# Importing libraries
import pandas as pd
import yfinance as yf
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import scipy.stats as scs
import statsmodels.api as sm
import statsmodels.tsa.api as smt

# Downloading MSFT data from yfinance from 1st January 2010 to 31st March 2020
msftStockData = yf.download( 'MSFT',
                        start = '2010-01-01',
                        end = '2020-03-31',
                        progress = False)

# Checking what's in there the dataframe by loading first 5 rows
msftStockData.head()

# Checking what's in there the dataframe by loading last 5 rows
msftStockData.tail()

# Calculating log returns and obtaining column to contain it
msftStockData['Log Returns'] = np.log(msftStockData['Adj Close']/msftStockData['Adj Close'].shift(1)) 

# Checking what's in there the dataframe by loading first 5 rows
msftStockData.head()

# Using back fill method to replace NaN values
msftStockData['Log Returns'] = msftStockData['Log Returns'].fillna(method = 'bfill')
msftStockData.head()

# Creating the acf plots for squared and absolute returns
fig, ax = plt.subplots(2, 1, figsize=(14, 10))

# Using statsmodels library to obtain acf plot for squared returns
smt.graphics.plot_acf(msftStockData['Log Returns'] ** 2, lags=35, alpha=0.05, ax = ax[0])

# Setting title, y-axis labels and x-axis labels of first subplot 
ax[0].set(title='Autocorrelation plots of sqaured log returns', ylabel='Squared Log Returns', xlabel='Lag')

# Obtaining acf plot of absolute returns using abs function of numpy library
smt.graphics.plot_acf(np.abs(msftStockData['Log Returns']), lags=35, alpha=0.05, ax = ax[1])

# Setting title, y-axis labels and x-axis labels of second subplot 
ax[1].set(title='Autocorrelation plots of absolute log returns', ylabel='Absolute Log Returns', xlabel='Lag')