Appendix - Introduction (in R/Python)


Copyright 2011 - 2019 Jon Danielsson. This code is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This code is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. The GNU General Public License is available at: https://www.gnu.org/licenses/.


Listing R.1: Entering and Printing Data in R
Last updated June 2018

x = 10   # assign x the value 10
print(x) # print x
		
Listing P.1: Entering and Printing Data in Python
Last updated June 2018

x = 10   # assign x the value 10
print(x) # print the value of x
		

Listing R.2: Vectors, Matrices and Sequences in R
Last updated June 2018

y = c(1,3,5,7,9)                   # create vector using c()
print(y)
print(y[3])                        # calling 3rd element (R indices start at 1)
print(dim(y))                      # gives NULL since y is a vector, not a matrix
print(length(y))                   # as expected, y has length 5
v = matrix(nrow=2,ncol=3)          # fill a 2 x 3 matrix with NaN values (default)
print(dim(v))                      # as expected, v is size (2,3)
w = matrix(c(1,2,3),nrow=6,ncol=3) # repeats matrix twice by rows, thrice by columns
print(w)
s = 1:10                           # s is a list of integers from 1 to 10 inclusive
print(s)
		
Listing P.2: Vectors, Matrices and Sequences in Python
Last updated June 2018

y = [1,3,5,7,9]                        # lists in square brackets are stored as arrays
print(y)
print(y[2])                            # 3rd element (Python indices start at 0)
print(len(y))                          # as expected, y has length 5
import numpy as np
v = np.full([2,3], np.nan)             # create a 2x3 matrix with NaN values
print(v)
print(v.shape)                         # as expected, v is size (2,3)
w=np.tile(np.transpose([1,2,3]),(3,2)) # repeats twice by rows, thrice by columns
print(w)
s = range(10)                          # an iterator from 0 to 9
print([x for x in s])                  # return  elements using list comprehension
		

Listing R.3: Importing Data in R
Last updated June 2018

## There are many data sources for financial data, for instance
## Yahoo Finance, AlphaVantage and Quandl. However, some of the
## free data sources have numerous issues with accuracy and
## handling of missing data, so only CSV importing is shown here.
##
## For csv data, one can use read.csv to read it
##
## Example:
## data = read.csv('Ch1aprices.csv', header=TRUE, sep=',')
## one can use the zoo() function from the package zoo
## to turn the data into a timeseries (see Listing 1.1/1.2)
		
Listing P.3: Importing Data in Python
Last updated June 2018

## There are many data sources for financial data, for instance
## Yahoo Finance, AlphaVantage and Quandl. However, some of the
## free data sources have numerous issues with accuracy and
## handling of missing data, so only CSV importing is shown here.
##
## For csv data, one can use numpy.loadtxt() to read it
##
## Example:
## using numpy as np
## data = np.loadtxt('data.csv', delimiter = ',', skiprows = 1)
## skiprows=1 ensures that the header row is skipped
		

Listing R.4: Basic Summary Statistics in R
Last updated June 2018

y=matrix(c(3.1,4.15,9))
sum(y)                  # sum of all elements of y
prod(y)                 # product of all elements of y
max(y)                  # maximum value of y
min(y)                  # minimum value of y
range(y)                # min, max value of y
mean(y)                 # arithmetic mean
median(y)               # median
var(y)                  # variance
cov(y)                  # covar matrix = variance for single vector
cor(y)                  # corr matrix = [1] for single vector
sort(y)                 # sorting in ascending order
log(y)                  # natural log
		
Listing P.4: Basic Summary Statistics in Python
Last updated June 2018

import numpy as np
y = [3.14,15,9.26,5]
print(sum(y))         # sum of all elements of y
print(max(y))         # maximum value of y
print(min(y))         # minimum value of y
print(np.mean(y))     # arithmetic mean
print(np.median(y))   # median
print(np.var(y))      # variance
print(np.cov(y))      # covar matrix = variance for single vector
print(np.corrcoef(y)) # corr matrix = [1] for single vector
print(np.sort(y))     # sort in ascending order
print(np.log(y))      # natural log
		

