How to do it...

Execute the following steps to train a 1D CNN in PyTorch.

  1. Import the libraries:
import yfinance as yfimport numpy as npimport osimport randomimport torchimport torch.optim as optimimport torch.nn as nnfrom import (Dataset, TensorDataset,                              DataLoader, Subset)from collections import OrderedDictfrom chapter_10_utils import create_input_data, custom_set_seedfrom sklearn.metrics import mean_squared_errordevice = 'cuda' if torch.cuda.is_available() else 'cpu'
  1. Define the parameters:
# dataTICKER = 'INTL'START_DATE = '2015-01-02'END_DATE = '2019-12-31'VALID_START = '2019-07-01'N_LAGS = 12# neural network BATCH_SIZE = 5N_EPOCHS = 2000
  1. Download and prepare the data:
df =,  start=START_DATE, ...

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

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.