archives/nhl-levenshtein
1
0
Fork 0
mirror of https://github.com/Wessel/nhl-levenshtein.git synced 2026-06-05 23:55:45 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: Replace microseconds with u to allow LaTeX to compile

Browse Source
This commit is contained in:
Wessel T
2025-03-23 19:30:20 +01:00
parent 7dd6124ef9
commit ca32488afa
16 changed files with 175 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
Report/main.tex
View File

@@ -1,4 +1,4 @@
\documentclass[9pt]{IEEEconf}
\documentclass{IEEEconf}
\input{packages.tex}
\input{variables.tex}
@@ -8,7 +8,7 @@
% \sffamily
% Front page containing title, author and date
\pagenumbering{gobble}
\input{sec/0 frontpage.tex}
\input{sec/0-frontpage.tex}
\newpage
% Set page numbering to arabic and show the table of contents, toc should not contain page number
@@ -21,18 +21,19 @@
\twocolumn
% Dictionary containing all the terms used in the document
\input{sec/0 dictionairy.tex}
\input{sec/0-dictionairy.tex}
\newpage
% Abstract of the document
\input{sec/0 abstract.tex}
\input{sec/0-abstract.tex}
% Sections of the document
\input{sec/1 introduction.tex}
\input{sec/2 theoretical framework.tex}
\input{sec/3 methodology.tex}
\input{sec/4 results.tex}
\input{sec/5 conclusion.tex}
\input{sec/1-introduction.tex}
% \cite{ebert2016cyclomatic}
\input{sec/2-theoretical-framework.tex}
\input{sec/3-methodology.tex}
\input{sec/4-results.tex}
\input{sec/5-conclusion.tex}
\section*{Acknowledgements}
\label{sec:acknowledgements}
@@ -45,8 +46,8 @@ The author would like to thank the following people for their contribution to th
\end{itemize}
\label{sec:referenties}
\bibliographystyle{IEEEtran}
\bibliography{references}
\nocite{*}
\input{sec/0 appendice.tex}
\input{sec/0-appendice.tex}
\end{document}

3
Report/packages.tex
View File

@@ -7,7 +7,7 @@
\usepackage{sectsty}
%/ Use case: text formatting
\usepackage{url}
\usepackage[newfloat,outputdir=tmp]{minted}
\usepackage[newfloat]{minted}
\usepackage[colorlinks=true, allcolors=teal]{hyperref}
\usepackage{textcomp}
\usepackage{amsmath}
@@ -30,3 +30,4 @@
\usepackage{algorithm}
\usepackage{algpseudocode}
\usepackage{amsmath}
\usepackage{cite}

BIN
Report/report-v1.pdf Normal file
View File

Binary file not shown.

23
Report/sec/0 dictionairy.tex
View File

@@ -1,23 +0,0 @@
\onecolumn
% todo(wessel)
\section*{Dictionairy}
\begin{table}[ht]
\raggedright
\begin{threeparttable}
\begin{tabular}{p{4cm}|p{11.5cm}}
\toprule
\textbf{Term} & \textbf{Meaning} \\
\hline
ns & Nanoseconds, a unit of time equal to one billionth of a second. \\
ms & Milliseconds, a unit of time equal to one thousandth of a second. \\
Programming Paradigm & A style of programming, such as imperative, declarative, or functional. \\
Imperative & A programming paradigm that uses statements to change a program's state. \\
Functional & A programming paradigm that treats computation as the evaluation of mathematical functions. \\
Semi-Functional & A programming paradigm that uses functional programming concepts in an imperative language. \\
Mutable & A variable that can be changed after it has been declared. \\
Immutable & A variable that cannot be changed after it has been declared. \\
\bottomrule
\end{tabular}
\end{threeparttable}
\end{table}
\twocolumn