Listing R.5: Calculating Moments in R
Last updated June 2018

library(moments)
mean(y)          # mean
var(y)           # variance
sd(y)            # unbiased standard deviation, by default
skewness(y)      # skewness
kurtosis(y)      # kurtosis
		
Listing P.5: Calculating Moments in Python
Last updated June 2018

import numpy as np
from scipy import stats
print(np.mean(y))                        # mean
print(np.var(y))                         # variance
print(np.std(y, ddof = 1))               # ddof = 1 for unbiased standard deviation
print(stats.skew(y))                     # skewness
print(stats.kurtosis(y, fisher = False)) # fisher = False gives Pearson definition
		

Listing R.6: Basic Matrix Operations in R
Last updated June 2018

z = matrix(c(1,2,3,4),2,2) # z is a 2 x 2 matrix
x = matrix(c(1,2),1,2)     # x is a 1 x 2 matrix
## Note: z * x is undefined since the two matrices are not conformable
z %*% t(x)                 # this evaluates to a 2 x 1 matrix
rbind(z,x)                 # "stacking" z and x vertically
cbind(z,t(x))              # "stacking z and x' horizontally
## Note: dimensions must match along the combining axis
		
Listing P.6: Basic Matrix Operations in Python
Last updated June 2018

import numpy as np
z = np.matrix([[1, 2], [3, 4]])                   # z is a 2 x 2 matrix
x = np.matrix([1, 2])                             # x is a 1 x 2 matrix
## Note: z * x is undefined since the two matrices are not conformable
print(z * np.transpose(x))                        # this evaluates to a 2 x 1 matrix
b = np.concatenate((z,x), axis = 0)               # "stacking" z and x vertically
print(b)
c = np.concatenate((z,np.transpose(x)), axis = 1) # "stacking" z and x horizontally
print(c)
## note: dimensions must match along the combining axis
		

Listing R.7: Statistical Distributions in R
Last updated June 2018

q = seq(from = -3, to = 3, length = 7)    # specify a set of values
p = seq(from = 0.1, to = 0.9, length = 9) # specify a set of probabilities
qnorm(p, mean = 0, sd = 1)                # element-wise inverse Normal quantile
pt(q, df = 4)                             # element-wise cdf under Student-t(4)
dchisq(q, df = 2)                         # element-wise pdf under Chisq(2)
## Similar syntax for other distributions
## q for quantile, p for cdf, d for pdf
## followed by the abbreviation of the distribution
## One can also obtain pseudorandom samples from distributions
x = rt(100, df = 5)                       # Sampling 100 times from TDist with 5 df
y = rnorm(50, mean = 0, sd = 1)           # Sampling 50 times from a standard normal
## Given data, we obtain MLE estimates of distribution parameters with package MASS:
library(MASS)
res = fitdistr(x, densfun = "normal")     # Fitting x to normal dist
print(res)
		
Listing P.7: Statistical Distributions in Python
Last updated June 2018

import numpy as np
from scipy import stats
q = np.arange(-3,4,1)                    # specify a set of values
p = np.arange(0.1,1.0,0.1)               # specify a set of probabilities
print(stats.norm.ppf(p))                 # element-wise inverse Normal quantile
print(stats.t.cdf(q,4))                  # element-wise cdf under Student-t(4)
print(stats.chi2.pdf(q,2))               # element-wise pdf under Chisq(2)
## One can also obtain pseudorandom samples from distributions using numpy.random
x = np.random.standard_t(df=5, size=100) # Sampling 100 times from TDist with 5 df
y = np.random.normal(size=50)            # Sampling 50 times from a standard normal
## Given data, we obtain MLE estimates of parameters with stats:
res = stats.norm.fit(x)                  # Fitting x to normal dist
print(res)
		

Listing R.8: Statistical Tests in R
Last updated June 2018

library(tseries)
x = rt(500, df = 5)                          # Create hypothetical dataset x
jarque.bera.test(x)                          # Jarque-Bera test for normality
Box.test(x, lag = 20, type = c("Ljung-Box")) # Ljung-Box test for serial correlation
		
