Exemplo n.º 1
0
        'layers': 3,
        # 샘플을 위해 빨리 끝나도록 설정
        'nb_epoch': 5,  # 1000
        'patience': 10,
        'dropout': 0.5,
        'units': 512,
    }

    # 특징 지정
    features = [f'feat_{i}' for i in range(1, 94)]

    # xgboost에 의한 학습 및 예측
    runner = Runner('xgb1', ModelXGB, features, params_xgb)
    runner.run_train_cv()
    runner.run_predict_cv()
    Submission.create_submission('xgb1')

    # 신경망에 의한 학습 예측
    runner = Runner('nn1', ModelNN, features, params_nn)
    runner.run_train_cv()
    runner.run_predict_cv()
    Submission.create_submission('nn1')

    '''
    # (참고)xgboost를 통한 학습 및 예측 - 학습 데이터 전체를 사용하는 경우
    runner = Runner('xgb1-train-all', ModelXGB, features, params_xgb_all)
    runner.run_train_all()
    runner.run_test_all()
    Submission.create_submission('xgb1-train-all')
    '''
Exemplo n.º 2
0
    use_feature_name = runner.get_feature_name() # 今回の学習で使用する特徴量名を取得

    # モデルのconfigをjsonで保存
    value_list = [features, use_feature_name, model_params, cv, setting]
    save_model_config(key_list, value_list, dir_name, run_name)

    # runner.visualize_corr() # 相関係数を可視化して保存
    if cv.get('method') == 'None':
        runner.run_train_all()  # 全データで学習
        runner.run_predict_all()  # 推論
    else:
        runner.run_train_cv()  # 学習
        ModelLGB.calc_feature_importance(dir_name, run_name, use_feature_name)  # feature_importanceを計算
        runner.run_predict_cv()  # 推論

    Submission.create_submission(run_name, dir_name, setting.get('target'))  # submit作成


    # ######################################################
    # 学習・推論 xgboost ###################################

    # run nameの設定
    run_name = 'xgb'
    run_name = run_name + suffix
    dir_name = MODEL_DIR_NAME + run_name + '/'

    # exist_check(MODEL_DIR_NAME, run_name)  # 実行可否確認
    my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

    # 諸々の設定
    setting = {
Exemplo n.º 3
0
def main(mode='prd', create_features=True, model_type='lgb') -> str:

    # confirm('***** mode:{}, create_feature:{} '.format(str(mode), str(create_features)))

    now = datetime.datetime.now()
    suffix = now.strftime("_%m%d%H%M")

    # CVの設定.methodは[KFold, StratifiedKFold ,GroupKFold, StratifiedGroupKFold, CustomTimeSeriesSplitter, TrainTestSplit]から選択可能
    # CVしない場合(全データで学習させる場合)はmethodに'None'を設定
    # StratifiedKFold or GroupKFold or StratifiedGroupKFold の場合はcv_target_gr, cv_target_sfに対象カラム名を設定する
    # TrainTestSplitの場合はtest_sizeにtest setの割合を設定する

    cv = {
        'method': 'StratifiedKFold',
        'n_splits': 5,
        'random_state': 42,
        'shuffle': True,
        'cv_target_gr': 'chip_id',
        'cv_target_sf': 'target'
    }

    # run nameの設定
    run_name = 'cat'
    run_name = run_name + '_' + cv.get('method') + suffix + 'depth5_pl'
    dir_name = MODEL_DIR_NAME + run_name + '/'

    exist_check(MODEL_DIR_NAME, run_name)
    my_makedirs(dir_name)

    # 諸々の設定
    setting = {
        'run_name': run_name,  # run名
        'feature_directory': FEATURE_DIR_NAME,  # 特徴量の読み込み先ディレクトリ
        'target': 'target',  # 目的変数
        'calc_shap': False,  # shap値を計算するか否か
        'save_train_pred':
        True  # trainデータでの推論値を保存するか否か(trainデータでの推論値を特徴量として加えたい場合はTrueに設定する)
    }

    # モデルのパラメータ
    model_params = {
        'loss_function': 'Logloss',
        'eval_metric': 'AUC',
        'learning_rate': 0.05,
        'iterations': 4000,
        'early_stopping_rounds': 400,
        'random_seed': 42,
        'verbose_eval': 100,
        'depth': 5
    }