0
Report/sec/0 abstract.tex → Report/sec/0-abstract.tex
View File

10
Report/sec/0 appendice.tex → Report/sec/0-appendice.tex
View File

@@ -89,19 +89,19 @@
benchmarking levenshteinRatio - short different strings
time 966.6 ns (953.2 ns .. 985.3 ns)
0.996 R² (0.991 R² .. 0.999 R²)
mean 992.3 ns (970.7 ns .. 1.036 μs)
mean 992.3 ns (970.7 ns .. 1.036 us)
std dev 97.98 ns (50.78 ns .. 187.7 ns)
benchmarking levenshteinRatio - short similar strings
time 2.410 μs (2.386 μs .. 2.436 μs)
time 2.410 us (2.386 us .. 2.436 us)
0.999 R² (0.999 R² .. 1.000 R²)
mean 2.391 μs (2.374 μs .. 2.417 μs)
mean 2.391 us (2.374 us .. 2.417 us)
std dev 69.63 ns (50.30 ns .. 104.4 ns)
benchmarking levenshteinRatio - long identical strings
time 3.786 μs (3.765 μs .. 3.815 μs)
time 3.786 us (3.765 us .. 3.815 us)
1.000 R² (0.999 R² .. 1.000 R²)
mean 3.815 μs (3.795 μs .. 3.842 μs)
mean 3.815 us (3.795 us .. 3.842 us)
std dev 79.62 ns (63.85 ns .. 103.2 ns)
benchmarking levenshteinRatio - long different strings

24
Report/sec/0-dictionairy.tex Normal file
View File

@@ -0,0 +1,24 @@
\onecolumn
% todo(wessel)
\section*{Dictionairy}
\begin{table}[ht]
\raggedright
\begin{threeparttable}
\begin{tabular}{p{4cm}|p{11.5cm}}
\toprule
\textbf{Term} & \textbf{Meaning} \\
\hline
ms & Milliseconds, one thousandth of a second. \\
us & Microseconds, one millionth of a second. \\
ns & Nanoseconds, one billionth of a second. \\
Programming Paradigm & A style of programming. \\
Imperative & A programming paradigm that uses statements to change a program's state. \\
Functional & A programming paradigm that treats programming as mathematical functions. \\
Semi-Functional & A mix between functional and imperative programming. \\
Mutable & A variable that can be changed. \\
Immutable & A variable that cannot be changed. \\
\bottomrule
\end{tabular}
\end{threeparttable}
\end{table}
\twocolumn

0
Report/sec/0 frontpage.tex → Report/sec/0-frontpage.tex
View File

0
Report/sec/1 introduction.tex → Report/sec/1-introduction.tex
View File

91
Report/sec/2 theoretical framework.tex
View File

@@ -1,91 +0,0 @@
\section{Theoretical Framework}
\subsection{Functional Programming}
\label{ssec:fp}
Functional programming is one of four programming paradigms that treats computation as mathematical
functions where all data is immmutable.\cite{hudak1989conception} This makes functional programming
declarative. The program specifies what it should do, rather than how it should do it.
Functional programming is based on the concept of pure functions, which are functions
that have no side effects and always return the same output for the same input.
\subsubsection*{Haskell}
Haskell (or HS) is a functional programming language that is based on the lambda calculus.\cite{hutton2016programming}
Haskell is a pure functional language, which means that all functions in Haskell are pure functions.
It is also a lazy language, meaning that expressions are only ran when their values are needed.
\subsection{Imperative Programming}
Imperative programming is one of the four programming paradigms that uses statements to change
the state of a program. In imperative programming, the program is a sequence of statements that
are executed in order.\cite{syme2007introducing}
The state of the program is determined by mutable variables. Imperative programming is the
complete opposite of functional programming mentioned in \autoref{ssec:fp},
promoting the use of mutable variables.
The mutable nature of imperaetive programming makes it difficult to reason the behavior of
a function, as the state of the program can change at any time.
\subsubsection*{CSharp}
C\# (or CSharp) is an object-oriented programming language that supports imperative programming.
C\# is widely used for developing Windows applications, web applications, and games.
\subsection{The Levenshtein Distance Algorithm}
\label{ssec:t-levenshtein}
The Levenshtein Distance algorithm is an algorithm used to calculate the similarity between two
pieces of text. This is done by calculating the minimum number of single-character edits
(insertions, deletions, or substitutions) required to change one string into another.\cite{po2020similarity}
The result of the Levenshtein Distance algorithm is a value between zero and one
that represents the number of edits required to change one string into another.
This number is called the \textit{Levenshtein Ratio}.
The pseudocode for the Levenshtein Distance algorithm with a complexity of $O(m \times n)$
is shown in \autoref{alg:levenshtein}.
\begin{algorithm}
\small
\caption{Levenshtein Distance Algorithm\cite{po2020similarity}}
\label{alg:levenshtein}
\begin{algorithmic}[1]
\Function{LevenshteinDistance}{$s, t$}
\State $n \gets$ length of $s$.
\State $m \gets$ length of $t$.
\If{$n = 0$}
\State \Return $m$
\EndIf
\If{$m = 0$}
\State \Return $n$
\EndIf
\State Create matrix $d$ of size $0..m \times 0..n$.
\State Initialize first row to $0..n$.
\State Initialize first column to $0..m$.
\State Examine each character of $s$ (i from $1$ to $n$).
\State Examine each character of $t$ (j from $1$ to $m$).
\If{$s[i] = t[j]$}
\State $c \gets 0$
\Else
\State $c \gets 1$
\EndIf
\State $d[i,j] \gets \min(
\begin{cases}
\text{Cell above} = [i,j-1] + 1 \\
\text{Cell left} = [di,j-1] + 1 \\
\text{Cell diagonal} = d[i-1,j-1] + c
\end{cases}
)$
\State \Return $d[n,m]$.
\EndFunction
\end{algorithmic}
\end{algorithm}

