03_train_model/source_dir/training.py [11:62]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def parse_args():

    parser = argparse.ArgumentParser()

    parser.add_argument("--max_depth", type=int, default=5)
    parser.add_argument("--eta", type=float, default=0.05)
    parser.add_argument("--gamma", type=int, default=4)
    parser.add_argument("--min_child_weight", type=int, default=6)
    parser.add_argument("--silent", type=int, default=0)
    parser.add_argument("--objective", type=str, default="binary:logistic")
    parser.add_argument("--eval_metric", type=str, default="auc")
    parser.add_argument("--num_round", type=int, default=10)
    
    parser.add_argument('--train', type=str, default=os.environ.get('SM_CHANNEL_TRAIN'))
    parser.add_argument('--validation', type=str, default=os.environ.get('SM_CHANNEL_VALIDATION'))

    args = parser.parse_args()

    return args

def main():

    args = parse_args()
    train_files_path, validation_files_path = args.train, args.validation
    
    train_features_path = os.path.join(args.train, 'train_features.csv')
    train_labels_path = os.path.join(args.train, 'train_labels.csv')
    
    val_features_path = os.path.join(args.validation, 'val_features.csv')
    val_labels_path = os.path.join(args.validation, 'val_labels.csv')
    
    print('Loading training dataframes...')
    df_train_features = pd.read_csv(train_features_path, header=None)
    df_train_labels = pd.read_csv(train_labels_path, header=None)
    
    print('Loading validation dataframes...')
    df_val_features = pd.read_csv(val_features_path, header=None)
    df_val_labels = pd.read_csv(val_labels_path, header=None)
    
    X = df_train_features.values
    y = df_train_labels.values.reshape(-1)
    
    val_X = df_val_features.values
    val_y = df_val_labels.values.reshape(-1)
    
    print('Train features shape: {}'.format(X.shape))
    print('Train labels shape: {}'.format(y.shape))
    print('Validation features shape: {}'.format(val_X.shape))
    print('Validation labels shape: {}'.format(val_y.shape))

    dtrain = xgboost.DMatrix(X, label=y)
    dval = xgboost.DMatrix(val_X, label=val_y)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



03_train_model/source_dir/training_debug.py [14:65]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def parse_args():

    parser = argparse.ArgumentParser()

    parser.add_argument("--max_depth", type=int, default=5)
    parser.add_argument("--eta", type=float, default=0.05)
    parser.add_argument("--gamma", type=int, default=4)
    parser.add_argument("--min_child_weight", type=int, default=6)
    parser.add_argument("--silent", type=int, default=0)
    parser.add_argument("--objective", type=str, default="binary:logistic")
    parser.add_argument("--eval_metric", type=str, default="auc")
    parser.add_argument("--num_round", type=int, default=10)
    
    parser.add_argument('--train', type=str, default=os.environ.get('SM_CHANNEL_TRAIN'))
    parser.add_argument('--validation', type=str, default=os.environ.get('SM_CHANNEL_VALIDATION'))

    args = parser.parse_args()

    return args

def main():

    args = parse_args()
    train_files_path, validation_files_path = args.train, args.validation
    
    train_features_path = os.path.join(args.train, 'train_features.csv')
    train_labels_path = os.path.join(args.train, 'train_labels.csv')
    
    val_features_path = os.path.join(args.validation, 'val_features.csv')
    val_labels_path = os.path.join(args.validation, 'val_labels.csv')
    
    print('Loading training dataframes...')
    df_train_features = pd.read_csv(train_features_path, header=None)
    df_train_labels = pd.read_csv(train_labels_path, header=None)
    
    print('Loading validation dataframes...')
    df_val_features = pd.read_csv(val_features_path, header=None)
    df_val_labels = pd.read_csv(val_labels_path, header=None)
    
    X = df_train_features.values
    y = df_train_labels.values.reshape(-1)
    
    val_X = df_val_features.values
    val_y = df_val_labels.values.reshape(-1)
    
    print('Train features shape: {}'.format(X.shape))
    print('Train labels shape: {}'.format(y.shape))
    print('Validation features shape: {}'.format(val_X.shape))
    print('Validation labels shape: {}'.format(val_y.shape))

    dtrain = xgboost.DMatrix(X, label=y)
    dval = xgboost.DMatrix(val_X, label=val_y)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -