002847.538457e-052.251263e-045.335568e-051.109602e-041.570086e-040.0009431.600815e-010.0645350.0001092.618389e-042.511403e-050.0000031.836072e-043.709388e-050.0005758.712757e-050.0009532.716510e-042.229966e-013.242180e-03...3.210657e-030.0000230.0004275.467216e-038.005240e-041.949348e-050.0000142.245934e-024.216856e-040.0004480.0089780.0007790.0000062.978568e-048.339832e-065.788993e-040.0000226.210698e-050.0004560.0060996.281915e-050.0004782.265796e-060.0222540.0000070.0085242.782175e-054.884402e-059.318779e-042.084454e-030.0000250.0001690.0002060.0001280.0001823.782199e-060.0001049.369272e-050.0000400.000016
50040ccc9.wav0.0005563.041458e-021.932438e-042.235261e-040.0002391.036470e-012.222872e-021.699268e-050.0000211.831755e-040.0000620.0002261.521068e-053.988605e-040.0000090.0042880.0001770.0000110.0000255.146225e-031.162609e-042.069164e-034.274890e-051.887775e-040.4713551.090678e-040.0004540.0039367.042997e-057.448813e-020.0983101.901209e-048.742103e-040.0000155.642817e-040.0000181.526077e-041.220786e-064.773493e-03...4.116311e-050.0015110.0000737.081772e-064.757624e-024.403128e-050.0240052.074340e-035.765594e-050.0010360.0060450.0003970.0001991.742207e-031.705496e-045.245533e-050.0002821.074289e-050.0001130.0000503.586254e-040.0000514.476319e-050.0171810.0005730.0525021.387473e-053.587873e-049.228754e-032.962126e-040.0000610.0001460.0000050.0047060.0000145.000351e-050.0004955.174444e-060.0005240.001096
60046b732.wav0.0077973.837354e-033.656549e-041.381223e-030.0197654.497544e-048.764734e-059.321010e-040.0013232.667928e-020.0015510.0067961.984230e-042.622164e-030.0197930.0061070.0008920.0015960.0016203.285127e-032.247964e-041.109791e-041.994364e-032.119187e-030.0065391.314592e-030.0002210.0074017.490981e-042.109993e-030.0152395.625503e-042.637256e-020.0031345.537259e-040.0001603.003232e-023.566091e-056.480181e-04...1.370562e-030.0002890.0287755.797870e-045.650554e-027.664901e-040.0840662.372639e-047.397623e-050.0727960.0073110.0010990.0011442.488853e-037.864743e-043.956124e-040.0019924.892855e-030.0618380.0009392.183298e-020.0003261.963108e-040.0315330.1609910.0290491.352524e-042.306524e-044.181696e-041.820519e-020.0044410.0015610.0004230.0101290.0006476.094626e-040.0186681.056733e-020.0704880.081312
7004f3bbc.wav0.0030551.963438e-062.230096e-028.196454e-050.0002591.038530e-016.380854e-016.022306e-040.0001601.982279e-040.0000210.0099023.340797e-045.051746e-050.0005030.0000200.0005030.0001310.0003686.718806e-041.850328e-031.013554e-021.404057e-033.899306e-050.0030432.324516e-040.0000530.0015063.616079e-023.636769e-030.0002943.252876e-056.957240e-050.0002532.317043e-040.0001451.405527e-042.957018e-042.145926e-02...6.730323e-060.0037540.0009191.508827e-032.489449e-022.857384e-050.0025451.021811e-025.034636e-040.0033740.0003790.0012920.0000327.769438e-031.586312e-043.142054e-020.0000915.812748e-030.0006920.0017681.649887e-040.0005571.251952e-050.0046030.0037600.0011622.030911e-051.808755e-029.973269e-042.002592e-030.0004510.0000630.0004700.0009460.0006769.330489e-050.0000841.237567e-030.0001360.005014
800526050.wav0.0000225.383440e-078.127618e-052.010926e-050.0000298.261414e-014.521882e-045.344139e-050.0007081.344397e-040.0000300.0001501.620888e-066.639316e-060.0001830.0000010.0007890.0003330.0000291.000339e-023.253077e-031.604624e-043.124810e-046.587979e-060.0052631.065649e-030.0003750.0003351.606210e-037.505972e-040.0002204.141227e-064.084535e-050.0000399.125480e-040.0000306.107909e-061.213364e-044.519504e-04...1.493842e-050.0003820.0000733.954277e-052.572087e-032.155210e-070.0000724.712017e-021.138814e-040.0001000.0025140.0000890.0006801.150105e-041.004751e-064.324757e-030.0001501.335147e-030.0000220.0010572.944841e-060.0000711.236892e-050.0083520.0000040.0007288.967961e-065.161498e-056.923421e-024.374991e-030.0000210.0000030.0000710.0010680.0001559.459470e-060.0002414.438092e-040.0000240.000150
900559da4.wav0.0000781.273427e-063.368900e-053.292713e-040.0011406.570463e-051.033901e-062.197639e-030.0000399.941246e-060.0003690.0012063.457774e-051.968561e-040.0460610.0004010.0002640.0032160.0006841.910503e-046.864408e-037.039552e-042.243124e-041.301521e-030.0017046.178374e-040.0004290.0115598.201384e-054.532142e-060.0001352.989829e-063.197308e-040.0001474.493026e-050.0010701.194962e-056.489340e-072.068362e-05...8.237130e-050.0000420.0003856.815403e-043.481853e-031.176509e-050.0009191.087711e-061.479995e-040.0005400.0008600.0001350.0126921.038008e-035.069295e-051.556025e-050.4771253.618979e-020.0000180.0003103.914938e-040.0004742.716893e-040.0061560.0024500.0130746.235140e-047.915946e-063.936348e-032.005509e-020.0005950.0003400.0001060.0943990.0002224.790354e-030.0010756.710216e-020.0001510.167180
1000582bbe.wav0.0004821.056167e-045.961698e-033.065007e-040.0403876.939038e-023.641768e-042.216691e-030.0002411.982682e-030.0006890.0107851.851436e-042.246512e-040.0033530.0000820.0122940.0020280.0034003.505297e-031.102783e-024.471947e-022.709481e-043.116704e-040.0645891.379973e-030.0037450.0120258.471852e-038.094845e-040.0061371.288646e-043.052698e-040.0017478.126380e-040.0005292.814336e-049.448229e-045.821374e-04...2.358872e-050.0023400.0016117.491393e-043.163603e-012.052900e-040.0031351.329385e-031.827858e-040.0211040.0023570.0023820.0031311.090210e-022.364460e-043.046255e-030.0193493.040267e-030.0000990.0011361.032484e-030.0051254.610212e-030.0151780.0017950.0112141.268789e-043.410969e-031.743392e-011.027200e-020.0078540.0003360.0014530.0243430.0028748.114224e-040.0024895.048235e-030.0000880.014790