    features = [
        # 'chip_id',
        'exc_wl',
        # 'layout_a',
        # 'layout_x',
        # 'layout_y',
        'distance',
        'distance_x',
        'distance_y',
        'pos_x',
        'params0',
        'params1',
        'params2',
        'params3',
        'params4',
        'params5',
        'params6',
        # --- TODO: paramsの交互作用特徴量
        'params0_multi_rms',
        'params0_divid_rms',
        # 'params0_plus_rms',
        # 'params0_minus_rms',
        'params0_multi_beta',
        'params0_divid_beta',
        # 'params0_plus_beta',
        # 'params0_minus_beta',
        'params1_multi_rms',
        'params1_divid_rms',
        # 'params1_plus_rms',
        # 'params1_minus_rms',
        'params1_multi_beta',
        'params1_divid_beta',
        # 'params1_plus_beta',
        # 'params1_minus_beta',
        'params2_multi_rms',
        'params2_divid_rms',
        # 'params2_plus_rms',
        # 'params2_minus_rms',
        'params2_multi_beta',
        'params2_divid_beta',
        # 'params2_plus_beta',
        # 'params2_minus_beta',
        'params3_multi_rms',
        'params3_divid_rms',
        # 'params3_plus_rms',
        # 'params3_minus_rms',
        'params3_multi_beta',
        'params3_divid_beta',
        # 'params3_plus_beta',
        # 'params3_minus_beta',
        'params4_multi_rms',
        'params4_divid_rms',
        # 'params4_plus_rms',
        # 'params4_minus_rms',
        'params4_multi_beta',
        'params4_divid_beta',
        # 'params4_plus_beta',
        # 'params4_minus_beta',
        'params5_multi_rms',
        'params5_divid_rms',
        # 'params5_plus_rms',
        # 'params5_minus_rms',
        'params5_multi_beta',
        'params5_divid_beta',
        # 'params5_plus_beta',
        # 'params5_minus_beta',
        'params6_multi_rms',
        'params6_divid_rms',
        # 'params6_plus_rms',
        # 'params6_minus_rms',
        'params6_multi_beta',
        'params6_divid_beta',
        # 'params6_plus_beta',
        # 'params6_minus_beta',
        'params0_multi_params1',
        'params0_divid_params1',
        # 'params0_plus_params1',
        # 'params0_minus_params1',
        'params0_multi_params2',
        'params0_divid_params2',
        # 'params0_plus_params2',
        # 'params0_minus_params2',
        'params0_multi_params3',
        'params0_divid_params3',
        # 'params0_plus_params3',
        # 'params0_minus_params3',
        'params0_multi_params4',
        'params0_divid_params4',
        # 'params0_plus_params4',
        # 'params0_minus_params4',
        'params0_multi_params5',
        'params0_divid_params5',
        # 'params0_plus_params5',
        # 'params0_minus_params5',
        'params0_multi_params6',
        'params0_divid_params6',
        # 'params0_plus_params6',
        # 'params0_minus_params6',
        'params1_multi_params0',
        'params1_divid_params0',
        # 'params1_plus_params0',
        # 'params1_minus_params0',
        'params1_multi_params2',
        'params1_divid_params2',
        # 'params1_plus_params2',
        # 'params1_minus_params2',
        'params1_multi_params3',
        'params1_divid_params3',
        # 'params1_plus_params3',
        # 'params1_minus_params3',
        'params1_multi_params4',
        'params1_divid_params4',
        # 'params1_plus_params4',
        # 'params1_minus_params4',
        'params1_multi_params5',
        'params1_divid_params5',
        # 'params1_plus_params5',
        # 'params1_minus_params5',
        'params1_multi_params6',
        'params1_divid_params6',
        # 'params1_plus_params6',
        # 'params1_minus_params6',
        'params2_multi_params0',
        'params2_divid_params0',
        # 'params2_plus_params0',
        # 'params2_minus_params0',
        'params2_multi_params1',
        'params2_divid_params1',
        # 'params2_plus_params1',
        # 'params2_minus_params1',
        'params2_multi_params3',
        'params2_divid_params3',
        # 'params2_plus_params3',
        # 'params2_minus_params3',
        'params2_multi_params4',
        'params2_divid_params4',
        # 'params2_plus_params4',
        # 'params2_minus_params4',
        'params2_multi_params5',
        'params2_divid_params5',
        # 'params2_plus_params5',
        # 'params2_minus_params5',
        # 'params2_absminus_params5',
        'params2_multi_params6',
        'params2_divid_params6',
        # 'params2_plus_params6',
        # 'params2_minus_params6',
        'params3_multi_params0',
        'params3_divid_params0',
        # 'params3_plus_params0',
        # 'params3_minus_params0',
        'params3_multi_params1',
        'params3_divid_params1',
        # 'params3_plus_params1',
        # 'params3_minus_params1',
        'params3_multi_params2',
        'params3_divid_params2',
        # 'params3_plus_params2',
        # 'params3_minus_params2',
        'params3_multi_params4',
        'params3_divid_params4',
        # 'params3_plus_params4',
        # 'params3_minus_params4',
        'params3_multi_params5',
        'params3_divid_params5',
        # 'params3_plus_params5',
        # 'params3_minus_params5',
        'params3_multi_params6',
        'params3_divid_params6',
        # 'params3_plus_params6',
        # 'params3_minus_params6',
        'params4_multi_params0',
        'params4_divid_params0',
        # 'params4_plus_params0',
        # 'params4_minus_params0',
        'params4_multi_params1',
        'params4_divid_params1',
        # 'params4_plus_params1',
        # 'params4_minus_params1',
        'params4_multi_params2',
        'params4_divid_params2',
        # 'params4_plus_params2',
        # 'params4_minus_params2',
        'params4_multi_params3',
        'params4_divid_params3',
        # 'params4_plus_params3',
        # 'params4_minus_params3',
        'params4_multi_params5',
        'params4_divid_params5',
        # 'params4_plus_params5',
        # 'params4_minus_params5',
        'params4_multi_params6',
        'params4_divid_params6',
        # 'params4_plus_params6',
        # 'params4_minus_params6',
        'params5_multi_params0',
        'params5_divid_params0',
        # 'params5_plus_params0',
        # 'params5_minus_params0',
        'params5_multi_params1',
        'params5_divid_params1',
        # 'params5_plus_params1',
        # 'params5_minus_params1',
        'params5_multi_params2',
        'params5_divid_params2',
        # 'params5_plus_params2',
        # 'params5_minus_params2',
        'params5_multi_params3',
        'params5_divid_params3',
        # 'params5_plus_params3',
        # 'params5_minus_params3',
        'params5_multi_params4',
        'params5_divid_params4',
        # 'params5_plus_params4',
        # 'params5_minus_params4',
        'params5_multi_params6',
        'params5_divid_params6',
        # 'params5_plus_params6',
        # 'params5_minus_params6',
        'params6_multi_params0',
        'params6_divid_params0',
        # 'params6_plus_params0',
        # 'params6_minus_params0',
        'params6_multi_params1',
        'params6_divid_params1',
        # 'params6_plus_params1',
        # 'params6_minus_params1',
        'params6_multi_params2',
        'params6_divid_params2',
        # 'params6_plus_params2',
        # 'params6_minus_params2',
        'params6_multi_params3',
        'params6_divid_params3',
        # 'params6_plus_params3',
        # 'params6_minus_params3',
        'params6_multi_params4',
        'params6_divid_params4',
        # 'params6_plus_params4',
        # 'params6_minus_params4',
        'params6_multi_params5',
        'params6_divid_params5',
        # 'params6_plus_params5',
        # 'params6_minus_params5',
        'rms',
        'beta',
        # --- TODO: スペクトル波長データ
        'intensity_max',
        'intensity_min',
        'intensity_mean',
        'intensity_std',
        'intensity_sum',
        'intensity_median',
        'intensity_amplitude_v',
        # 'intensity_max_log1p',
        # 'intensity_mean_log1p',
        # 'intensity_std_log1p',
        # 'intensity_sum_log1p',
        # 'intensity_median_log1p',
        # 'intensity_amplitude_v_log1p',
        'intensity_q10',
        'intensity_q25',
        'intensity_q50',
        'intensity_q75',
        'intensity_q80',
        'intensity_q85',
        'intensity_q90',
        'intensity_max_minus_q90',
        'intensity_max_minus_q85',
        'intensity_max_minus_q80',
        'intensity_max_minus_q75',
        'intensity_max_minus_q50',
        'intensity_max_multi_q90',
        'intensity_max_multi_q85',
        'intensity_max_multi_q80',
        'intensity_max_multi_q75',
        'intensity_max_multi_q50',
        'intensity_max_divid_q90',
        'intensity_max_divid_q85',
        'intensity_max_divid_q80',
        'intensity_max_divid_q75',
        'intensity_max_divid_q50',
        'intensity_q85_divid_q90',
        'intensity_q80_divid_q90',
        'intensity_q75_divid_q90',
        'intensity_q50_divid_q90',
        # --- ピーク&半値幅のデータ
        'fwhm_09',
        # 'num_peak_09',
        'fwhm_088',
        # 'num_peak_088',
        'fwhm_086',
        # 'num_peak_086',
        'fwhm_084',
        # 'num_peak_084',
        'fwhm_082',
        # 'num_peak_082',
        'fwhm_08',
        # 'num_peak_08',
        'fwhm_078',
        # 'num_peak_078',
        'fwhm_076',
        # 'num_peak_076',
        'fwhm_074',
        # 'num_peak_074',
        'fwhm_072',
        # 'num_peak_072',
        'fwhm_07',
        # 'num_peak_07',
        'fwhm_068',
        # 'num_peak_068',
        'fwhm_066',
        # 'num_peak_066',
        'fwhm_064',
        # 'num_peak_064',
