price = csvread('index.csv', 1, 0);
y=diff(log(price)); % calculate returns
plot(y) % plot returns
import numpy as np
import matplotlib.pyplot as plt
price = np.loadtxt('index.csv', delimiter = ',', skiprows = 1)
y = np.diff(np.log(price), n=1, axis=0)
plt.plot(y)
plt.show()
plt.close()
%% the function sacf uses Kevin Sheppard's MFE toolbox
%% download at https://www.kevinsheppard.com/MFE_Toolbox
mean(y)
std(y)
min(y)
max(y)
skewness(y)
kurtosis(y)
sacf(y,1,[],0)
sacf(y.^2,1,[],0)
[h,pValue,stat]=jbtest(y);
[h,pValue,stat]=lbqtest(y,'lags',20);
[h,pValue,stat]=lbqtest(y.^2,'lags',20);
%% NOTE: in MATLAB 2018a, some functions require name-value pairs
%% e.g. MATLAB 2016a: [h,pValue,stat] = lbqtest(y,20)
from scipy import stats
import statsmodels.api as sm
print (np.mean(y))
print (np.std(y, ddof=1))
print (np.min(y))
print (np.max(y))
print (stats.skew(y))
print (stats.kurtosis(y, fisher = False))
print (sm.tsa.stattools.acf(y, nlags=1))
print (sm.tsa.stattools.acf(np.square(y),nlags=1))
print (stats.jarque_bera(y))
from statsmodels.stats.diagnostic import acorr_ljungbox
print (acorr_ljungbox(y, lags=20))
print (acorr_ljungbox(np.square(y), lags=20))
%% subplots here are just for ease of visualization
subplot(1,2,1)
autocorr(y, 20)
subplot(1,2,2)
autocorr(y.^2, 20)
import statsmodels.api as sm
import matplotlib.pyplot as plt
q = sm.tsa.stattools.acf(y, nlags=20)
plt.bar(x = np.arange(1,len(q)), height = q[1:])
plt.show()
plt.close()
q = sm.tsa.stattools.acf(np.square(y), nlags=20)
plt.bar(x = np.arange(1,len(q)), height = q[1:])
plt.show()
plt.close()
%% subplots here are just for ease of visualization
subplot(1,2,1)
qqplot(y)
subplot(1,2,2)
qqplot(y, fitdist(y,'tLocationScale'))
from statsmodels.graphics.gofplots import qqplot
fig1 = qqplot(y, line='q', dist = stats.norm, fit = True)
plt.show()
plt.close()
fig2 = qqplot(y, line='q', dist = stats.t, distargs=(5,), fit = True)
plt.show()
plt.close()
price = csvread('stocks.csv', 1, 0);
y=diff(log(price));
corr(y) % correlation matrix
import numpy as np
p = np.loadtxt('stocks.csv',delimiter=',',skiprows = 1)
y = np.diff(np.log(p), n=1, axis=0)
np.corrcoef(y, rowvar=False) # correlation matrix
## rowvar=False indicates that columns are variables