110064aedf.wav0.0389663.605338e-045.666946e-031.737663e-030.0101226.085525e-041.743758e-046.838922e-030.0003671.128729e-020.0009900.0479013.196440e-032.788201e-030.0315760.0071510.0017190.0030000.0227904.942740e-041.222904e-021.081384e-022.898110e-035.911874e-030.0472963.369508e-030.0029860.1350128.968627e-041.529915e-030.0023691.423229e-036.155165e-040.0041095.399369e-050.0085252.640098e-041.152919e-058.656764e-03...2.994512e-040.0012880.0068382.044570e-035.289563e-037.179504e-040.0015751.145189e-045.267644e-030.0130750.0293360.0149120.0198279.844488e-032.225140e-027.974861e-050.0217295.542960e-030.0002980.0029559.687756e-040.0205039.589938e-030.0223680.0045430.0258585.978964e-036.311989e-038.777881e-031.301174e-020.0061530.0052260.0041070.0771560.0170322.014487e-020.0028428.056344e-030.0004790.129515
120065512b.wav0.0200131.767897e-063.591313e-042.416338e-030.0016941.359574e-041.845747e-061.100777e-020.0016543.078244e-030.0012560.0047101.520271e-033.309540e-030.0434370.0001510.0008890.0027200.0009514.374237e-031.623673e-023.863694e-025.535033e-043.113708e-030.0022572.050536e-030.0009800.0205273.977080e-034.262987e-060.0054623.237765e-056.707647e-050.0126352.100971e-030.0096476.241534e-041.056892e-041.721712e-04...1.756189e-050.0000410.0053043.942256e-024.191418e-038.844699e-050.0033701.584303e-051.799405e-020.0062820.0020130.0266130.0077593.013959e-021.148415e-031.548722e-030.0726772.527745e-020.0001920.0030814.923345e-040.0095292.462622e-030.0024700.0065650.0126741.418675e-011.492923e-043.658156e-038.815849e-040.0077030.0134910.0020580.0592290.0096899.794185e-020.0008432.312399e-020.0000700.130989
13006a91d2.wav0.0072102.860906e-061.169479e-053.580333e-040.0007003.610891e-052.826709e-071.716265e-030.0002555.743199e-050.0022800.0068634.144645e-023.285889e-040.0008140.0000250.0001550.0053360.0011564.046391e-047.330840e-041.713308e-034.928485e-046.066350e-040.0002832.907798e-040.0008560.0031159.356335e-052.940244e-070.0000749.798096e-074.775198e-060.0001482.313572e-050.0013289.005017e-062.137305e-061.970754e-05...9.077794e-070.0000130.0013092.257193e-044.801213e-041.199208e-050.0000052.066524e-076.000829e-030.0006580.0005910.0089070.0020555.779234e-044.273555e-041.056825e-050.0243502.153658e-040.0000050.0002441.193145e-040.0003124.365013e-020.0014070.0000650.0030243.587490e-012.824579e-061.843905e-041.022856e-030.0042920.0408290.0003000.0309360.0003823.805746e-010.0000713.268890e-040.0000020.008649
14006ea9ee.wav0.0045283.825845e-046.438290e-022.268223e-040.0082599.774446e-052.623444e-031.556822e-040.0002942.774848e-040.0001900.0036629.149844e-041.633090e-040.0000460.0001160.0158250.0007790.2572353.070738e-042.725562e-041.532546e-041.518870e-046.200272e-040.0000682.175231e-040.0004950.0001849.897611e-051.386048e-020.0000781.566102e-022.943190e-040.0000535.705662e-040.0000253.161273e-046.480012e-045.235195e-01...6.203501e-040.0001990.0003312.816124e-061.973996e-031.983596e-030.0001435.525908e-035.047170e-050.0032800.0017600.0010430.0012271.147738e-036.711950e-034.104393e-050.0000362.148633e-040.0004840.0001797.315422e-050.0008496.519788e-050.0003810.0001580.0003748.363380e-064.850860e-026.305491e-043.863234e-040.0002890.0009180.0000830.0001360.0004007.381386e-050.0002622.270235e-050.0002230.001273
15006f9dca.wav0.0005932.539030e-065.677006e-034.397213e-040.0064003.975722e-042.220020e-059.611730e-020.0001345.392048e-030.0000180.0045645.180656e-042.901544e-040.0234560.0000690.0005490.0006870.0017386.994989e-042.724028e-033.972116e-031.775267e-045.147960e-040.0009791.314104e-030.0010240.0089112.637385e-034.241458e-050.0004991.981423e-054.101150e-040.0201607.454725e-040.1099891.268853e-033.416869e-051.164801e-03...1.951479e-050.0002940.0044291.034800e-033.155728e-021.058648e-040.0027774.334821e-052.344802e-050.0034410.0025460.0008520.0020511.416853e-033.688761e-041.868506e-030.0024002.760205e-020.0001820.0012995.646746e-040.1858531.384695e-030.0041190.0104420.0024577.550152e-042.869084e-037.040718e-032.963507e-030.0277320.0001570.0951760.0078640.1596036.823923e-040.0016864.648888e-030.0003240.066992
16007450dc.wav0.0001062.398684e-051.593884e-071.698138e-050.0000094.958832e-071.790763e-051.068204e-030.0000194.627041e-020.0013250.0000341.644321e-054.716260e-050.0003270.0013130.0055610.0002180.0005142.312158e-037.049907e-063.909021e-065.162763e-051.771980e-040.1659914.382609e-030.0027970.0000725.543395e-041.990513e-040.0000171.344393e-031.300832e-030.0209231.609030e-080.0000891.144039e-034.497157e-051.720120e-05...1.799454e-030.0004940.0176342.187199e-053.247659e-064.235647e-030.0011102.952649e-061.017673e-050.0203490.0000560.0001400.0042204.247601e-066.545917e-062.932912e-040.0000204.451461e-050.5378480.0416728.163134e-030.0010631.942914e-050.0026340.0159810.0476957.397753e-058.370138e-083.645822e-051.891903e-030.0001660.0001460.0033130.0006790.0012087.142184e-060.0002703.825772e-040.0273740.000296
1700979c8a.wav0.0029068.480622e-061.743531e-035.198459e-040.0133419.759310e-033.777916e-045.873174e-030.0004561.125516e-020.0003770.0113874.478129e-032.475842e-040.0180400.0003220.0019750.0012890.0015921.104463e-032.985374e-021.197696e-021.692734e-034.075955e-040.0171842.704294e-030.0013570.1174533.273430e-035.048618e-040.0012231.316774e-048.714349e-040.0022141.504257e-030.0008173.446236e-033.282651e-045.017281e-03...2.364965e-050.0007760.0071231.752859e-031.133212e-016.382536e-050.0105933.031148e-046.966203e-040.0361240.0157710.0034490.0007902.447392e-011.124847e-032.892717e-030.0044129.535822e-030.0006040.0025482.262620e-030.0069731.805258e-030.0194410.0205010.0050606.638439e-041.746646e-036.267467e-033.973524e-030.0050880.0012280.0011230.0311700.0055351.689865e-030.0012782.085651e-020.0008960.115068