        'fwhm_062',
        # 'num_peak_062',
        'fwhm_06',
        # 'num_peak_06',
        'fwhm_058',
        # 'num_peak_058',
        'fwhm_056',
        # 'num_peak_056',
        'fwhm_054',
        # 'num_peak_054',
        'fwhm_052',
        # 'num_peak_052',
        'fwhm_05',
        # 'num_peak_05',
        'fwhm_divid_num_peak_09',
        'fwhm_mult_num_peak_09',
        'fwhm_divid_num_peak_088',
        'fwhm_mult_num_peak_088',
        'fwhm_divid_num_peak_086',
        'fwhm_mult_num_peak_086',
        'fwhm_divid_num_peak_084',
        'fwhm_mult_num_peak_084',
        'fwhm_divid_num_peak_082',
        'fwhm_mult_num_peak_082',
        'fwhm_divid_num_peak_08',
        'fwhm_mult_num_peak_08',
        'fwhm_divid_num_peak_078',
        'fwhm_mult_num_peak_078',
        'fwhm_divid_num_peak_076',
        'fwhm_mult_num_peak_076',
        'fwhm_divid_num_peak_074',
        'fwhm_mult_num_peak_074',
        'fwhm_divid_num_peak_072',
        'fwhm_mult_num_peak_072',
        'fwhm_divid_num_peak_07',
        'fwhm_mult_num_peak_07',
        # 'fwhm_divid_num_peak_068',
        # 'fwhm_mult_num_peak_068',
        # 'fwhm_divid_num_peak_066',
        # 'fwhm_mult_num_peak_066',
        # 'fwhm_divid_num_peak_064',
        # 'fwhm_mult_num_peak_064',
        # 'fwhm_divid_num_peak_062',
        # 'fwhm_mult_num_peak_062',
        # 'fwhm_divid_num_peak_06',
        # 'fwhm_mult_num_peak_06',
        # 'fwhm_divid_num_peak_058',
        # 'fwhm_mult_num_peak_058',
        # 'fwhm_divid_num_peak_056',
        # 'fwhm_mult_num_peak_056',
        # 'fwhm_divid_num_peak_054',
        # 'fwhm_mult_num_peak_054',
        # 'fwhm_divid_num_peak_052',
        # 'fwhm_mult_num_peak_052',
        # 'fwhm_divid_num_peak_05',
        # 'fwhm_mult_num_peak_05',
        # --- TODO: 波形の圧縮データ
        'dc_umap1',
        'dc_umap2',
        'dc_tsne1',
        'dc_tsne2',
        # --- TODO: カテゴリごとの平均値と自身との差分
        # 'diff_chip_id_mean_params0',
        # 'diff_chip_id_mean_params1',
        # 'diff_chip_id_mean_params2',
        # 'diff_chip_id_mean_params3',
        # 'diff_chip_id_mean_params4',
        # 'diff_chip_id_mean_params5',
        # 'diff_chip_id_mean_params6',
        # 'diff_chip_id_mean_rms',
        # 'diff_chip_id_mean_beta',
        # 'diff_chip_id_mean_intensity_amplitude_v',
        # 'diff_chip_id_mean_fwhm_09',
        # # 'diff_chip_id_mean_num_peak_09',
        # 'diff_chip_id_mean_fwhm_088',
        # # 'diff_chip_id_mean_num_peak_088',
        # 'diff_chip_id_mean_fwhm_086',
        # # 'diff_chip_id_mean_num_peak_086',
        # 'diff_chip_id_mean_fwhm_084',
        # # 'diff_chip_id_mean_num_peak_084',
        # 'diff_chip_id_mean_fwhm_082',
        # # 'diff_chip_id_mean_num_peak_082',
        # 'diff_chip_id_mean_fwhm_08',
        # # 'diff_chip_id_mean_num_peak_08',
        # 'diff_chip_id_mean_fwhm_078',
        # # 'diff_chip_id_mean_num_peak_078',
        # 'diff_chip_id_mean_fwhm_076',
        # # 'diff_chip_id_mean_num_peak_076',
        # 'diff_chip_id_mean_fwhm_074',
        # # 'diff_chip_id_mean_num_peak_074',
        # 'diff_chip_id_mean_fwhm_072',
        # # 'diff_chip_id_mean_num_peak_072',
        # 'diff_chip_id_mean_fwhm_07',
        # # 'diff_chip_id_mean_num_peak_07',
        # 'diff_chip_id_mean_fwhm_068',
        # # 'diff_chip_id_mean_num_peak_068',
        # 'diff_chip_id_mean_fwhm_066',
        # # 'diff_chip_id_mean_num_peak_066',
        # 'diff_chip_id_mean_fwhm_064',
        # # 'diff_chip_id_mean_num_peak_064',
        # 'diff_chip_id_mean_fwhm_062',
        # # 'diff_chip_id_mean_num_peak_062',
        # 'diff_chip_id_mean_fwhm_06',
        # # 'diff_chip_id_mean_num_peak_06',
        # 'diff_chip_id_mean_fwhm_058',
        # # 'diff_chip_id_mean_num_peak_058',
        # 'diff_chip_id_mean_fwhm_056',
        # # 'diff_chip_id_mean_num_peak_056',
        # 'diff_chip_id_mean_fwhm_054',
        # # 'diff_chip_id_mean_num_peak_054',
        # 'diff_chip_id_mean_fwhm_052',
        # # 'diff_chip_id_mean_num_peak_052',
        # 'diff_chip_id_mean_fwhm_05',
        # # 'diff_chip_id_mean_num_peak_05',
        # # 'diff_chip_id_mean_intensity_max',
        # # 'diff_chip_id_mean_intensity_min',
        # # 'diff_chip_id_mean_intensity_q90',
        # # 'diff_chip_id_mean_intensity_q75',
        'diff_exc_wl_mean_params0',
        'diff_exc_wl_mean_params1',
        'diff_exc_wl_mean_params2',
        'diff_exc_wl_mean_params3',
        'diff_exc_wl_mean_params4',
        'diff_exc_wl_mean_params5',
        'diff_exc_wl_mean_params6',
        'diff_exc_wl_mean_rms',
        'diff_exc_wl_mean_beta',
        'diff_exc_wl_mean_intensity_amplitude_v',
        'diff_exc_wl_mean_fwhm_09',
        # 'diff_exc_wl_mean_num_peak_09',
        'diff_exc_wl_mean_fwhm_088',
        # 'diff_exc_wl_mean_num_peak_088',
        'diff_exc_wl_mean_fwhm_086',
        # 'diff_exc_wl_mean_num_peak_086',
        'diff_exc_wl_mean_fwhm_084',
        # 'diff_exc_wl_mean_num_peak_084',
        'diff_exc_wl_mean_fwhm_082',
        # 'diff_exc_wl_mean_num_peak_082',
        'diff_exc_wl_mean_fwhm_08',
        # 'diff_exc_wl_mean_num_peak_08',
        'diff_exc_wl_mean_fwhm_078',
        # 'diff_exc_wl_mean_num_peak_078',
        'diff_exc_wl_mean_fwhm_076',
        # 'diff_exc_wl_mean_num_peak_076',
        'diff_exc_wl_mean_fwhm_074',
        # 'diff_exc_wl_mean_num_peak_074',
        'diff_exc_wl_mean_fwhm_072',
        # 'diff_exc_wl_mean_num_peak_072',
        'diff_exc_wl_mean_fwhm_07',
        # 'diff_exc_wl_mean_num_peak_07',
        'diff_exc_wl_mean_fwhm_068',
        # 'diff_exc_wl_mean_num_peak_068',
        'diff_exc_wl_mean_fwhm_066',
        # 'diff_exc_wl_mean_num_peak_066',
        'diff_exc_wl_mean_fwhm_064',
        # 'diff_exc_wl_mean_num_peak_064',
        'diff_exc_wl_mean_fwhm_062',
        # 'diff_exc_wl_mean_num_peak_062',
        'diff_exc_wl_mean_fwhm_06',
        # 'diff_exc_wl_mean_num_peak_06',
        'diff_exc_wl_mean_fwhm_058',
        # 'diff_exc_wl_mean_num_peak_058',
        'diff_exc_wl_mean_fwhm_056',
        # 'diff_exc_wl_mean_num_peak_056',
        'diff_exc_wl_mean_fwhm_054',
        # 'diff_exc_wl_mean_num_peak_054',
        'diff_exc_wl_mean_fwhm_052',
        # 'diff_exc_wl_mean_num_peak_052',
        'diff_exc_wl_mean_fwhm_05',
        # # 'diff_exc_wl_mean_num_peak_05',
        # # 'diff_exc_wl_mean_intensity_max',
        # # 'diff_exc_wl_mean_intensity_min',
        # # 'diff_exc_wl_mean_intensity_q90',
        # # 'diff_exc_wl_mean_intensity_q75',
        # 'diff_layout_a_mean_params0',
        # 'diff_layout_a_mean_params1',
        # 'diff_layout_a_mean_params2',
        # 'diff_layout_a_mean_params3',
        # 'diff_layout_a_mean_params4',
        # 'diff_layout_a_mean_params5',
        # 'diff_layout_a_mean_params6',
        # 'diff_layout_a_mean_rms',
        # 'diff_layout_a_mean_beta',
        # 'diff_layout_a_mean_intensity_amplitude_v',
        # 'diff_layout_a_mean_fwhm_09',
        # # 'diff_layout_a_mean_num_peak_09',
        # 'diff_layout_a_mean_fwhm_088',
        # # 'diff_layout_a_mean_num_peak_088',
        # 'diff_layout_a_mean_fwhm_086',
        # # 'diff_layout_a_mean_num_peak_086',
        # 'diff_layout_a_mean_fwhm_084',
        # # 'diff_layout_a_mean_num_peak_084',
        # 'diff_layout_a_mean_fwhm_082',
        # # 'diff_layout_a_mean_num_peak_082',
        # 'diff_layout_a_mean_fwhm_08',
        # # 'diff_layout_a_mean_num_peak_08',
        # 'diff_layout_a_mean_fwhm_078',
        # # 'diff_layout_a_mean_num_peak_078',
        # 'diff_layout_a_mean_fwhm_076',
        # # 'diff_layout_a_mean_num_peak_076',
        # 'diff_layout_a_mean_fwhm_074',
        # # 'diff_layout_a_mean_num_peak_074',
        # 'diff_layout_a_mean_fwhm_072',
        # # 'diff_layout_a_mean_num_peak_072',
        # 'diff_layout_a_mean_fwhm_07',
        # # 'diff_layout_a_mean_num_peak_07',
        # 'diff_layout_a_mean_fwhm_068',
        # # 'diff_layout_a_mean_num_peak_068',
        # 'diff_layout_a_mean_fwhm_066',
        # # 'diff_layout_a_mean_num_peak_066',
        # 'diff_layout_a_mean_fwhm_064',
        # # 'diff_layout_a_mean_num_peak_064',
        # 'diff_layout_a_mean_fwhm_062',
        # # 'diff_layout_a_mean_num_peak_062',
        # 'diff_layout_a_mean_fwhm_06',
        # # 'diff_layout_a_mean_num_peak_06',
        # 'diff_layout_a_mean_fwhm_058',
        # # 'diff_layout_a_mean_num_peak_058',
        # 'diff_layout_a_mean_fwhm_056',
        # # 'diff_layout_a_mean_num_peak_056',
        # 'diff_layout_a_mean_fwhm_054',
        # # 'diff_layout_a_mean_num_peak_054',
        # 'diff_layout_a_mean_fwhm_052',
        # # 'diff_layout_a_mean_num_peak_052',
        # 'diff_layout_a_mean_fwhm_05',
        # # 'diff_layout_a_mean_num_peak_05',
        # # 'diff_layout_a_mean_intensity_max',
        # # 'diff_layout_a_mean_intensity_min',
        # # 'diff_layout_a_mean_intensity_q90',
        # # 'diff_layout_a_mean_intensity_q75',
        # --- TODO: tsfreshで生成した特徴
        'intensity__ratio_beyond_r_sigma__r_10',
        'intensity__ar_coefficient__coeff_2__k_10',
        'intensity__change_quantiles__f_agg_"var"__isabs_True__qh_1.0__ql_0.8',
        'intensity__change_quantiles__f_agg_"var"__isabs_True__qh_1.0__ql_0.6',
        'intensity__change_quantiles__f_agg_"var"__isabs_True__qh_1.0__ql_0.4',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_1.0__ql_0.8',
        'intensity__change_quantiles__f_agg_"var"__isabs_True__qh_1.0__ql_0.2',
        'intensity__change_quantiles__f_agg_"var"__isabs_True__qh_1.0__ql_0.0',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_1.0__ql_0.6',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_1.0__ql_0.4',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_1.0__ql_0.0',
