A dive into understanding the correlation between different stock tickers and crypto currencies.
Here's why:
- By understanding asset correlation I can better adjust my portfolio for future investements.
- Learn about Negative Correlation and it's meaning!
- Find the hidden insights of different company stocks and their values 🤔
This section should list any major frameworks/libraries used to bootstrap your project. Leave any add-ons/plugins for the acknowledgements section. Here are a few examples.
There are a couple of prerequisites that had to be installed for this project, outlined below.
1- We have to install packages
pip install matplotlib seaborn pandas - You may run into troubles with your pip version if it's not the last updated version.
- To update pip run the command below:
pip install pip --upgrade
2- Yahoo Finance API recently went through some changes with the pandas-datareader
- You might have to install data-reader through Conda CMD if you're using Jupyter through Anaconda like me
- In addition you might have to install the package in a cell on the notebook itself through:
!pip install pandas-datareader
To use the Yahoo Finance API directly you can use the following command
get_data_yahooThen you can implement the data you want to read from the API by feeding the Ticker and the sart and finishing time.
To get the price changes and ploting a visualization I used the following cell:
for ticker in tickers:
plt.plot(combined[ticker], label=ticker)
plt.legend(loc="upper right")
plt.show
You can than change the scaling to logarithmic to get a better visualization of the ticker changes
After getting the price differences I set an empty list in addition to a list of stocks or Crypto currencies I wanted to find the correlation in. You can use something like the code cell below:
for chip in chips:
data_chip = pdr.get_data_yahoo(chip, start, now)
if len(colnames_chip) == 0:
#Take the closest adjusted price and copy it
combined_chip = data_chip[['Adj Close']].copy()
else:
combined_chip = combined_chip.join(data_chip['Adj Close'])
#Append to the colnames to know which stock we already added
colnames_chip.append(chip)
combined_chip.columns = colnames_chipNext you can input the data in a combined list and visualize a seaborn heatmap, the result should look like below:
Arya Moghadddam - [email protected]
I used these resources to validate my findings and learn more about different aspects of asset correlation.