1800992464.wav0.0000732.640450e-068.204499e-061.268781e-040.0000271.114690e-061.766959e-074.176806e-020.0000395.729701e-020.0001240.0006992.492258e-051.051962e-040.0678380.0004820.0022880.0008560.0000654.348209e-053.871570e-031.274478e-029.701746e-052.752544e-040.0117018.367246e-030.0022820.0052445.591903e-037.964192e-070.0211214.936728e-042.378839e-030.2271601.086492e-050.0050725.799165e-047.348628e-067.704927e-06...3.954615e-040.0001110.0070024.109832e-031.261188e-054.326605e-050.0007881.031709e-052.747075e-050.0017260.0000240.0005950.0015722.117169e-048.420398e-062.206346e-030.0000901.029817e-020.0008390.0222668.379880e-040.1132602.851948e-050.0003260.0009560.0088941.904255e-033.443824e-061.064867e-044.483080e-040.0677860.0000230.0911060.0009540.0942973.173022e-040.0253885.884275e-030.0030210.010349
1900b44a8a.wav0.0000268.701654e-061.886922e-051.652962e-040.0000911.424176e-053.830280e-072.088836e-020.0005894.633845e-040.0003790.0001311.551964e-061.841556e-040.0041000.0007130.0525210.0010240.0000216.142008e-046.246411e-041.413163e-042.856184e-044.239360e-040.0018635.369698e-020.0384320.0058592.533799e-048.818163e-060.0017962.455194e-048.246351e-030.1020042.034792e-040.0048062.199855e-034.372457e-058.929194e-06...1.771174e-030.0027440.0149492.646546e-021.744620e-041.451986e-040.0030502.916599e-053.774146e-050.0002250.0027680.0000290.0115216.841552e-051.559541e-067.124418e-050.0018074.206658e-030.0003130.3612064.700446e-030.0762668.032605e-040.0035400.0035390.0310483.136692e-031.280989e-051.349891e-031.726897e-020.0065560.0000730.0141140.0052140.0500149.636480e-040.0221239.568122e-030.0027940.000816
2000bfaaaf.wav0.0003981.997575e-046.610830e-063.882278e-050.0014617.050147e-075.456923e-071.863199e-040.0016501.260929e-030.0000120.0006975.648869e-066.505573e-050.0003640.0169750.0018910.0001280.0000122.093572e-044.530066e-071.059210e-063.412206e-041.464833e-040.0036622.417955e-030.0004950.0006862.092611e-051.162961e-060.0095901.955705e-032.849908e-020.0011431.378790e-060.0000892.245123e-021.515894e-065.642931e-07...2.864170e-030.0000880.2979324.084141e-044.587690e-064.209082e-030.0020513.543620e-066.702458e-070.0073660.0000240.0000850.0001052.802966e-052.804580e-066.948975e-060.0000014.499170e-040.0442160.0005732.396196e-010.0002611.683132e-060.0007160.1796420.0145104.364550e-061.958058e-052.038006e-061.125642e-030.0001480.0001120.0000570.0000450.0000729.228779e-060.0638034.842126e-040.0307850.011089
2100cf9680.wav0.0007181.723427e-046.788758e-042.611945e-030.0031943.399390e-032.503396e-052.058431e-030.0521613.393443e-030.0002230.0028008.055364e-033.926808e-030.0035940.0010130.0040900.0443040.0172321.125452e-023.004418e-034.860323e-031.625287e-034.123440e-030.0054243.336578e-020.0045650.0113592.130176e-034.139492e-040.0023041.365802e-046.194325e-040.0016163.503712e-020.0022921.428283e-023.769328e-033.636618e-02...1.304207e-030.0042240.0058196.149550e-032.666968e-018.965100e-050.0025021.988263e-021.121431e-030.1044680.0091530.0013470.0004565.183658e-037.308327e-041.384202e-030.0019573.415166e-020.0061890.0368268.939384e-030.0010431.319328e-040.0349920.0180720.0118831.244024e-037.526095e-047.657467e-032.885603e-020.0057970.0047920.0006370.0067400.0009564.954673e-030.0028302.654279e-030.0025110.012323
2200eae94d.wav0.0001039.675218e-083.122633e-069.896953e-040.0000269.821875e-069.219018e-084.639101e-010.0000911.362531e-040.0000320.0009502.330824e-054.390907e-040.0566560.0000580.0009400.0034710.0000114.726646e-043.663893e-036.456668e-027.245197e-044.389049e-040.0004461.919389e-020.0015520.0016605.448618e-033.326928e-070.0001251.395530e-061.248753e-040.0305469.135806e-040.0407594.172624e-051.511628e-056.789913e-06...4.240162e-040.0056980.0123393.998606e-037.384498e-059.584022e-070.0000571.804259e-063.404168e-060.0010940.0000380.0000600.0015604.684445e-053.999178e-061.734344e-030.0043498.074766e-020.0000910.0079841.207771e-040.0400998.632131e-050.0003710.0011640.0099002.628478e-039.559765e-073.863350e-043.335691e-030.0214260.0001340.0132150.0057040.0577664.223207e-040.0020591.361185e-020.0001270.004880
23011ec5b8.wav0.0032131.348595e-042.247253e-041.271829e-030.0067882.278279e-043.968701e-052.025258e-020.0022901.704932e-030.0015600.0027811.066693e-021.036506e-030.0454640.0006190.0032550.0240320.0010559.178968e-031.475059e-022.952990e-042.538336e-042.243755e-030.0056257.559831e-040.0022310.0716826.311943e-042.663446e-030.0038118.607485e-043.459852e-030.0008472.262243e-030.0008623.888576e-026.879042e-052.752103e-03...5.120136e-050.0001970.0079475.284324e-051.628276e-023.050782e-040.0233651.309725e-041.562058e-040.0064210.0375230.0020250.0019481.552192e-018.916922e-045.037765e-040.0051911.107135e-030.0038250.0013322.525240e-020.0082822.654444e-030.0143550.1362980.0274872.381018e-031.347192e-046.861434e-043.014199e-030.1193560.0034910.0006890.0400550.0021877.333332e-030.0117331.983829e-030.0019630.034261
24013200dc.wav0.0002502.088507e-056.739201e-045.991580e-040.0000524.335940e-044.272343e-051.051729e-020.0013559.356036e-030.0000210.0013652.034910e-046.880729e-040.1125530.0002990.0218190.0052350.0013563.057953e-046.845252e-028.151513e-021.850313e-044.335855e-040.0064061.015915e-020.0027810.0076885.838141e-038.479437e-050.1704011.286949e-054.134887e-040.0043741.602610e-030.0150033.692406e-045.711121e-051.527901e-03...9.821572e-050.0011540.0160231.527825e-026.514626e-044.177848e-050.0026913.129017e-051.880871e-040.0077660.0016600.0003980.0042448.410384e-031.226142e-043.495944e-030.0029541.028472e-010.0004630.0121491.198153e-040.0348537.013240e-050.0198890.0040050.0462354.342168e-043.241127e-041.506693e-026.968725e-020.0089290.0001260.0093820.0073930.0294254.179649e-040.0029221.239168e-020.0002780.007325