        'intensity__cid_ce__normalize_False',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_1.0__ql_0.2',
        'intensity__fft_coefficient__attr_"abs"__coeff_55',
        'intensity__fft_coefficient__attr_"abs"__coeff_56',
        'intensity__large_standard_deviation__r_0.1',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_5__f_agg_"var"',
        'intensity__fft_coefficient__attr_"abs"__coeff_64',
        'intensity__fft_coefficient__attr_"abs"__coeff_57',
        'intensity__fft_coefficient__attr_"abs"__coeff_51',
        'intensity__fft_coefficient__attr_"abs"__coeff_52',
        'intensity__fft_coefficient__attr_"abs"__coeff_66',
        'intensity__fft_coefficient__attr_"abs"__coeff_68',
        'intensity__fft_coefficient__attr_"abs"__coeff_59',
        'intensity__fft_coefficient__attr_"abs"__coeff_61',
        'intensity__fft_coefficient__attr_"abs"__coeff_53',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_1.0__ql_0.8',
        'intensity__fft_coefficient__attr_"abs"__coeff_54',
        'intensity__fft_coefficient__attr_"abs"__coeff_65',
        'intensity__partial_autocorrelation__lag_2',
        'intensity__fft_coefficient__attr_"abs"__coeff_63',
        'intensity__fft_coefficient__attr_"abs"__coeff_62',
        'intensity__fft_coefficient__attr_"abs"__coeff_71',
        'intensity__ar_coefficient__coeff_1__k_10',
        'intensity__fft_coefficient__attr_"abs"__coeff_50',
        'intensity__fft_coefficient__attr_"abs"__coeff_49',
        'intensity__fft_coefficient__attr_"abs"__coeff_48',
        'intensity__fft_coefficient__attr_"abs"__coeff_58',
        'intensity__fft_coefficient__attr_"abs"__coeff_46',
        'intensity__fft_coefficient__attr_"abs"__coeff_69',
        'intensity__fft_coefficient__attr_"abs"__coeff_67',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_1.0__ql_0.6',
        'intensity__fft_coefficient__attr_"abs"__coeff_47',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_50__f_agg_"max"',
        'intensity__fft_coefficient__attr_"abs"__coeff_60',
        'intensity__fft_coefficient__attr_"abs"__coeff_80',
        'intensity__fft_coefficient__attr_"abs"__coeff_72',
        'intensity__fft_coefficient__attr_"abs"__coeff_76',
        'intensity__binned_entropy__max_bins_10',
        'intensity__fft_coefficient__attr_"abs"__coeff_70',
        'intensity__fft_coefficient__attr_"abs"__coeff_79',
        'intensity__ar_coefficient__coeff_3__k_10',
        'intensity__fft_coefficient__attr_"abs"__coeff_44',
        'intensity__fft_coefficient__attr_"abs"__coeff_78',
        'intensity__fft_coefficient__attr_"abs"__coeff_74',
        'intensity__fft_coefficient__attr_"abs"__coeff_77',
        'intensity__fft_coefficient__attr_"abs"__coeff_45',
        'intensity__maximum',
        'intensity__fft_coefficient__attr_"abs"__coeff_81',
        'intensity__fft_coefficient__attr_"abs"__coeff_75',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_10__f_agg_"var"',
        'intensity__fft_coefficient__attr_"abs"__coeff_43',
        'intensity__fft_coefficient__attr_"abs"__coeff_83',
        'intensity__fft_coefficient__attr_"abs"__coeff_40',
        'intensity__fft_coefficient__attr_"abs"__coeff_82',
        'intensity__fft_coefficient__attr_"abs"__coeff_73',
        'intensity__fft_coefficient__attr_"abs"__coeff_42',
        'intensity__fft_coefficient__attr_"abs"__coeff_41',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_1.0__ql_0.4',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_10__f_agg_"max"',
        'intensity__fft_coefficient__attr_"abs"__coeff_36',
        'intensity__fft_coefficient__attr_"abs"__coeff_86',
        'intensity__fft_coefficient__attr_"abs"__coeff_39',
        'intensity__fft_coefficient__attr_"abs"__coeff_87',
        'intensity__index_mass_quantile__q_0.2',
        'intensity__fft_coefficient__attr_"abs"__coeff_84',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_2',
        'intensity__mean_abs_change',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_1.0__ql_0.0',
        'intensity__absolute_sum_of_changes',
        'intensity__fft_aggregated__aggtype_"kurtosis"',
        'intensity__fft_aggregated__aggtype_"variance"',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_1',
        'intensity__fft_coefficient__attr_"abs"__coeff_38',
        'intensity__index_mass_quantile__q_0.3',
        'intensity__fft_coefficient__attr_"abs"__coeff_37',
        'intensity__fft_coefficient__attr_"abs"__coeff_85',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_5__f_agg_"max"',
        'intensity__fft_coefficient__attr_"abs"__coeff_90',
        'intensity__fft_coefficient__attr_"abs"__coeff_88',
        'intensity__fft_coefficient__attr_"abs"__coeff_92',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_1.0__ql_0.2',
        'intensity__fft_coefficient__attr_"abs"__coeff_94',
        'intensity__fft_coefficient__attr_"abs"__coeff_89',
        'intensity__fft_coefficient__attr_"abs"__coeff_93',
        'intensity__fft_coefficient__attr_"abs"__coeff_35',
        'intensity__kurtosis',
        'intensity__skewness',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_5__f_agg_"var"',
        'intensity__fft_coefficient__attr_"abs"__coeff_97',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_3',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_0',
        'intensity__spkt_welch_density__coeff_2',
        'intensity__fft_coefficient__attr_"abs"__coeff_34',
        'intensity__index_mass_quantile__q_0.4',
        'intensity__partial_autocorrelation__lag_5',
        'intensity__index_mass_quantile__q_0.1',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_50__f_agg_"var"',
        'intensity__ratio_beyond_r_sigma__r_0.5',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_50__f_agg_"max"',
        'intensity__fft_coefficient__attr_"abs"__coeff_95',
        'intensity__partial_autocorrelation__lag_6',
        'intensity__approximate_entropy__m_2__r_0.9',
        'intensity__count_below_mean',
        'intensity__count_above_mean',
        'intensity__fft_coefficient__attr_"abs"__coeff_91',
        'intensity__approximate_entropy__m_2__r_0.7',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_10__f_agg_"max"',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_10__f_agg_"var"',
        'intensity__approximate_entropy__m_2__r_0.5',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_5__f_agg_"max"',
        'intensity__sample_entropy',
        'intensity__approximate_entropy__m_2__r_0.3',
        'intensity__fft_coefficient__attr_"abs"__coeff_96',
        'intensity__fft_coefficient__attr_"imag"__coeff_1',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_50__f_agg_"mean"',
        'intensity__linear_trend__attr_"stderr"',
        'intensity__linear_trend__attr_"slope"',
        'intensity__fft_coefficient__attr_"abs"__coeff_4',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_10__f_agg_"max"',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_5__f_agg_"mean"',
        'intensity__fft_coefficient__attr_"abs"__coeff_33',
        'intensity__first_location_of_maximum',
        'intensity__last_location_of_maximum',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_50__f_agg_"var"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_10__f_agg_"mean"',
        'intensity__fft_coefficient__attr_"abs"__coeff_3',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_50__f_agg_"mean"',
        'intensity__fft_coefficient__attr_"abs"__coeff_32',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_10__f_agg_"mean"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_5__f_agg_"mean"',
        'intensity__standard_deviation',
        'intensity__variance',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_5__f_agg_"max"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_5__f_agg_"min"',
        'intensity__linear_trend__attr_"rvalue"',
        'intensity__fft_coefficient__attr_"abs"__coeff_6',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_50__f_agg_"max"',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_9',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_5__f_agg_"min"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_10__f_agg_"var"',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_5__f_agg_"mean"',
        'intensity__fft_coefficient__attr_"abs"__coeff_2',
        'intensity__fft_coefficient__attr_"abs"__coeff_99',
        'intensity__augmented_dickey_fuller__attr_"usedlag"__autolag_"AIC"',
        'intensity__spkt_welch_density__coeff_5',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_10__f_agg_"min"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_10__f_agg_"min"',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_10__f_agg_"mean"',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_5__f_agg_"var"',
        'intensity__fft_coefficient__attr_"abs"__coeff_31',
        'intensity__fft_coefficient__attr_"abs"__coeff_5',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_50__f_agg_"mean"',
        'intensity__c3__lag_1',
        'intensity__fft_coefficient__attr_"abs"__coeff_7',
        'intensity__fft_coefficient__attr_"abs"__coeff_8',
        'intensity__fft_coefficient__attr_"abs"__coeff_30',
        'intensity__fft_coefficient__attr_"abs"__coeff_9',
        'intensity__fft_coefficient__attr_"abs"__coeff_98',
        'intensity__ar_coefficient__coeff_7__k_10',
        'intensity__ratio_beyond_r_sigma__r_7',
        'intensity__ar_coefficient__coeff_6__k_10',
        'intensity__fft_coefficient__attr_"abs"__coeff_29',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_50__f_agg_"var"',
        'intensity__fft_coefficient__attr_"abs"__coeff_1',
