I followed (copy/paste) the exact same code of wgan-gp_demo.ipynb with the same dataset as well, but I am getting worst result. Are you sure the code is updated? I'm getting RMSE:7.945424793070616 on testing dataset

Also, As you can see the trend of the prediction/actual seems much more similar to GAN or LSTM

Hello, I would like to ask you if the Class VAE() in your code is used to extract 10 features and add them to the original features? I look forward to hearing from you!

Hello, I would like to ask why the loss function of the generator in your paper is almost horizontal, can you explain it in detail? I look forward to your reply!

Main Problem

The following code produces the data leakage FFT feature.

close_fft = np.fft.fft(np.asarray(data_combine['Close'].tolist()))
fft_df = pd.DataFrame({'fft':close_fft})
fft_df['absolute'] = fft_df['fft'].apply(lambda x: np.abs(x))
fft_df['angle'] = fft_df['fft'].apply(lambda x: np.angle(x))

plt.figure(figsize=(14, 7), dpi=100)
fft_list = np.asarray(fft_df['fft'].tolist())
for num_ in [3, 6, 9, 27, 81, 100]:
    fft_list_m10= np.copy(fft_list); fft_list_m10[num_:-num_] = 0
    data_combine[f'FT_{num_}components'] = np.fft.ifft(fft_list_m10)
    plt.plot(np.fft.ifft(fft_list_m10), label='Fourier transform with {} components'.format(num_))
plt.plot(data_combine['Close'].values,  label='Real')

What goes wrong

• Generate the FFT from the whole time series.
• Use the future data to provide the previous FFT value.

What can happen

Even an MLP model can have a good result in predicting the next day's up/down trend.

Solution

To provide FFT feature without data leakage. You will need to generate it by each bar.

such as :

for i in range(1, len(df)):
    window = df[:i]['close']
    index_data.append(df.index[i])
    fft_close = np.fft.fft(window.values)
    absolute = np.abs(fft_close)
    angle = np.angle(absolute)
    ...

After this alteration, the model will perform very badly.

Hello, I would like to inquire about the code of HungChun Lin that is publicly available in your project.
In the WGAN-GP code
class GAN():
def train_step(self, data):
for _ in range(1):
for _ in range(3):
What do these two for loops represent?
Does a 1 inside the loop mean that there is only one variable to predict, and does a 3 mean that the sliding window is 3?
Looking forward to your reply, thanks.