{"cells":[{"metadata":{},"cell_type":"markdown","source":"## This notebooks shows how to extract MFCC feature\n* Extract features first, reduce pre-process data time.\n* We can use MFCC feature into CNN model.\n* Dataset will public for competitors use.\n* Public MFCC dataset https://www.kaggle.com/super13579/rcsadmfcc/"},{"metadata":{},"cell_type":"markdown","source":"### import packages"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n\nimport os\nimport librosa\nimport soundfile as sf","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Load training data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_f = pd.read_csv(\"../input/rfcx-species-audio-detection/train_fp.csv\")\ntrain_t = pd.read_csv(\"../input/rfcx-species-audio-detection/train_tp.csv\")\nsubmit = pd.read_csv(\"../input/rfcx-species-audio-detection/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.concat([train_f,train_t]).reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### MFCC Extract function\n* we can change fs and mfcc dimention"},{"metadata":{"trusted":true},"cell_type":"code","source":"def MFCC_Extract(path,fs=551, mfcc_dim=20):\n    x , sr = sf.read(path)\n    mfccs = librosa.feature.mfcc(x, n_mfcc=mfcc_dim, sr=fs)\n    return mfccs","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Data save as npy file"},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\ntrain_MFCC = []\nos.makedirs(\"./train_mfcc\")\nfor i in tqdm(train_df['recording_id']):\n    audio_path = f\"../input/rfcx-species-audio-detection/train/{i}.flac\"\n    mfcc = MFCC_Extract(audio_path)\n    np.save(f\"./train_mfcc/{i}.npy\",mfcc)\n    del mfcc","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}