        'intensity__variation_coefficient',
        'intensity__fft_coefficient__attr_"abs"__coeff_10',
        'intensity__max_langevin_fixed_point__m_3__r_30',
        'intensity__c3__lag_2',
        'intensity__spkt_welch_density__coeff_8',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_8',
        'intensity__abs_energy',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_10__f_agg_"min"',
        'intensity__c3__lag_3',
        'intensity__fft_coefficient__attr_"abs"__coeff_11',
        'intensity__ratio_beyond_r_sigma__r_1',
        'intensity__fft_coefficient__attr_"abs"__coeff_13',
        'intensity__agg_linear_trend__attr_"stderr"__chunk_len_5__f_agg_"min"',
        'intensity__fft_coefficient__attr_"real"__coeff_1',
        'intensity__index_mass_quantile__q_0.6',
        'intensity__fft_coefficient__attr_"abs"__coeff_27',
        'intensity__partial_autocorrelation__lag_7',
        'intensity__fft_coefficient__attr_"abs"__coeff_12',
        'intensity__agg_linear_trend__attr_"slope"__chunk_len_50__f_agg_"min"',
        'intensity__linear_trend__attr_"pvalue"',
        'intensity__fft_coefficient__attr_"abs"__coeff_28',
        'intensity__agg_linear_trend__attr_"rvalue"__chunk_len_50__f_agg_"min"',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_5__f_agg_"min"',
        'intensity__fft_coefficient__attr_"abs"__coeff_15',
        'intensity__fft_coefficient__attr_"abs"__coeff_25',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_10__f_agg_"min"',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_50__f_agg_"min"',
        'intensity__linear_trend__attr_"intercept"',
        'intensity__fft_coefficient__attr_"abs"__coeff_14',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_5__f_agg_"mean"',
        'intensity__fft_aggregated__aggtype_"skew"',
        'intensity__fft_coefficient__attr_"abs"__coeff_16',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_10__f_agg_"mean"',
        'intensity__partial_autocorrelation__lag_4',
        'intensity__fft_coefficient__attr_"abs"__coeff_26',
        'intensity__fft_coefficient__attr_"angle"__coeff_1',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_5__f_agg_"max"',
        'intensity__fft_coefficient__attr_"abs"__coeff_17',
        'intensity__index_mass_quantile__q_0.9',
        'intensity__fft_coefficient__attr_"abs"__coeff_24',
        'intensity__fft_coefficient__attr_"abs"__coeff_18',
        'intensity__longest_strike_above_mean',
        'intensity__fft_aggregated__aggtype_"centroid"',
        'intensity__longest_strike_below_mean',
        'intensity__approximate_entropy__m_2__r_0.1',
        'intensity__fft_coefficient__attr_"abs"__coeff_22',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_10__f_agg_"max"',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_50__f_agg_"mean"',
        'intensity__fft_coefficient__attr_"abs"__coeff_23',
        'intensity__cwt_coefficients__coeff_5__w_5__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_4__w_5__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_6__w_5__widths_(2, 5, 10, 20)',
        'intensity__sum_of_reoccurring_data_points',
        'intensity__partial_autocorrelation__lag_1',
        'intensity__autocorrelation__lag_1',
        'intensity__ar_coefficient__coeff_8__k_10',
        'intensity__fft_coefficient__attr_"imag"__coeff_7',
        'intensity__cwt_coefficients__coeff_3__w_5__widths_(2, 5, 10, 20)',
        'intensity__sum_of_reoccurring_values',
        'intensity__fft_coefficient__attr_"abs"__coeff_20',
        'intensity__fft_coefficient__attr_"abs"__coeff_19',
        'intensity__ar_coefficient__coeff_4__k_10',
        'intensity__cid_ce__normalize_True',
        'intensity__fft_coefficient__attr_"abs"__coeff_21',
        'intensity__cwt_coefficients__coeff_7__w_5__widths_(2, 5, 10, 20)',
        'intensity__energy_ratio_by_chunks__num_segments_10__segment_focus_4',
        'intensity__friedrich_coefficients__coeff_3__m_3__r_30',
        'intensity__ar_coefficient__coeff_10__k_10',
        'intensity__index_mass_quantile__q_0.7',
        'intensity__minimum',
        'intensity__large_standard_deviation__r_0.15000000000000002',
        'intensity__quantile__q_0.1',
        'intensity__quantile__q_0.2',
        'intensity__fft_coefficient__attr_"real"__coeff_9',
        'intensity__cwt_coefficients__coeff_7__w_10__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_8__w_10__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_2__w_5__widths_(2, 5, 10, 20)',
        'intensity__quantile__q_0.3',
        'intensity__cwt_coefficients__coeff_9__w_10__widths_(2, 5, 10, 20)',
        'intensity__quantile__q_0.4',
        'intensity__cwt_coefficients__coeff_6__w_10__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_2__w_2__widths_(2, 5, 10, 20)',
        'intensity__range_count__max_1000000000000.0__min_0',
        'intensity__count_above__t_0',
        'intensity__count_below__t_0',
        'intensity__cwt_coefficients__coeff_8__w_5__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_10__w_10__widths_(2, 5, 10, 20)',
        'intensity__ratio_beyond_r_sigma__r_5',
        'intensity__median',
        'intensity__cwt_coefficients__coeff_5__w_10__widths_(2, 5, 10, 20)',
        'intensity__number_crossing_m__m_0',
        'intensity__number_crossing_m__m_1',
        'intensity__number_crossing_m__m_-1',
        'intensity__fft_coefficient__attr_"imag"__coeff_21',
        'intensity__cwt_coefficients__coeff_11__w_10__widths_(2, 5, 10, 20)',
        'intensity__quantile__q_0.6',
        'intensity__cwt_coefficients__coeff_4__w_10__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_3__w_2__widths_(2, 5, 10, 20)',
        'intensity__ar_coefficient__coeff_5__k_10',
        'intensity__cwt_coefficients__coeff_12__w_10__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"angle"__coeff_11',
        'intensity__first_location_of_minimum',
        'intensity__range_count__max_1__min_-1',
        'intensity__last_location_of_minimum',
        'intensity__quantile__q_0.7',
        'intensity__fft_coefficient__attr_"angle"__coeff_21',
        'intensity__cwt_coefficients__coeff_9__w_5__widths_(2, 5, 10, 20)',
        'intensity__number_peaks__n_50',
        'intensity__cwt_coefficients__coeff_3__w_10__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_13__w_10__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"real"__coeff_61',
        'intensity__change_quantiles__f_agg_"mean"__isabs_True__qh_0.4__ql_0.2',
        'intensity__value_count__value_1',
        'intensity__partial_autocorrelation__lag_9',
        'intensity__fft_coefficient__attr_"real"__coeff_51',
        'intensity__fft_coefficient__attr_"imag"__coeff_18',
        'intensity__cwt_coefficients__coeff_0__w_20__widths_(2, 5, 10, 20)',
        'intensity__ratio_beyond_r_sigma__r_1.5',
        'intensity__cwt_coefficients__coeff_14__w_10__widths_(2, 5, 10, 20)',
        'intensity__change_quantiles__f_agg_"var"__isabs_False__qh_0.4__ql_0.2',
        'intensity__fft_coefficient__attr_"angle"__coeff_18',
        'intensity__cwt_coefficients__coeff_1__w_5__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"real"__coeff_8',
        'intensity__fft_coefficient__attr_"real"__coeff_22',
        'intensity__fft_coefficient__attr_"imag"__coeff_2',
        'intensity__fft_coefficient__attr_"imag"__coeff_22',
        'intensity__friedrich_coefficients__coeff_2__m_3__r_30',
        'intensity__cwt_coefficients__coeff_1__w_20__widths_(2, 5, 10, 20)',
        'intensity__cwt_coefficients__coeff_1__w_2__widths_(2, 5, 10, 20)',
        'intensity__value_count__value_-1',
        'intensity__agg_autocorrelation__f_agg_"median"__maxlag_40',
        'intensity__fft_coefficient__attr_"real"__coeff_50',
        'intensity__cwt_coefficients__coeff_2__w_20__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"imag"__coeff_62',
        'intensity__cwt_coefficients__coeff_3__w_20__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"real"__coeff_4',
        'intensity__fft_coefficient__attr_"angle"__coeff_13',
        'intensity__friedrich_coefficients__coeff_0__m_3__r_30',
        'intensity__agg_linear_trend__attr_"intercept"__chunk_len_50__f_agg_"max"',
        'intensity__cwt_coefficients__coeff_2__w_10__widths_(2, 5, 10, 20)',
        'intensity__fft_coefficient__attr_"real"__coeff_2',
        'intensity__quantile__q_0.8',
        'intensity__autocorrelation__lag_9',
        'intensity__fft_coefficient__attr_"real"__coeff_46',
        'intensity__number_cwt_peaks__n_1',
        # --- TODO: camaroさんの特徴量
        # 'peak_wave_length',
        # 'peak_intensity',
        # 'mean',
        # 'std',
        # 'skew',
        # 'kurtosis',
        # 'skew_10',
        # 'kurtosis_10',
        # 'mean_10',
        # 'std_10',
        # 'skew_15',
        # 'kurtosis_15',
        # 'mean_15',
        # 'std_15',
        # 'skew_20',
        # 'kurtosis_20',
        # 'mean_20',
        # 'std_20',
        # 'skew_25',
        # 'kurtosis_25',
        # 'mean_25',
        # 'std_25',
        # 'skew_30',
        # 'kurtosis_30',
        # 'mean_30',
        # 'std_30',
        # 'skew_50',
        # 'kurtosis_50',
        # 'mean_50',
        # 'std_50',
        # 'skew_100',
        # 'kurtosis_100',
        # 'mean_100',
        # 'std_100',
        # 'skew_150',
        # 'kurtosis_150',
        # 'mean_150',
        # 'std_150',
        # 'skew_200',
        # 'kurtosis_200',
        # 'mean_200',
        # 'std_200',
        # 'em_ev',
        # 'ex_ev',
        # 'ev_diff',
        # 'ev_ratio',
        # 'num_peak',
        # 'num_strong_peak',
        # 'peak_wave_length2',
        # 'peak_intensity2',
        # 'peak_ratio',
        # 'peak_ratio2'
    ]

