{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":70203,"databundleVersionId":8068726,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport librosa\nimport numpy as np\nimport pandas as pd\nfrom sklearn.preprocessing import StandardScaler\nimport joblib\n\n# サンプルサブミッションの読み込み\nsample_sub = pd.read_csv('/kaggle/input/birdclef-2024/sample_submission.csv')\nprint(sample_sub.head())\n\n# 特徴量抽出関数\ndef extract_features(file_name):\n    try:\n        audio, sample_rate = librosa.load(file_name, sr=32000)\n        mfccs = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=13)\n        mfccs_scaled = np.mean(mfccs.T, axis=0)\n        return mfccs_scaled\n    except Exception as e:\n        print(f\"Error processing {file_name}: {e}\")\n        return None\n\n# テストデータの音声ファイルリストを取得\ntest_audio_dir = \"/kaggle/input/birdclef-2024/test_soundscapes\"\ntest_audio_files = [os.path.join(test_audio_dir, f) for f in os.listdir(test_audio_dir) if f.endswith('.ogg')]\nprint(f\"Found {len(test_audio_files)} test audio files.\")\n\nif len(test_audio_files) == 0:\n    print(\"No test audio files found. This is expected when running locally.\")\n    # ダミーの提出ファイルを作成\n    dummy_data = {'row_id': ['soundscape_0_5', 'soundscape_0_10'], 'prediction': ['nocall', 'nocall']}\n    submission = pd.DataFrame(dummy_data)\n    submission.to_csv('submission.csv', index=False)\n    print(\"Dummy submission file created successfully:\")\n    print(submission.head())\nelse:\n    # テストデータの特徴量を抽出\n    test_features_list = []\n    for file_path in test_audio_files:\n        features = extract_features(file_path)\n        if features is not None:\n            test_features_list.append(features)\n\n    # 特徴量リストをNumPy配列に変換\n    test_features_array = np.array(test_features_list)\n    print(f\"Extracted features from {len(test_features_list)} test files.\")\n\n    if test_features_array.size > 0:\n        # スケーラーとモデルの読み込み\n        scaler = StandardScaler()\n        scaler.mean_ = np.load('scaler_mean.npy')\n        scaler.scale_ = np.load('scaler_scale.npy')\n        model = joblib.load('trained_model.pkl')\n\n        # テストデータのスケーリング\n        scaled_test_features = scaler.transform(test_features_array)\n\n        # 予測の実行\n        test_predictions = model.predict(scaled_test_features)\n\n        # 提出ファイルの作成\n        submission = pd.DataFrame(test_predictions, columns=['prediction'])\n        submission['row_id'] = [f'soundscape_{i}_{j*5}' for i in range(len(test_audio_files)) for j in range(1, 49)]  # 適宜変更\n\n        # 提出ファイルの保存\n        submission.to_csv('submission.csv', index=False)\n        print(\"Submission file created successfully:\")\n        print(submission.head())\n    else:\n        print(\"No features were extracted from the test data.\")","metadata":{"execution":{"iopub.status.busy":"2024-05-30T04:09:51.169054Z","iopub.execute_input":"2024-05-30T04:09:51.169430Z","iopub.status.idle":"2024-05-30T04:09:53.753458Z","shell.execute_reply.started":"2024-05-30T04:09:51.169401Z","shell.execute_reply":"2024-05-30T04:09:53.752077Z"},"trusted":true},"execution_count":null,"outputs":[]}]}