2501440c2e.wav0.0069306.522481e-011.985251e-042.472027e-040.0000521.232701e-053.779127e-044.662334e-050.0000186.363632e-050.0003110.0002315.349101e-051.307250e-040.0000110.0001550.0027810.0011690.0070749.446263e-053.010844e-062.720318e-064.487973e-071.323060e-030.0059131.514017e-040.0008600.0000591.359066e-062.496326e-020.0024463.646287e-039.573508e-040.0000272.869232e-090.0000253.844033e-051.785014e-052.968184e-04...1.085460e-010.0000480.0000805.523477e-071.380417e-051.511485e-030.0002231.121055e-029.313827e-050.0015090.0001770.0215900.0021224.051232e-057.189090e-032.966696e-060.0000366.713353e-060.0006610.0000393.782504e-050.0001311.267808e-060.0006190.0002660.0306321.972631e-044.243494e-041.253567e-051.068351e-030.0000840.0956640.0005240.0001870.0000161.293200e-040.0000958.343994e-070.0007960.000914
2601567a3d.wav0.0002996.704017e-055.200171e-049.730181e-040.0067803.936673e-023.226307e-052.215870e-040.0000959.195515e-040.0006420.0001084.678583e-068.452446e-040.0089670.0002280.0056640.0001030.0002412.681353e-029.015919e-032.981909e-041.011061e-055.779957e-040.0570251.016420e-020.0119710.0946432.778026e-046.982398e-040.0064231.439342e-051.517616e-030.0001291.586039e-030.0001024.418754e-054.460102e-069.057715e-05...3.196857e-040.0018950.0001387.608013e-051.202967e-016.707954e-060.0018691.292234e-032.703229e-050.0001130.1704780.0001880.0319902.516133e-045.908321e-051.826286e-040.0245468.942260e-030.0000310.0014322.481636e-050.0004121.957336e-020.0693950.0017280.0215852.546980e-051.913711e-041.109121e-013.954886e-020.0002340.0001310.0000380.0610950.0002728.615900e-050.0030327.531790e-030.0005750.011832
270163d203.wav0.0038132.673478e-052.481829e-043.382786e-040.0144312.584033e-046.782766e-055.788927e-030.0009716.175659e-040.0072570.0384227.880112e-032.254448e-040.0480750.0003830.0008240.0127250.0016193.140975e-041.355654e-021.137533e-021.794377e-027.892981e-040.0181873.751140e-040.0007880.0509621.652070e-033.406451e-050.0011092.677777e-044.057778e-040.0030528.967552e-050.0016511.877292e-043.421477e-052.063498e-04...1.509201e-050.0000400.0075381.197280e-035.508744e-031.333728e-040.0018613.186931e-056.222521e-030.0544260.0069670.0233590.0023793.576717e-019.113777e-049.852406e-040.0063961.601144e-030.0000900.0007111.864873e-030.0044958.159327e-030.0284340.0010530.0336034.157200e-031.810095e-043.702163e-033.507447e-030.0067030.0086280.0023650.0554710.0038611.766926e-020.0017881.662308e-020.0001330.051107
28017c24b2.wav0.0076819.632573e-059.083861e-064.171254e-030.0183104.509846e-041.700752e-058.352475e-030.0017023.086167e-040.0004270.0024641.769489e-023.927880e-030.0102350.0009160.0031920.0260370.0084182.503273e-029.555037e-032.466227e-034.704422e-045.337477e-030.0016475.811371e-040.0023720.0074416.357258e-041.749614e-020.0073662.983071e-041.162169e-030.0009406.118167e-030.0001181.396341e-021.015747e-047.406075e-02...2.009657e-030.0013400.0126912.435386e-053.583288e-031.267536e-030.0085795.240718e-041.063764e-040.3860120.0043990.0041480.0006981.607521e-023.139772e-032.692204e-040.0006462.515065e-030.0131310.0021058.304629e-030.0009763.461696e-030.0059590.0310810.0411301.974589e-037.295771e-066.753111e-042.859553e-030.0712130.0081500.0001440.0064810.0008866.199250e-030.0095353.001680e-040.0341700.011569
2901a992c5.wav0.0003891.642764e-022.518148e-041.305930e-050.0014221.956043e-053.405473e-061.929782e-030.0005731.467218e-030.0008240.0295771.170477e-041.322933e-050.0019960.0009320.0000920.0153720.0004751.783469e-045.042541e-056.900018e-046.949733e-012.919213e-050.0794393.649015e-040.0003240.0000261.183185e-063.401562e-060.0053102.464603e-022.272277e-030.0000303.011822e-050.0013311.625415e-034.906673e-066.511431e-05...5.595851e-060.0000690.0228423.589388e-052.053801e-047.509998e-030.0001259.212385e-065.909590e-040.0100820.0007350.0018570.0039141.731489e-021.049801e-048.550325e-070.0011982.009351e-040.0021310.0000996.589924e-030.0002861.099350e-040.0006220.0000250.0047953.674612e-032.457519e-051.314257e-051.162214e-030.0007670.0002880.0003630.0051860.0002512.170430e-030.0066097.708509e-030.0026550.004163
......................................................................................................................................................................................................................................................
1090406306b6.wav0.0013581.339471e-051.330948e-026.453206e-040.1247101.178027e-031.205372e-039.809025e-040.0021307.078374e-030.0007320.0045441.440159e-035.243126e-040.0006400.0000940.0164400.0039170.0748632.588911e-035.235214e-041.917463e-041.654854e-041.249352e-030.0010852.150085e-030.0022580.0054203.100607e-045.824064e-030.0000457.186098e-032.209408e-030.0000791.883421e-030.0002283.979865e-032.285936e-034.726631e-01...2.406498e-040.0012110.0022756.656096e-052.806340e-021.416382e-040.0010545.087670e-032.416368e-050.0476220.0185070.0002830.0001934.440038e-036.037106e-042.097501e-040.0001214.189667e-030.0227400.0016222.749475e-030.0008531.595813e-030.0017570.0058570.0023953.157907e-051.187317e-022.599356e-033.097903e-030.0234090.0005260.0000460.0012190.0022187.214498e-050.0002451.592499e-030.0244680.006316
1091406a1cc1.wav0.0037928.161184e-041.209869e-021.041733e-020.0355932.259112e-058.461112e-067.119580e-030.0081861.758207e-030.0008360.0719791.090684e-022.968115e-020.0056790.0014400.0471820.0769480.1124593.199540e-021.078379e-032.378915e-032.528018e-034.632432e-020.0048918.176018e-030.0140060.0088274.496339e-033.236573e-040.0005591.364197e-034.030872e-030.0044134.205608e-040.0005297.663323e-036.909758e-041.628274e-03...1.257083e-030.0001190.0054921.172274e-036.448912e-031.874306e-030.0030861.925431e-041.952352e-030.0364780.0112170.0100610.0257111.032090e-025.093493e-032.354586e-030.0027371.349840e-020.0108900.0039874.467991e-030.0160647.604560e-030.0106420.0149560.0177335.317740e-039.142940e-031.644791e-031.500183e-020.0154050.0142130.0073320.0047670.0184105.909509e-030.0137811.716238e-030.0042100.073884