    try:
        # インスタンス生成
        runner = atm5_Runner(run_name, ModelCB, features, setting,
                             model_params, cv, FEATURE_DIR_NAME,
                             MODEL_DIR_NAME)
        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        runner.run_train_cv()  # 学習
        runner.run_predict_cv()  # 推論

        Submission.create_submission(run_name, dir_name,
                                     setting.get('target'))  # submit作成

        print('Done!')

    except Exception as e:
        print(traceback.format_exc())
        print(f'ERROR:{e}')
Exemplo n.º 4
0
    save_model_config(key_list, value_list, dir_name, run_name)

    # 学習
    if cv_setting.get('method') == 'None':
        runner.run_train_all()  # 全データで学習
        runner.run_predict_all()  # 予測
    else:
        runner.run_train_cv()  # 学習
        ModelLGB.calc_feature_importance(
            dir_name, run_name, use_feature_name)  # feature_importanceを計算
        ModelLGB.plot_learning_curve(run_name)  # learning curveを描画
        runner.run_predict_cv()  # 予測

    # submissionファイルの作成
    lgb_preds = Util.load_df_pickle(dir_name + f'{run_name}-pred.pkl')
    Submission.create_submission(run_name, dir_name, lgb_preds)  # submit作成

# ##### ニューラルネットワーク ###########################################################

#     features = features

#     # CV設定の読み込み
#     cv_setting = get_cv_info(random_state=53)

#     # run nameの設定
#     run_name = get_run_name(cv_setting, model_type="nn")
#     dir_name = MODEL_DIR_NAME + run_name + '/'

#     my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

#     # ファイルの設定を読み込む
Exemplo n.º 5
0
def main(model_type='lgb') -> str:
    """トレーニングのmain関数

    model_typeによって学習するモデルを変更する
    → lgb, cb, xgb, nnが標準で用意されている

    Args:
        model_type (str, optional): どのモデルで学習させるかを指定. Defaults to 'lgb'.

    Returns:
        str: [description]

    Examples:
        >>> python hoge.py --model_type="lgb"
        >>> python hoge.py lgb

    """

    cv = get_cv_info()  # CVの情報辞書
    run_name = get_run_name(cv, model_type)  # run名
    dir_name = MODEL_DIR_NAME + run_name + '/'  # 学習に使用するディレクトリ
    setting = get_setting_info()  # 諸々の設定ファイル辞書

    # すでに実行済みのrun名がないかチェックし、ディレクトリを作成する
    exist_check(MODEL_DIR_NAME, run_name)
    my_makedirs(dir_name)

    # モデルに合わせてパラメータを読み込む
    model_cls = None
    if model_type == 'lgb':
        model_params = yml['MODEL_LGB']['PARAM']
        model_cls = atm5_ModelLGB
    elif model_type == 'cb':
        model_params = yml['MODEL_CB']['PARAM']
        model_cls = ModelCB
    elif model_type == 'xgb':
        pass
    elif model_type == 'nn':
        pass
    else:
        print('model_typeが不正なため終了します')
        sys.exit(0)

    features = [
        'exc_wl',
        'distance',
        'distance_x',
        'distance_y',
        'pos_x',
        'params0',
        'params1',
        'params2',
        'params3',
        'params4',
        'params5',
        'params6',
        'params0_multi_rms',
        'params0_divid_rms',
        'params0_multi_beta',
        'params0_divid_beta',
        'params1_multi_rms',
        'params1_divid_rms',
        'params1_multi_beta',
        'params1_divid_beta',
        'params2_multi_rms',
        'params2_divid_rms',
        'params2_multi_beta',
        'params2_divid_beta',
        'params3_multi_rms',
        'params3_divid_rms',
        'params3_multi_beta',
        'params3_divid_beta',
        'params4_multi_rms',
        'params4_divid_rms',
        'params4_multi_beta',
        'params4_divid_beta',
        'params5_multi_rms',
        'params5_divid_rms',
        'params5_multi_beta',
        'params5_divid_beta',
        'params6_multi_rms',
        'params6_divid_rms',
        'params6_multi_beta',
        'params6_divid_beta',
        'params0_multi_params1',
        'params0_divid_params1',
        'params0_multi_params2',
        'params0_divid_params2',
        'params0_multi_params3',
        'params0_divid_params3',
        'params0_multi_params4',
        'params0_divid_params4',
        'params0_multi_params5',
        'params0_divid_params5',
        'params0_multi_params6',
        'params0_divid_params6',
        'params1_multi_params0',
        'params1_divid_params0',
        'params1_multi_params2',
        'params1_divid_params2',
        'params1_multi_params3',
        'params1_divid_params3',
        'params1_multi_params4',
        'params1_divid_params4',
        'params1_multi_params5',
        'params1_divid_params5',
        'params1_multi_params6',
        'params1_divid_params6',
        'params2_multi_params0',
        'params2_divid_params0',
        'params2_multi_params1',
        'params2_divid_params1',
        'params2_multi_params3',
        'params2_divid_params3',
        'params2_multi_params4',
        'params2_divid_params4',
        'params2_multi_params5',
        'params2_divid_params5',
        'params2_multi_params6',
        'params2_divid_params6',
        'params3_multi_params0',
        'params3_divid_params0',
        'params3_multi_params1',
        'params3_divid_params1',
        'params3_multi_params2',
        'params3_divid_params2',
        'params3_multi_params4',
        'params3_divid_params4',
        'params3_multi_params5',
        'params3_divid_params5',
        'params3_multi_params6',
        'params3_divid_params6',
        'params4_multi_params0',
        'params4_divid_params0',
        'params4_multi_params1',
        'params4_divid_params1',
        'params4_multi_params2',
        'params4_divid_params2',
        'params4_multi_params3',
        'params4_divid_params3',
        'params4_multi_params5',
        'params4_divid_params5',
        'params4_multi_params6',
        'params4_divid_params6',
        'params5_multi_params0',
        'params5_divid_params0',
        'params5_multi_params1',
        'params5_divid_params1',
        'params5_multi_params2',
        'params5_divid_params2',
        'params5_multi_params3',
        'params5_divid_params3',
        'params5_multi_params4',
        'params5_divid_params4',
        'params5_multi_params6',
        'params5_divid_params6',
        'params6_multi_params0',
        'params6_divid_params0',
        'params6_multi_params1',
        'params6_divid_params1',
        'params6_multi_params2',
        'params6_divid_params2',
        'params6_multi_params3',
        'params6_divid_params3',
        'params6_multi_params4',
        'params6_divid_params4',
        'params6_multi_params5',
        'params6_divid_params5',
        'rms',
        'beta',
        # --- TODO: スペクトル波長データ
        'intensity_max',
        'intensity_min',
        'intensity_mean',
        'intensity_std',
        'intensity_sum',
        'intensity_median',
        'intensity_amplitude_v',
        'intensity_q10',
        'intensity_q25',
        'intensity_q50',
        'intensity_q75',
        'intensity_q80',
        'intensity_q85',
        'intensity_q90',
        'intensity_max_minus_q90',
        'intensity_max_minus_q85',
        'intensity_max_minus_q80',
        'intensity_max_minus_q75',
        'intensity_max_minus_q50',
        'intensity_max_multi_q90',
        'intensity_max_multi_q85',
        'intensity_max_multi_q80',
        'intensity_max_multi_q75',
        'intensity_max_multi_q50',
        'intensity_max_divid_q90',
        'intensity_max_divid_q85',
        'intensity_max_divid_q80',
        'intensity_max_divid_q75',
        'intensity_max_divid_q50',
        'intensity_q85_divid_q90',
        'intensity_q80_divid_q90',
        'intensity_q75_divid_q90',
        'intensity_q50_divid_q90',
        # --- TODO: 波形の圧縮データ
        'dc_umap1',
        'dc_umap2',
        'dc_tsne1',
        'dc_tsne2',
        'diff_exc_wl_mean_params0',
        'diff_exc_wl_mean_params1',
        'diff_exc_wl_mean_params2',
        'diff_exc_wl_mean_params3',
        'diff_exc_wl_mean_params4',
        'diff_exc_wl_mean_params5',
        'diff_exc_wl_mean_params6',
        'diff_exc_wl_mean_rms',
        'diff_exc_wl_mean_beta',
        'diff_exc_wl_mean_intensity_amplitude_v',
        'diff_exc_wl_mean_fwhm_09',
    ]

