Univariate Time Series With Stacked LSTM, BiLSTM and NeuralProphet
This notebook has been specifically created for an article that focuses on univariate time series analysis.
The article delves into the development of Deep Learning models, particularly LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), and NeuralProphet models. These models are designed for the multi-step forecasting of stock prices, offering insights into how these sophisticated techniques can be applied in the financial domain.
The content of this notebook is a practical extension of the theoretical concepts discussed in the article. It provides a detailed exploration of Stacked LSTM, BiLSTM, and NeuralProphet models, demonstrating their application in univariate time series forecasting. The notebook serves as a comprehensive guide for those interested in understanding and implementing these advanced deep learning models in the context of stock price prediction.
import numpy as np
import pandas as pd
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
%matplotlib inline
from matplotlib.pylab import rcParams
from datetime import datetime
import warnings
from pylab import rcParams
from sklearn.model_selection import train_test_split as split
import warnings
import itertools
warnings.filterwarnings("ignore")
from fbprophet import Prophet
from IPython import display
from matplotlib import pyplot
import os
import re
import seaborn as sns
import plotly.express as px
import warnings
from matplotlib.patches import Patch
This code uses various imports to set up the environment for a data analysis machine learning project. It imports libraries such as NumPy, pas, scikit-learn, also customizes plot properties displays plots inline. The code also sets configurations to ignore warnings imports modules for working with dates, looping, data visualization. This set of imports is typically used at the start of a data science project.