{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"from fastai.vision.all import *\nimport torchaudio","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DATA_PATH = Path('/kaggle/input/rfcx-species-audio-detection/')\ntrain_df = pd.read_csv(DATA_PATH/'train_tp.csv')\ntrain_files = get_files(DATA_PATH/'train', '.flac')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tfms = [torchaudio.transforms.MelSpectrogram(n_mels=32), torchaudio.transforms.AmplitudeToDB]\ndls = DataBlock(blocks=(TransformBlock(type_tfms=tfms), MultiCategoryBlock),                   \n                 get_x=lambda x: torchaudio.load(x)[0],\n                 get_y=lambda x: set(train_df[train_df.recording_id == x.stem].species_id) or {24}).dataloaders(train_files, bs=32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(dls, resnet18, config={\"n_in\":1}, metrics=[accuracy_multi])\nlearn.fine_tune(5, 1e-2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv(DATA_PATH/'sample_submission.csv')\ntest_files = [DATA_PATH/'test'/f'{id}.flac' for id in sample.recording_id]\n\ntest_dl = dls.test_dl(test_files)\npreds,_ = learn.get_preds(dl=test_dl)\n\nsubmission = pd.concat([sample['recording_id'], pd.DataFrame(preds[:,:-1].numpy(), columns=sample.columns[1:])], axis=1)\nsubmission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('submission.csv', index=False)","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}