    try:
        # インスタンス生成
        runner = atm5_Runner(run_name, model_cls, features, setting,
                             model_params, cv)
        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        # 学習・推論
        runner.run_train_cv()
        runner.run_predict_cv()

        # submit作成
        Submission.create_submission(run_name, dir_name, setting.get('target'))

        if model_type == 'lgb':
            # feature_importanceを計算
            atm5_ModelLGB.calc_feature_importance(dir_name,
                                                  run_name,
                                                  use_feature_name,
                                                  cv.get('n_splits'),
                                                  type='gain')

    except Exception as e:
        print(traceback.format_exc())
        print(f'ERROR:{e}')
Exemplo n.º 6
0
    params_nn = {
        "layers": 3,
        # サンプルのため早く終わるように設定
        "nb_epoch": 5,  # 1000
        "patience": 10,
        "dropout": 0.5,
        "units": 512,
    }

    # 特徴量の指定
    features = [f"feat_{i}" for i in range(1, 94)]

    # xgboostによる学習・予測
    runner = Runner("xgb1", ModelXGB, features, params_xgb)
    runner.run_train_cv()
    runner.run_predict_cv()
    Submission.create_submission("xgb1")

    # ニューラルネットによる学習・予測
    runner = Runner("nn1", ModelNN, features, params_nn)
    runner.run_train_cv()
    runner.run_predict_cv()
    Submission.create_submission("nn1")
    """
    # (参考)xgboostによる学習・予測 - 学習データ全体を使う場合
    runner = Runner('xgb1-train-all', ModelXGB, features, params_xgb_all)
    runner.run_train_all()
    runner.run_test_all()
    Submission.create_submission('xgb1-train-all')
    """
Exemplo n.º 7
0
def main(mode='prd', create_features=True, model_type='lgb', is_kernel=False) -> str:

    confirm('mode:{}, create_feature:{} '.format(str(mode), str(create_features)))

    if create_features:
        # データ生成
        train, test, specs, train_labels, submission = read_data_all(mode)

        features_train, features_test, win_code, list_of_user_activities, list_of_event_code, \
            activities_labels, assess_titles, list_of_event_id, all_title_event_code, all_type_world = encode_title(train, test)

        del train, test
        gc.collect()

        features_train = features_train.merge(specs, how='left', on='event_id', suffixes=('','_y'))
        features_test = features_test.merge(specs, how='left', on='event_id', suffixes=('','_y'))
        features_train, features_test = get_train_and_test(features_train, features_test,
                                        win_code, list_of_user_activities, list_of_event_code,
                                        activities_labels, assess_titles, list_of_event_id, all_title_event_code, all_type_world, is_kernel)
        reduce_train, reduce_test, _ = preprocess(features_train, features_test, assess_titles)

        # user属性情報の生成とマージ
        """ スコア悪くなるので一旦コメント
        train, train_session_master = add_session_order_to_train(train, train_labels)
        user_profiles_train = create_user_profile_train(train)
        user_profiles_test = create_user_profile_test(test)
        train_session_master = train_session_master.merge(user_profiles_train, how='left', on=['installation_id', 'session_order'])
        reduce_train = reduce_train.merge(train_session_master, how='left', on=['installation_id', 'game_session'])
        reduce_test = reduce_test.merge(user_profiles_test, how='left', on='installation_id')
        """

        del features_train, features_test, _
        gc.collect()

        # 不要なカラムの削除
        # cols_to_drop = ['game_session', 'installation_id', 'timestamp', 'session_order', 'accuracy_group', 'timestampDate'] + ['acc_' + title for title in assess_titles] # installation_idでGroupKFoldしない場合はこちらを使用
        cols_to_drop = ['game_session', 'timestamp', 'session_order', 'accuracy_group', 'timestampDate'] + ['acc_' + title for title in assess_titles]
        cols_to_drop = [col for col in cols_to_drop if col in reduce_train.columns]
        X_train = reduce_train.drop(cols_to_drop, axis=1)
        X_train.columns = ["".join(c if c.isalnum() else "_" for c in str(x)) for x in X_train.columns]  # カラム名にカンマなどが含まれており、lightgbmでエラーが出るため
        y_train = reduce_train['accuracy_group']

        cols_to_drop = [col for col in cols_to_drop if col in reduce_test.columns]
        X_test = reduce_test.drop(cols_to_drop, axis=1)
        X_test.columns = ["".join(c if c.isalnum() else "_" for c in str(x)) for x in X_test.columns]  # カラム名にカンマなどが含まれており、lightgbmでエラーが出るため

        # 特徴量選択
        """ スコア悪くなるので一旦コメント
        to_exclude, X_test = select_ajusted(X_train, X_test)
        X_train = X_train.drop(to_exclude, axis=1)
        X_test = X_test.drop(to_exclude, axis=1)
        """

        X_train.to_pickle(FEATURE_DIR_NAME + 'X_train.pkl')
        y_train.to_pickle(FEATURE_DIR_NAME + 'y_train.pkl')
        X_test.to_pickle(FEATURE_DIR_NAME + 'X_test.pkl')

    # CVの設定.methodは[KFold, StratifiedKFold ,GroupKFold]から選択可能
    # CVしない場合(全データで学習させる場合)はmethodに'None'を設定
    # StratifiedKFold or GroupKFoldの場合は、cv_targetに対象カラム名を設定する
    cv = {
        'method': 'GroupKFold',
        'n_splits': 5,
        'random_state': 42,
        'shuffle': True,
        'cv_target': 'installation_id'
    }

    if model_type == 'lgb' or model_type == 'all':
        # ######################################################
        # 学習・推論 LightGBM ###################################

        # run nameの設定
        run_name = 'lgb'
        run_name = run_name + suffix
        dir_name = MODEL_DIR_NAME + run_name + '/'

        exist_check(MODEL_DIR_NAME, run_name)
        my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

        # 諸々の設定
        setting = {
            'run_name': run_name,  # run名
            'feature_directory': FEATURE_DIR_NAME,  # 特徴量の読み込み先ディレクトリ
            'target': 'accuracy_group',  # 目的変数
            'calc_shap': False,  # shap値を計算するか否か
            'save_train_pred': False  # trainデータでの推論値を保存するか否か(trainデータでの推論値を特徴量として加えたい場合はTrueに設定する)
        }

        # モデルのパラメータ
        model_params = {
            'boosting_type': 'gbdt',
            'objective': 'regression',
            'metric': 'rmse',
            'learning_rate': 0.01,
            'subsample': 0.75,
            'subsample_freq': 1,
            'feature_fraction': 0.9,
            'max_depth': 15,
            'lambda_l1': 1,
            'lambda_l2': 1,
            'num_round': 50000,
            'early_stopping_rounds': 300,
            'verbose': -1,
            'verbose_eval': 300,
            'random_state': 999
        }

        if is_kernel:
            runner = Runner(run_name, ModelLGB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME, X_train, y_train, X_test)
        else:
            runner = Runner(run_name, ModelLGB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME)

        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        if cv.get('method') == 'None':
            # TODO: こちらも動くように修正する
            runner.run_train_all()  # 全データで学習
            runner.run_predict_all()  # 推論
        else:
            runner.run_train_cv()  # 学習
            ModelLGB.calc_feature_importance(dir_name, run_name, use_feature_name)  # feature_importanceを計算
            _pred = runner.run_predict_cv(is_kernel)  # 推論

        if is_kernel:
            # kaggleカーネル実行
            if model_type == 'lgb':
                # シングルモデルでのcsv作成
                submission[setting.get('target')] = _pred.astype(int)
                submission.to_csv('submission.csv', index=False)
            else:
                # ブレンドするためのcsv作成
                submission_lgb = submission.copy()
                submission_lgb[setting.get('target')] = _pred.astype(int)
                submission_lgb.to_csv('submission_lgb.csv', index=False)
        else:
            # ローカルでの実行
            Submission.create_submission(run_name, dir_name, setting.get('target'))  # submit作成


    if model_type == 'cb' or model_type == 'all':
        # ######################################################
        # 学習・推論 Catboost ###################################
        # run nameの設定
        run_name = 'cb'
        run_name = run_name + suffix
        dir_name = MODEL_DIR_NAME + run_name + '/'

        exist_check(MODEL_DIR_NAME, run_name)
        my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

