lm17

# Calculate the mean and standard deviation of the original dataset
mean_return <- mean(return_log)
sd_return <- sd(return_log)
# Rescale the predicted and original values
y_train_pred_rescaled <- y_train_pred_returns * sd_return + mean_return
y_test_pred_rescaled <- y_test_pred_returns * sd_return + mean_return
y_train_rescaled<-y_train * sd_return + mean_return
y_test_rescaled<-y_test * sd_return + mean_return
# Shift the predicted values to start from where the training data predictions end
shift <- length(y_train_pred_rescaled)
y_test_pred_shifted <- c(rep(NA, shift), y_test_pred_rescaled[,1])
# Plot the training and predicted values
options(repr.plot.width=12, repr.plot.height=8)
plot(return_log, type = "l", col = "green",main="LSTM-APPLE-RETURNS PREDICTION", xlab = "Day", ylab = "Returns",lwd=3)
lines(y_train_pred_rescaled, col = "blue",lwd=3)
lines(y_test_pred_shifted, col = "red",lwd=3)
legend(x = "topleft", legend = c("Original", "Train Predictions","Test-Prediction"), col = c("green","blue" ,"red"), lwd = 2)
grid()