Hacker’s Guide to Machine Learning with Python by Venelin Valkov

Author:Venelin Valkov [Venelin Valkov]
Language: eng
Format: epub, mobi
Publisher: leanpub.com
Published: 2019-10-25T00:00:00+00:00

We use isnan as a mask to filter out NaN values. Again we reshape the data after removing the NaNs.

Making sequences

LSTMs expect the data to be in 3 dimensions. We need to split the data into sequences of some preset length. The shape we want to obtain is:

1 [batch_size, sequence_length, n_features]

We also want to save some data for testing. Let’s build some sequences:

1 SEQ_LEN = 100 2 3 def to_sequences(data, seq_len): 4 d = [] 5 6 for index in range(len(data) - seq_len): 7 d.append(data[index: index + seq_len]) 8 9 return np.array(d) 10 11 def preprocess(data_raw, seq_len, train_split): 12 13 data = to_sequences(data_raw, seq_len) 14 15 num_train = int(train_split * data.shape[0]) 16 17 X_train = data[:num_train, :-1, :] 18 y_train = data[:num_train, -1, :] 19 20 X_test = data[num_train:, :-1, :] 21 y_test = data[num_train:, -1, :] 22 23 return X_train, y_train, X_test, y_test 24 25 26 X_train, y_train, X_test, y_test =\ 27 preprocess(scaled_close, SEQ_LEN, train_split = 0.95)

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.