How to do it...

Execute the following steps to train an RNN for a time series prediction problem.

  1. Import the libraries:
import yfinance as yfimport numpy as npimport torchimport torch.optim as optimimport torch.nn as nnfrom torch.utils.data import (Dataset, TensorDataset,                              DataLoader, Subset)from chapter_10_utils import create_input_data, custom_set_seedfrom sklearn.metrics import mean_squared_errorfrom sklearn.preprocessing import MinMaxScalerdevice = 'cuda' if torch.cuda.is_available() else 'cpu'
  1. Define the parameters:
# dataTICKER = 'INTL'START_DATE = '2010-01-02'END_DATE = '2019-12-31'VALID_START = '2019-07-01'N_LAGS = 12# neural network BATCH_SIZE = 16N_EPOCHS = 100
  1. Download and prepare the data:
df = yf.download(TICKER,  start=START_DATE, ...

Get Python for Finance Cookbook now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.