kazutotess / ML-ROM_Various_Shapes

This repository contains the simple source codes of "Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes"
15 stars 10 forks source link

FileNotFoundError: [Errno 2] No such file or directory: './data/LSTM/Dataset/72_values_MS-BN-1_dataset.csv' #2

Open NainaWay opened 3 years ago

NainaWay commented 3 years ago

Hi, This is NainaWay. I am working on your file "LSTM_with_shape.py", I am finding it difficult as you haven't given any dummy data. For the file, "Muliti-Scale_CNN-AE.py" one can feed image data directly but for the other file, you are using CSV files for both LSTM and CNN-AE. I'll be really thankful to you if you share some dummy data so that I can create my own dataset for the model.

` # perpare data assert num_of_ts + time_step * (maxlen - 1) < \ num_of_ts_for_data, 'The data aumont is not enough.'

data_LSTM = pd.read_csv(path_data, header=None, delim_whitespace=False)
data_LSTM = data_LSTM.values

X_CNN = np.zeros([number_of_shape * num_of_ts, 120, 120, 1])
for i in range(number_of_shape):
    data_CNN = pd.read_csv(
        path_to_present_dir +
        '/data/LSTM/Flags/Flag' +
        '{0:03d}'.format(i + 1) + '.csv',
        header=None,
        delim_whitespace=False
    )
    data_CNN = data_CNN.values
    X_CNN[i * num_of_ts: (i + 1) * num_of_ts, :, :, 0] = data_CNN

X = np.zeros([number_of_shape * num_of_ts, maxlen, data_size])
Y = np.zeros([number_of_shape * num_of_ts, maxlen, data_size])

for i in range(number_of_shape):
    for j in range(num_of_ts):
        X[i * num_of_ts + j] = \
            data_LSTM[
                i * num_of_ts_for_data + j:
            i * num_of_ts_for_data + j +
            time_step * maxlen: time_step
        ]
        Y[i * num_of_ts + j] = \
            data_LSTM[
                i * num_of_ts_for_data + j + 1:
            i * num_of_ts_for_data + j +
            time_step * maxlen + 1: time_step
        ]

`

kazutotess commented 3 years ago

Hello NainaWay, and thank you for your question. I am sorry, but these are just sample codes, so I cannot shear some data to you.