Listing P.8: Statistical Tests in Python
Last updated June 2018

from scipy import stats
from statsmodels.stats.diagnostic import acorr_ljungbox
x = np.random.standard_t(df=5, size=500)                # Create dataset x
print(stats.jarque_bera(x))                             # Jarque-Bera test
print(acorr_ljungbox(x, lags=20))                       # Ljung-Box test
		

Listing R.9: Time Series in R
Last updated June 2018

x = rt(60, df = 5)         # Create hypothetical dataset x
par(mfrow=c(1,2), pty='s')
acf(x,20)                  # autocorrelation for lags 1:20
pacf(x,20)                 # partial autocorrelation for lags 1:20
		
Listing P.9: Time Series in Python
Last updated June 2018

import numpy as np
import statsmodels.api as sm
import matplotlib.pyplot as plt
y = np.random.standard_t(df = 5, size = 60)        # Create hypothetical dataset y
q1 = sm.tsa.stattools.acf(y, nlags=20)             # autocorrelation for lags 1:20
plt.bar(x = np.arange(1,len(q1)), height = q1[1:])
plt.show()
plt.close()
q2 = sm.tsa.stattools.pacf(y, nlags=20)            # partial autocorr for lags 1:20
plt.bar(x = np.arange(1,len(q2)), height = q2[1:])
plt.show()
plt.close()
		

Listing R.10: Loops and Functions in R
Last updated June 2018

## For loops
for (i in 3:7)                             # iterates through [3,4,5,6,7]
    print(i^2)
## If-else loops
X = 10
if (X %% 3 == 0) {
    print("X is a multiple of 3")
} else {
    print("X is not a multiple of 3")
}
## Functions (example: a simple excess kurtosis function)
excess_kurtosis = function(x, excess = 3){ # note: excess optional, default=3
    m4 = mean((x-mean(x))^4)
    excess_kurt = m4/(sd(x)^4) - excess
    excess_kurt
}
x = rt(60, df = 5)                         # Create hypothetical dataset x
excess_kurtosis(x)
		
Listing P.10: Loops and Functions in Python
Last updated June 2018

import numpy as np
## For loops
for i in range(3,8):                     # NOTE: range(start, end), end excluded
    print(i**2)                          # range(3,8) iterates through [3,4,5,6,7)
## If-else loops
X = 10
if X % 3 == 0:
    print("X is a multiple of 3")
else:
    print("X is not a multiple of 3")
## Functions (example: a simple excess kurtosis function)
def excess_kurtosis(x, excess = 3):      # note: excess optional, default = 3
    m4=np.mean((x-np.mean(x))**4)        # note: exponentiation in Python uses **
    excess_kurt=m4/(np.std(x)**4)-excess
    return excess_kurt
x = np.random.standard_t(df=5,size=60)   # Create hypothetical dataset x
print(excess_kurtosis(x))
		

Listing R.11: Basic Graphs in R
Last updated June 2018

y = rnorm(50, mean = 0, sd = 1)
par(mfrow=c(2,2))               # sets up space for subplots
barplot(y)                      # bar plot
plot(y,type='l')                # line plot
hist(y)                         # histogram
plot(y)                         # scatter plot
		
Listing P.11: Basic Graphs in Python
Last updated June 2018

import numpy as np
import matplotlib.pyplot as plt
y = np.random.normal(size = 50)
z = np.random.standard_t(df = 4, size = 50)
## using Matplotlib to plot bar, line, histogram and scatter plots
plt.subplot(2,2,1)
plt.bar(range(len(y)), y)
plt.subplot(2,2,2)
plt.plot(y)
plt.subplot(2,2,3)
plt.hist(y)
plt.subplot(2,2,4)
plt.scatter(y,z)
		

Listing R.12: Miscellaneous Useful Functions in R
Last updated June 2018

## Convert objects from one type to another with as.integer() etc
## To check type, use typeof(object)
x = 8.0
print(typeof(x))
x = as.integer(x)
print(typeof(x))
		
Listing P.12: Miscellaneous Useful Functions in Python
Last updated June 2018

## Convert objects from one type to another with int(), float() etc
## To check type, use type(object)
x = 8.0
print(type(x))
x = int(x)
print(type(x))