1092406ade5e.wav0.0038072.275581e-065.618879e-067.588771e-040.0000206.614577e-051.534407e-051.724205e-010.0000221.952296e-030.0000580.0031871.071626e-042.173592e-040.0047020.0000200.0003090.0018250.0000231.130584e-041.010231e-031.183677e-024.066640e-042.239416e-040.0308092.593889e-030.0042590.0095958.965198e-031.152703e-050.0013203.233145e-054.815485e-050.0701313.573333e-060.0163391.777467e-054.434455e-051.364760e-05...9.427009e-050.0007390.0009245.769090e-043.907329e-053.827359e-060.0000642.070381e-042.979807e-040.0006160.0001550.0057260.0013382.548695e-044.188371e-051.720295e-030.0004615.070514e-040.0000820.0182343.454182e-040.1200112.531659e-060.0010420.0001730.0171673.091512e-034.770046e-061.785774e-041.472159e-030.1237200.0001670.1005720.0053890.1107698.162544e-040.0006721.213639e-020.0000620.000271
10934093913f.wav0.0005949.446932e-051.914342e-035.957531e-020.0008185.237868e-044.051733e-052.358476e-020.0075907.624881e-040.0256190.0077727.104749e-023.002553e-020.0040690.0005830.0002290.0187330.0042591.253261e-023.497524e-039.586035e-046.224697e-038.923371e-020.0557534.887221e-040.0006500.0012183.935219e-037.200056e-050.0007467.623161e-034.489660e-050.0088425.452025e-050.0683923.073623e-021.735677e-051.134336e-04...1.599468e-040.0015010.0194851.213952e-045.569673e-055.136238e-040.0003961.814398e-053.711549e-030.0030790.0015440.0032410.0022881.094908e-032.151574e-048.446970e-040.0332863.794927e-040.0161950.0189866.034311e-020.0377361.930993e-050.0122480.0012990.0295402.435823e-025.759186e-052.095061e-051.165167e-020.0399350.0087060.0080720.0091320.0348132.120437e-020.0007097.035477e-030.0004840.005274
109440957335.wav0.0179418.304720e-031.153260e-024.024923e-030.0218611.952651e-048.974387e-041.846524e-040.0009892.451094e-030.0061530.0089702.095129e-033.057883e-030.0016820.0038790.0058060.0076790.0805286.511211e-031.186122e-041.193692e-052.280998e-052.221723e-020.0017135.182006e-030.0066900.0087131.845041e-043.643458e-030.0291197.446731e-031.902657e-020.0011212.079043e-050.0003714.834875e-026.541696e-052.110254e-02...6.407411e-030.0001820.0016237.885708e-059.665495e-031.978350e-020.0032981.594455e-032.348273e-040.2326580.0136250.0082120.0013603.039708e-031.586046e-027.461772e-050.0005101.460028e-040.0194400.0009642.101725e-020.0011116.741912e-050.0379300.0182540.0761021.296719e-041.879423e-022.058177e-041.693785e-020.0073420.0394020.0009480.0068300.0003951.584509e-030.0100873.373959e-040.0265860.002213
10954098028d.wav0.0035983.185635e-053.981918e-043.107648e-040.0040545.400307e-052.106090e-056.463985e-030.0013141.449217e-040.0007120.0010892.741010e-023.426939e-040.0380470.0000100.0004120.0086530.0051862.296922e-046.712305e-011.463572e-022.631211e-039.665078e-040.0008953.846172e-040.0009340.0055071.002610e-034.719883e-050.0013331.811141e-046.186954e-050.0038803.984109e-040.0004747.148242e-043.256698e-053.173083e-03...6.630866e-050.0001150.0004711.209865e-031.522050e-035.794207e-040.0003261.336541e-052.935383e-030.0140090.0006500.0162110.0021192.373366e-027.196766e-043.599080e-040.0045806.165848e-040.0000400.0008051.955368e-040.0065521.648077e-030.0051500.0000800.0090713.340945e-031.266055e-041.606543e-033.040941e-030.0036850.0278370.0020260.0107210.0020252.672397e-020.0008108.259667e-030.0000040.005985
109640afd1b3.wav0.0026865.462238e-043.705348e-052.859948e-030.0044701.154418e-032.579192e-042.347627e-020.0028653.984516e-030.0233650.0066591.071245e-031.889839e-030.0533780.0029870.0036940.0152370.0149133.631756e-032.979857e-043.938843e-057.498828e-038.700946e-030.0105372.651773e-040.0012370.0025682.307211e-028.010295e-050.0001231.384972e-039.418157e-030.0224363.007902e-040.0074844.021228e-034.224707e-046.269632e-04...3.547191e-030.0037540.0045484.850572e-049.788896e-041.699449e-020.0040071.281608e-022.754716e-030.0237280.0011490.0028260.0180851.860154e-024.838162e-041.916946e-020.0005547.524236e-040.0106650.0064766.162149e-020.0482241.483839e-060.0311630.0246020.0239602.045212e-041.582021e-057.796160e-053.680906e-020.0878630.0105330.0069940.0165120.0655945.113484e-040.0222236.395493e-020.0118170.000464
109740c1ed87.wav0.0000773.674894e-061.021016e-055.729217e-040.0002743.990861e-046.676230e-065.328025e-030.0110772.307035e-020.0001010.0005126.506864e-043.222765e-030.0189800.0000570.0161710.0370770.0067501.250457e-033.905072e-028.042139e-031.893910e-021.293043e-030.0010434.374015e-020.0108990.0005938.190428e-023.488762e-050.0005585.792319e-051.514248e-040.1097122.759835e-030.0047546.628123e-037.727919e-044.510400e-04...6.666062e-050.0025410.0214565.051594e-021.002820e-031.993778e-050.0003343.107996e-045.048645e-030.0300410.0005520.0009020.0464851.217772e-025.537765e-069.427550e-020.0003756.474242e-020.0005310.0549192.676870e-040.0314172.803024e-050.0077890.0002610.0067106.245202e-036.092912e-067.654707e-035.796113e-030.0044190.0002030.0159850.0010520.0491995.963354e-050.0053577.229452e-030.0000860.003541
109840c50046.wav0.0000452.006105e-054.709108e-043.317298e-030.0000771.706885e-047.771476e-062.677230e-030.0038852.153724e-030.0031400.0026781.552008e-052.768118e-030.0702110.0000630.0102550.0004640.0002021.014825e-041.252053e-014.115667e-046.561088e-045.683214e-030.0037964.806656e-030.0032220.0282821.004778e-033.034620e-050.0000465.994610e-049.809099e-030.0071132.630171e-050.0011174.150368e-053.357219e-057.840772e-07...2.902469e-050.0000670.0003386.619026e-038.323326e-041.793557e-040.0031751.137042e-049.970883e-040.0000230.0130490.0014650.2213461.103859e-032.444800e-055.023203e-040.0146321.473644e-010.0000240.0040933.629642e-050.0366872.232953e-040.0747200.0002200.0218802.403581e-048.595752e-058.402987e-038.777794e-030.0029760.0000710.0081980.0055660.0336011.795875e-040.0006204.282073e-020.0036370.004456
