Last Updated on April 22, 2023 by mishou
Work in progress.
I. Retriveing the data
Let’s load the historical data of NASDAQ Composite, Dow Jones Industrial Average, and S&P 500 using yfinance and create a dictionary of the tickers and their corresponding data frames.
!pip install yfinanc
import yfinance as yf
import pandas as pd
import datetime
# set the start and end dates
start_date = '2022-01-03'
end_date = datetime.date.today().strftime('%Y-%m-%d')
# load the data and create a dictionary
# list the ticker symbols
ticker_ls = ["^IXIC", "^DJI", "^GSPC"]
# create a dictionary for each df
dic_df = {}
for ticker in ticker_ls:
dic_df[ticker] = yf.download(tickers = ticker, start = start_date, end = end_date, interval = "1d")
II. visualize missing values
Let’s create a heatmap for showing missing values.
# visualize missing values in yellow
import seaborn as sns
import matplotlib.pyplot as plt
plt.figure(figsize = (10, 7))
sns.set(font_scale = 1.4)
plt.tight_layout()
sns.heatmap(stocks.isnull(), yticklabels=False, cbar=False, cmap='viridis'
III. Moving averages and backtesting the strategies
You can learn the code for Hull Moving Averages and backtesting the strategies from the tutorial linked below:
Hull Moving Average (HMA) Using Python
You can see the code on Google Colaboratory:
https://colab.research.google.com/drive/13CdNzGbGIzA2DXRA3RjD2WnHnf5a6K89?usp=sharing
This is how to change tickers for creating charts on Google Colaboratory using Find and replace:
You can also learn from the following tutorial:
Reducing Lag in Data — The Hull Moving Average as a Trend Reversal Indicator
IV. Algorithmic trading
RNNs for Algorithmic Trading: Simplified Theory and Python Implementation