PYTHON

python cointegration

import matplotlib.pyplot as plt
import yfinance as yf
import pandas as pd
import datetime as dt
import statsmodels.tsa.stattools as ts
from scipy.stats import linregress


def download_data(stock, start, end):
    stock_data = {}
    ticker = yf.download(stock, start, end)
    stock_data['Price'] = ticker['Adj Close']
    return pd.DataFrame(stock_data)


def plot_pairs(data1, data2):
    fig, (ax1, ax2) = plt.subplots(2)
    fig.suptitle('Pair Of Stocks')
    ax1.plot(data1)
    ax2.plot(data2)
    plt.show()


def scatter_plot(data1, data2):
    plt.scatter(data1.values, data2.values)
    plt.suptitle('Cointegration')
    plt.xlabel('XOM')
    plt.ylabel('CVX')
    plt.show()


if __name__ == '__main__':
    start_date = dt.datetime(2011, 4, 1)
    end_date = dt.datetime(2020, 1, 1)

    pair1 = download_data('XOM', start_date, end_date)
    pair2 = download_data('CVX', start_date, end_date)

    plot_pairs(pair1, pair2)
    scatter_plot(pair1, pair2)

    # Linear Regression
    result = linregress(pair1.values[:, 0], pair2.values[:, 0])
    print(result)

    # Create the residual series
    residuals = pair1 - result.slope * pair2

    adf = ts.adfuller(residuals)
    print(adf)