109940d0726d.wav0.0929523.715526e-046.392650e-051.090399e-030.0001293.653014e-041.129535e-044.901245e-040.0008302.683250e-050.0598850.0024412.509669e-011.339935e-030.0005920.0005400.0000700.0059360.0036747.857169e-045.904834e-042.909939e-042.077346e-046.535399e-030.0083164.301094e-040.0002330.0090673.350941e-051.904498e-040.0007055.479712e-048.045742e-050.0004423.619752e-050.0017362.326359e-041.895142e-052.001830e-04...2.689400e-050.0000440.0029788.998901e-045.749372e-041.131218e-030.0002836.545421e-061.832014e-020.0002220.0175180.2405560.0009361.524518e-035.451334e-021.067693e-050.0075614.558512e-050.0001540.0006081.998794e-030.0002333.661157e-040.0103240.0002170.0084826.021449e-035.305964e-053.661302e-056.249070e-040.0009630.0954570.0001050.0208180.0003164.919152e-020.0006964.046295e-040.0001010.002886
110040dd1274.wav0.0092394.748647e-038.437111e-044.808073e-020.0282208.919500e-059.058238e-056.313046e-030.0008122.315413e-030.0066750.0028469.740202e-048.544119e-020.0069780.0184700.0030950.0008910.0741752.652820e-024.368320e-042.460234e-057.581809e-051.342192e-010.0013761.534810e-030.0019890.0318652.007825e-042.093918e-030.0002615.637029e-031.880261e-020.0036544.655487e-040.0003913.236918e-038.633027e-051.110884e-03...1.689134e-020.0005390.0022752.628801e-042.177938e-022.249263e-020.0225768.449564e-044.287508e-040.0016770.0129360.0098060.0338722.383635e-048.287102e-035.288613e-050.0080263.348183e-030.0236610.0163616.315159e-030.0135129.228374e-030.0083050.0209770.0117653.329895e-047.372508e-046.058937e-043.372788e-020.0453640.0057860.0011520.0059890.0106481.050256e-030.0076841.416972e-030.0620280.011626
110140e25750.wav0.0052744.298302e-021.620348e-062.827984e-030.0000749.825683e-078.061406e-071.145623e-040.0000139.600987e-020.0149330.0001306.306747e-031.798643e-030.0017890.0461530.0019730.0002620.0014941.033632e-042.606322e-051.414391e-062.819948e-048.291304e-030.0987057.517181e-040.0017440.0005731.283094e-054.276948e-050.0023297.475533e-041.457625e-030.0002634.470245e-080.0003874.758240e-036.571196e-072.112297e-05...3.980534e-040.0005270.0111821.156372e-052.073828e-068.758618e-030.0019712.207584e-063.252337e-040.0661760.0002870.0024530.0017512.426633e-053.845798e-045.739294e-060.0000203.920142e-060.1146090.0005581.073312e-010.0005953.254583e-050.0024620.2363430.0415942.719760e-041.623583e-061.142270e-053.952677e-030.0006540.0100900.0103070.0015590.0004052.703094e-040.0011811.492732e-040.0261730.001371
1102410837eb.wav0.0013701.222419e-038.809319e-034.712881e-030.0060521.599823e-031.232605e-042.054974e-020.0008073.685734e-030.0098910.0086593.959045e-042.082990e-030.0533250.0016500.0132080.0429670.0025422.293061e-034.206712e-034.254929e-034.953196e-034.889734e-030.0048762.312916e-030.0062290.0165362.074321e-031.840104e-040.0845218.877828e-048.956209e-030.0062846.052720e-030.0072194.288373e-034.345748e-032.074442e-03...2.631048e-030.0048650.0267096.898747e-031.694369e-024.980901e-040.0631101.758955e-035.047595e-040.0496220.0205100.0030810.0173222.193726e-025.879565e-041.317101e-030.0096273.878346e-020.0014350.0232744.522735e-030.0138412.771118e-030.0201860.0285860.0252311.829687e-037.467507e-033.877120e-038.706050e-020.0153590.0076340.0010180.0342640.0147591.547130e-030.0035561.052447e-020.0021510.036582
1103410c2138.wav0.0365544.786503e-051.037012e-053.417911e-030.0002955.288288e-056.342929e-051.227755e-010.0000803.878904e-040.0004690.0019207.576471e-051.741389e-030.0020770.0019620.0002650.0037390.0016212.983480e-041.657310e-041.784415e-031.085483e-033.422957e-030.0012307.327714e-040.0015620.0007258.138187e-041.899898e-040.0000122.958824e-041.960814e-040.0464235.400175e-060.0226413.134472e-058.947252e-068.932614e-05...2.284675e-040.0003030.0567638.583015e-046.196440e-051.182746e-020.0000103.152477e-062.128334e-020.0001360.0006810.0255500.1691641.110614e-033.095961e-031.101649e-040.0011741.928998e-030.0000920.0021931.846242e-010.0730975.613839e-030.0004610.0004880.0019226.310666e-031.177986e-063.112887e-055.403964e-040.0568560.0005720.0029630.0023800.0948491.869956e-030.0002543.017847e-030.0000580.000834
1104411993fd.wav0.0000312.926084e-061.344676e-058.120576e-050.0002446.209703e-031.629219e-062.194925e-040.0004821.081776e-040.0000290.0000521.740163e-064.019164e-050.0004260.0000400.0039730.0007100.0001935.564018e-021.823911e-034.748851e-047.815006e-056.320612e-050.0016933.249330e-020.0273060.0020683.698811e-045.585673e-050.0063533.401104e-062.958871e-040.0002292.928751e-030.0008584.379822e-041.437907e-041.007536e-03...2.543775e-040.7697210.0061511.049287e-031.337086e-043.189981e-060.0000164.656033e-054.685261e-060.0001600.0008580.0000270.0021825.226251e-051.371121e-064.637412e-040.0000444.509982e-030.0000390.0366725.179208e-040.0001046.899763e-050.0011560.0003970.0033701.562513e-041.247254e-051.902739e-021.097020e-030.0000670.0000510.0000490.0018910.0002487.479814e-050.0014041.561713e-040.0001710.000339
1105413b5427.wav0.0000193.188784e-013.151345e-054.424937e-050.0000719.866556e-072.080297e-059.158301e-070.0000321.964281e-060.0000840.0000421.243545e-063.155593e-050.0000010.0000660.0005840.0006160.0014971.237862e-041.466759e-061.295643e-076.891768e-064.403197e-050.0000234.864584e-050.0001300.0000183.547045e-072.508371e-040.0000714.443199e-044.088322e-040.0000044.355341e-090.0001848.389462e-053.010725e-068.669753e-06...6.639422e-010.0001270.0001972.495720e-061.229343e-061.571275e-040.0000041.223351e-042.558746e-060.0002820.0000130.0000230.0005394.485603e-067.295036e-063.372301e-060.0000011.207520e-070.0009550.0000133.043604e-050.0000051.512495e-070.0001370.0002080.0062611.118225e-066.841416e-058.863460e-071.038295e-040.0000670.0009810.0000260.0000390.0000019.031228e-070.0000772.415454e-070.0017060.000007