        # 諸々の設定
        setting = {
            'run_name': run_name,  # run名
            'feature_directory': FEATURE_DIR_NAME,  # 特徴量の読み込み先ディレクトリ
            'target': 'accuracy_group',  # 目的変数
            'calc_shap': False,  # shap値を計算するか否か
            'save_train_pred': False  # trainデータでの推論値を保存するか否か(trainデータでの推論値を特徴量として加えたい場合はTrueに設定する)
        }

        # モデルのパラメータ
        model_params = {
            'loss_function': 'RMSE',
            'task_type': "CPU",
            'iterations': 50000,
            'od_type': "Iter",
            'depth': 10,
            'colsample_bylevel': 0.5,
            'early_stopping_rounds': 300,
            'l2_leaf_reg': 18,
            'random_seed': 42,
            'verbose_eval': 300,
            'use_best_model': True
        }

        if is_kernel:
            runner = Runner(run_name, ModelCB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME, X_train, y_train, X_test)
        else:
            runner = Runner(run_name, ModelCB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME)

        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        if cv.get('method') == 'None':
            # TODO: こちらも動くように修正する
            runner.run_train_all()  # 全データで学習
            runner.run_predict_all()  # 推論
        else:
            runner.run_train_cv()  # 学習
            _pred = runner.run_predict_cv(is_kernel)  # 推論

        if is_kernel:
            # kaggleカーネル実行
            if model_type == 'cb':
                # シングルモデルでのcsv作成
                submission[setting.get('target')] = _pred.astype(int)
                submission.to_csv('submission.csv', index=False)
            else:
                # ブレンドするためのcsv作成
                submission_cb = submission.copy()
                submission_cb[setting.get('target')] = _pred.astype(int)
                submission_cb.to_csv('submission_cb.csv', index=False)
        else:
            # ローカルでの実行
            Submission.create_submission(run_name, dir_name, setting.get('target'))  # submit作成

    if model_type == 'nn' or model_type == 'all':
        # ######################################################
        # 学習・推論 NN(MLP) ###################################
        # run nameの設定
        run_name = 'nn'
        run_name = run_name + suffix
        dir_name = MODEL_DIR_NAME + run_name + '/'

        exist_check(MODEL_DIR_NAME, run_name)
        my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

        # 諸々の設定
        setting = {
            'run_name': run_name,  # run名
            'feature_directory': FEATURE_DIR_NAME,  # 特徴量の読み込み先ディレクトリ
            'target': 'accuracy_group',  # 目的変数
            'calc_shap': False,  # shap値を計算するか否か
            'save_train_pred': False  # trainデータでの推論値を保存するか否か(trainデータでの推論値を特徴量として加えたい場合はTrueに設定する)
        }

        # モデルのパラメータ
        model_params = {
            'layers': 4,
            'nb_epoch': 500,
            'patience': 20,
            'dropout': 0.3,
            'units': 512,
            'classes': 1
        }

        if is_kernel:
            runner = Runner(run_name, ModelNN, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME, X_train, y_train, X_test)
        else:
            runner = Runner(run_name, ModelNN, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME)

        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        # one-hot-encoding
        if len(runner.categoricals) > 0:
            one_hot_encoder = ce.OneHotEncoder(cols=runner.categoricals, drop_invariant=True)
            one_hot_encoder.fit(runner.train_x[runner.categoricals])
            ohe_path = os.path.join('.', 'one-hot-enc.pkl')
            Util.dump(one_hot_encoder, ohe_path)

        if cv.get('method') == 'None':
            # TODO: こちらも動くように修正する
            runner.run_train_all()  # 全データで学習
            runner.run_predict_all()  # 推論
        else:
            runner.run_train_cv()  # 学習
            _pred = runner.run_predict_cv(is_kernel)  # 推論

        if is_kernel:
            # kaggleカーネル実行
            if model_type == 'nn':
                # シングルモデルでのcsv作成
                submission[setting.get('target')] = _pred.astype(int)
                submission.to_csv('submission.csv', index=False)
            else:
                # ブレンドするためのcsv作成
                submission_nn = submission.copy()
                submission_nn[setting.get('target')] = _pred.astype(int)
                submission_nn.to_csv('submission_nn.csv', index=False)
        else:
            # ローカルでの実行
            Submission.create_submission(run_name, dir_name, setting.get('target'))  # submit作成

    if model_type == 'xgb' or model_type == 'all':
        # ######################################################
        # 学習・推論 xgboost ###################################
        # run nameの設定
        run_name = 'xgb'
        run_name = run_name + suffix
        dir_name = MODEL_DIR_NAME + run_name + '/'

        exist_check(MODEL_DIR_NAME, run_name)
        my_makedirs(dir_name)  # runディレクトリの作成。ここにlogなどが吐かれる

        # 諸々の設定
        setting = {
            'run_name': run_name,  # run名
            'feature_directory': FEATURE_DIR_NAME,  # 特徴量の読み込み先ディレクトリ
            'target': 'accuracy_group',  # 目的変数
            'calc_shap': False,  # shap値を計算するか否か
            'save_train_pred': False  # trainデータでの推論値を保存するか否か(trainデータでの推論値を特徴量として加えたい場合はTrueに設定する)
        }

        # モデルのパラメータ
        model_params = {
            'objective':'reg:squarederror',
            'eval_metric': 'rmse',
            'colsample_bytree': 0.8,
            'learning_rate': 0.01,
            'max_depth': 10,
            'subsample': 1,
            'min_child_weight':3,
            'gamma':0.25,
            'num_round': 50000,
            'early_stopping_rounds': 300,
            'verbose': 300,
            'random_state': 999
        }

        if is_kernel:
            runner = Runner(run_name, ModelXGB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME, X_train, y_train, X_test)
        else:
            runner = Runner(run_name, ModelXGB, setting, model_params, cv, FEATURE_DIR_NAME, MODEL_DIR_NAME)

        use_feature_name = runner.get_feature_name()  # 今回の学習で使用する特徴量名を取得

        # モデルのconfigをjsonで保存
        value_list = [use_feature_name, model_params, cv, setting]
        save_model_config(key_list, value_list, dir_name, run_name)

        if cv.get('method') == 'None':
            # TODO: こちらも動くように修正する
            runner.run_train_all()  # 全データで学習
            runner.run_predict_all()  # 推論
        else:
            runner.run_train_cv()  # 学習
            ModelXGB.calc_feature_importance(dir_name, run_name, use_feature_name)  # feature_importanceを計算
            _pred = runner.run_predict_cv(is_kernel)  # 推論

        if is_kernel:
            # kaggleカーネル実行
            if model_type == 'xgb':
                # シングルモデルでのcsv作成
                submission[setting.get('target')] = _pred.astype(int)
                submission.to_csv('submission.csv', index=False)
            else:
                # ブレンドするためのcsv作成
                submission_xgb = submission.copy()
                submission_xgb[setting.get('target')] = _pred.astype(int)
                submission_xgb.to_csv('submission_xgb.csv', index=False)
        else:
            # ローカルでの実行
            Submission.create_submission(run_name, dir_name, setting.get('target'))  # submit作成

    # 推論のブレンド
    # TODO: xbgの結果も入れる
    if model_type == 'all' and is_kernel:
        weights = {'lgb': 0.30, 'cb': 0.40, 'nn': 0.00, 'xgb': 0.30}
        blend_pred = (submission_lgb[setting.get('target')] * weights['lgb']) \
                        + (submission_cb[setting.get('target')] * weights['cb']) \
                        + (submission_nn[setting.get('target')] * weights['nn']) \
                        + (submission_xgb[setting.get('target')] * weights['xgb'])

        dist = Counter(reduce_train[setting.get('target')])
        for k in dist:
            dist[k] /= len(reduce_train)

        acum = 0
        bound = {}
        for i in range(3):
            acum += dist[i]
            bound[i] = np.percentile(blend_pred, acum * 100)

        def classify(x):
            if x <= bound[0]:
                return 0
            elif x <= bound[1]:
                return 1
            elif x <= bound[2]:
                return 2
            else:
                return 3

        blend_pred = np.array(list(map(classify, blend_pred)))

        submission[setting.get('target')] = blend_pred.astype(int)
        submission.to_csv('submission.csv', index=False)

    return 'Success!'