110641522a65.wav0.0000162.501079e-071.078652e-072.398892e-050.0000052.145622e-033.211947e-063.804808e-030.0069351.902506e-050.0001930.0010461.957392e-051.769349e-050.0075030.0000740.0004310.6841900.0001166.521450e-041.168029e-023.409046e-021.816612e-022.918636e-050.0006738.413588e-030.0001760.0008672.364217e-032.622361e-050.0005834.959464e-067.675985e-050.0018393.088128e-030.0764973.643263e-044.312581e-048.399744e-04...4.264514e-060.0048790.0392435.459175e-032.709588e-034.186816e-070.0005403.482011e-042.199378e-030.0007040.0000610.0000210.0000483.428606e-045.973637e-073.894401e-030.0001689.952603e-030.0008020.0170518.448281e-030.0002195.152911e-070.0016940.0069680.0115937.077989e-041.562501e-072.268172e-041.040472e-020.0000690.0000110.0002770.0006580.0001451.771950e-040.0004536.403057e-040.0002830.000632
1107415f4c8f.wav0.0000011.780748e-079.909535e-072.197184e-070.0000023.865274e-086.452060e-097.667792e-060.0724033.073569e-050.0000030.0005543.944366e-089.812268e-080.0000490.0000020.0025840.0009220.0000083.045173e-071.594444e-059.817435e-073.256130e-052.195856e-070.0000251.387900e-010.0273580.0000221.630812e-046.088855e-080.0001158.860749e-085.296671e-050.0023633.264965e-070.0101391.955040e-052.607808e-033.520971e-07...2.648510e-040.0000460.0084683.987710e-012.771203e-061.733927e-060.0000062.418956e-035.685685e-070.0000150.0001330.0000040.0014492.341952e-057.865408e-097.674064e-060.0000191.655284e-040.0000020.2051912.199095e-050.0128521.326342e-080.0003740.0000040.0983031.628653e-077.370650e-078.599387e-051.285756e-030.0000020.0000010.0013010.0000020.0096965.176859e-080.0001764.909527e-040.0000010.000013
110841759973.wav0.0078181.065190e-062.873111e-073.401269e-040.0000082.783990e-068.376820e-081.879269e-040.0000449.341614e-070.0058590.0004225.717043e-041.207982e-040.0000740.0000020.0000460.0023900.0099362.088282e-051.957938e-047.096383e-055.751468e-061.144906e-030.0001081.174247e-040.0002380.0024351.419484e-076.462129e-060.0000247.489325e-051.124458e-050.0001038.132489e-070.8437881.660805e-071.897086e-078.858320e-07...1.504235e-050.0000030.0125442.795071e-051.516990e-052.013755e-050.0000024.522982e-092.284147e-020.0075060.0004590.0007920.0007631.530265e-043.896181e-041.291721e-080.0036551.685965e-030.0000160.0000291.960265e-050.0001951.218657e-050.0000520.0000220.0012413.400579e-023.581162e-081.276404e-058.476489e-060.0070200.0101130.0000040.0055450.0001251.173213e-020.0000011.015728e-040.0000390.002662
1109419271cc.wav0.0005126.142420e-043.075687e-064.247157e-050.0000321.463593e-061.523699e-061.104371e-040.0484229.881980e-040.0007030.0000542.975174e-053.420964e-050.0003650.0388250.0638230.0146840.0007221.234542e-042.191958e-042.053713e-051.596384e-032.227212e-040.0360482.309345e-010.1279580.0000542.083988e-041.509219e-050.0001129.321300e-044.029735e-030.0126632.721672e-060.0031323.013039e-041.746833e-035.409144e-05...1.601227e-030.0000410.0018141.219639e-035.147580e-055.155154e-050.0000791.297192e-022.781141e-040.0056330.0004790.0003790.0001348.739518e-047.647606e-062.221572e-050.0000043.618455e-050.0000480.0017541.500530e-040.0038404.810869e-070.0059540.0000370.1969934.568081e-049.755441e-071.030935e-031.507949e-010.0000500.0002120.0032680.0002910.0018771.129357e-050.0145066.614608e-040.0001030.000098
11104195cb1a.wav0.0000011.628391e-041.809853e-041.986881e-050.0000351.908054e-042.461921e-052.780522e-050.1163836.422612e-050.0001040.0001442.464258e-073.487829e-060.0002040.0005430.1962480.0242470.0001225.465921e-061.460897e-051.039055e-045.104658e-035.455400e-060.0003303.960028e-020.0263870.0000317.650796e-042.173632e-050.0007569.986504e-052.607870e-040.0053714.802940e-060.0014962.114155e-036.465405e-025.462122e-04...7.405314e-020.0064740.0027453.865033e-022.797323e-042.029552e-060.0000051.030654e-012.588023e-060.0018110.0001890.0000200.0003851.080045e-043.688912e-084.648699e-040.0000113.865633e-040.0008370.0081131.272571e-040.0004273.701392e-090.0028520.0001690.2156501.033186e-051.094671e-043.161006e-045.261113e-020.0000220.0000650.0018470.0000260.0002081.094946e-060.0012221.799843e-040.0000740.000011
111141af688a.wav0.0001092.754968e-051.617807e-042.101402e-040.0106743.839515e-058.939158e-079.060526e-030.0006861.929156e-020.0002960.0015681.164358e-032.147026e-040.1134420.0443980.0089470.0153530.0014225.368832e-031.208564e-022.556708e-031.359134e-033.977382e-040.0213512.174282e-020.0083320.0323355.806436e-031.241671e-050.0176711.108280e-051.225377e-030.0183631.440909e-040.0005324.218224e-031.708736e-042.412634e-03...5.260411e-040.0011650.0061702.061801e-032.528176e-039.480273e-060.0019988.848001e-053.853388e-040.1145300.0035180.0004300.0057516.077189e-031.839270e-042.966764e-030.0046262.085519e-020.0007470.0028611.046993e-020.0008829.183555e-050.0173830.1234850.0298892.642453e-031.527611e-042.738101e-036.532524e-020.0028050.0009440.0029140.0333970.0012602.083230e-030.0055785.332655e-020.0003170.083611
111241c60bba.wav0.0005361.431107e-044.249956e-033.454305e-040.0072621.853977e-022.690951e-041.610510e-030.0005349.395577e-030.0001220.0014061.041276e-033.092929e-040.0133940.0004840.0247750.0007660.0029421.237304e-039.552674e-036.723073e-049.493299e-056.325900e-040.0309943.399485e-030.0118400.1107846.413563e-044.886266e-030.0158481.086114e-044.108294e-030.0006012.003059e-030.0003741.365612e-031.242960e-042.568467e-03...4.601998e-040.0022820.0040511.181011e-032.032154e-015.529108e-040.0092161.048403e-036.269845e-050.0050080.0728530.0008310.0042051.006683e-032.742816e-042.019595e-040.0077931.164115e-020.0024140.0068251.384092e-030.0031574.587877e-040.1356280.0560920.0188506.531479e-051.845979e-033.290176e-025.357222e-020.0006870.0005020.0002650.0335460.0025065.192861e-040.0019978.807267e-030.0017990.019773
111341cfee6d.wav0.0007528.533224e-013.361616e-051.976465e-040.0000812.535216e-062.145653e-052.980523e-040.0000061.059934e-040.0010490.0003765.408557e-052.026185e-040.0000110.0000220.0002710.0001220.0008532.250905e-045.288495e-072.384114e-067.595178e-073.621403e-040.0060365.001384e-040.0006330.0000712.401904e-061.170803e-030.0001452.506168e-047.483019e-050.0000219.726332e-080.0000048.503975e-061.559419e-064.292245e-05...2.855400e-030.0000140.0000512.360624e-083.208847e-052.267040e-030.0000483.114288e-055.035015e-040.0028360.0001120.0003200.0001321.156721e-041.319003e-031.520555e-060.0001872.037504e-060.0018470.0000188.728817e-050.0000291.299164e-070.0058240.0002510.1013477.876576e-051.387085e-051.130778e-053.061404e-040.0001450.0102770.0002070.0005720.0000081.937160e-040.0000944.946753e-070.0004820.000020
111441f16193.wav0.0014281.572913e-044.257583e-061.831971e-030.0052123.307194e-046.458247e-074.716359e-030.0062981.157082e-040.0147000.0022135.607556e-037.377984e-040.0640570.0008140.0022730.0044420.0009138.433216e-034.857614e-031.589211e-041.151406e-022.882203e-030.0519441.896344e-030.0033350.0490901.036970e-041.580795e-040.0056901.949163e-055.916938e-040.0182261.010271e-030.0011881.544054e-042.121700e-051.251274e-04...9.345174e-050.0000680.0055677.961133e-031.232059e-022.239294e-040.0014672.319534e-054.060359e-050.0023950.0288590.0057850.0044402.300183e-032.337904e-048.466282e-060.0206863.676632e-040.0020630.0118794.625563e-040.0154229.261962e-030.2230300.0192950.1050348.144126e-043.284089e-061.558747e-033.630762e-030.0046270.0062990.0025530.1596300.0152513.363540e-030.0088703.283441e-030.0006480.032800
111541f1ea4a.wav0.0746512.097391e-039.024153e-051.290044e-030.0065244.507549e-047.408360e-054.623167e-050.0016441.494794e-050.1719060.0050374.867334e-024.625927e-040.0007530.0000050.0002580.0087990.0099162.277489e-038.386259e-048.440755e-042.269809e-031.624245e-030.0010186.047844e-050.0001510.0036502.023412e-062.575070e-030.0067687.269488e-041.404182e-050.0000358.613176e-050.0046509.866673e-063.823345e-053.931169e-03...2.124957e-050.0033200.0052287.031571e-054.305675e-031.153602e-030.0000162.869857e-055.799864e-030.0007680.0453490.0197930.0011925.112302e-021.627305e-021.128665e-060.0057882.087605e-050.0004410.0007871.979390e-040.0000562.307649e-030.0232440.0001510.0223496.720810e-028.702157e-054.799081e-056.369429e-050.0005950.0941210.0000110.1092060.0000431.527386e-010.0000161.721970e-040.0000040.001630
111641f86bc4.wav0.0122754.597004e-061.041870e-061.108591e-010.0047567.583213e-055.149296e-075.228466e-020.0000109.086083e-050.0005840.0012102.283093e-051.190525e-010.0058590.0001160.0002910.0000790.0006283.544412e-021.536154e-048.949828e-033.311160e-045.201068e-020.0000491.434028e-040.0027560.0019963.150889e-031.011080e-040.0017812.772629e-052.679944e-040.0191181.865675e-040.0270901.059066e-049.082190e-072.179720e-05...1.888128e-040.0239640.0372641.335635e-041.766954e-043.133099e-040.0001423.933625e-064.606144e-060.0069700.0000350.0001160.0007192.404230e-053.119211e-041.718681e-040.0026151.577607e-030.0044770.0015796.487466e-040.0152221.009881e-030.0005600.0044220.0033893.758392e-024.033464e-071.464765e-044.446671e-030.1618060.0000970.0050890.0127650.0189742.742922e-030.0009014.141305e-030.0062680.168439
11174215309a.wav0.0070161.166809e-051.908942e-044.371612e-030.0045514.013753e-045.540373e-062.521123e-020.0006553.005429e-040.0006210.0013303.279208e-022.502720e-030.0391180.0009960.0076430.0010990.0040548.108933e-031.155102e-019.419793e-031.292939e-025.447818e-030.0001333.171464e-030.0013440.0043075.614173e-031.340542e-030.0004242.879294e-051.857950e-030.0044511.964731e-020.0002382.334155e-056.405749e-051.300742e-01...7.397745e-040.0008490.0014831.316113e-034.974232e-044.029029e-060.0021591.505329e-049.678261e-050.0006350.0622370.0007730.0111172.730514e-042.219877e-032.048042e-030.0016393.725628e-010.0001120.0016398.075664e-060.0032028.858847e-030.0035160.0010280.0054671.847698e-031.088042e-043.820503e-036.427231e-030.0052380.0072930.0004330.0009500.0031351.140338e-030.0208562.829468e-030.0001760.002794
11184248d196.wav0.0007184.472765e-072.819911e-074.513846e-010.0000234.099113e-065.060380e-071.744119e-030.0000075.788434e-070.0001590.0000105.215728e-041.713694e-010.0000080.0000360.0000050.0000030.0000212.840242e-025.703184e-062.842315e-041.111273e-053.247655e-010.0000064.857669e-070.0000250.0000026.923027e-061.815113e-050.0001061.169006e-068.055175e-070.0001322.984590e-060.0003251.397893e-077.243050e-073.273314e-05...1.555307e-050.0000120.0000291.004048e-077.049059e-072.336224e-050.0000151.643383e-066.926491e-060.0000230.0000170.0007550.0001632.730250e-071.579984e-041.656955e-060.0001522.300639e-050.0005190.0000348.592230e-070.0001261.962341e-030.0000190.0000060.0002012.239383e-038.088248e-087.748721e-087.804358e-070.0046700.0034200.0001350.0001160.0000924.192469e-030.0001071.264107e-060.0001850.000186
111942542036.wav0.0904031.273267e-022.377892e-032.466837e-020.0148623.172161e-051.148355e-042.763204e-030.0007477.380627e-050.0159700.0280491.606786e-022.506395e-020.0002900.0013150.0004770.0054550.2954575.283047e-034.386170e-053.078220e-052.828751e-041.044318e-010.0008164.750976e-050.0004190.0027704.192928e-055.655159e-030.0000866.925306e-031.857141e-030.0007841.820370e-050.0001971.371859e-037.768242e-051.431908e-02...5.281945e-030.0002010.0017532.096449e-054.956024e-046.365159e-030.0020856.267646e-046.330230e-040.0018840.0070250.0240010.0030462.762767e-031.294016e-013.673481e-050.0013228.676654e-050.0020870.0001671.424453e-030.0009681.422975e-030.0030180.0009730.0021161.543025e-032.167562e-033.947694e-055.075460e-040.0364740.0622760.0001600.0022750.0009876.288621e-030.0010454.401285e-050.0017560.002288
\n

1120 rows × 81 columns

\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}