91
Report/sec/2-theoretical-framework.tex Normal file
View File

@@ -0,0 +1,91 @@
\section{Theoretical Framework}
\subsection{Functional Programming}
\label{ssec:fp}
Functional programming is one of four programming paradigms that treats computation as mathematical
functions where all data is immmutable.\cite{hudak1989conception} This makes functional programming
declarative. The program specifies what it should do, rather than how it should do it.
Functional programming is based on the concept of pure functions, which are functions
that have no side effects and always return the same output for the same input.
\subsubsection*{Haskell}
Haskell (or HS) is a functional programming language that is based on the lambda calculus.\cite{hutton2016programming}
Haskell is a pure functional language, which means that all functions in Haskell are pure functions.
It is also a lazy language, meaning that expressions are only ran when their values are needed.
\subsection{Imperative Programming}
Imperative programming is one of the four programming paradigms that uses statements to change
the state of a program. In imperative programming, the program is a sequence of statements that
are executed in order.\cite{syme2007introducing}
The state of the program is determined by mutable variables. Imperative programming is the
complete opposite of functional programming mentioned in \autoref{ssec:fp},
promoting the use of mutable variables.
The mutable nature of imperaetive programming makes it difficult to reason the behavior of
a function, as the state of the program can change at any time.
\subsubsection*{CSharp}
C\# (or CSharp) is an object-oriented programming language that supports imperative programming.
C\# is widely used for developing Windows applications, web applications, and games.
\subsection{The Levenshtein Distance Algorithm}
\label{ssec:t-levenshtein}
The Levenshtein Distance algorithm is an algorithm used to calculate the similarity between two
pieces of text. This is done by calculating the minimum number of single-character edits
(insertions, deletions, or substitutions) required to change one string into another.\cite{po2020similarity}
The result of the Levenshtein Distance algorithm is a value between zero and one
that represents the number of edits required to change one string into another.
This number is called the \textit{Levenshtein Ratio}.
The pseudocode for the Levenshtein Distance algorithm with a complexity of $O(m \times n)$
is shown in \autoref{alg:levenshtein}.
\begin{algorithm}
\small
\caption{Levenshtein Distance Algorithm\cite{po2020similarity}}
\label{alg:levenshtein}
\begin{algorithmic}[1]
\Function{LevenshteinDistance}{$s, t$}
\State $n \gets$ length of $s$.
\State $m \gets$ length of $t$.
\If{$n = 0$}
\State \Return $m$
\EndIf
\If{$m = 0$}
\State \Return $n$
\EndIf
\State Create matrix $d$ of size $0..m \times 0..n$.
\State Initialize first row to $0..n$.
\State Initialize first column to $0..m$.
\State Examine each character of $s$ (i from $1$ to $n$).
\State Examine each character of $t$ (j from $1$ to $m$).
\If{$s[i] = t[j]$}
\State $c \gets 0$
\Else
\State $c \gets 1$
\EndIf
\State $d[i,j] \gets \min(
\begin{cases}
\text{Cell above} = [i,j-1] + 1 \\
\text{Cell left} = [di,j-1] + 1 \\
\text{Cell diagonal} = d[i-1,j-1] + c
\end{cases}
)$
\State \Return $d[n,m]$.
\EndFunction
\end{algorithmic}
\end{algorithm}

0
Report/sec/3 methodology.tex → Report/sec/3-methodology.tex
View File

0
Report/sec/4 results.tex → Report/sec/4-results.tex
View File

0
Report/sec/5 conclusion.tex → Report/sec/5-conclusion.tex
View File

4
Report/variables.tex
View File

@@ -20,7 +20,7 @@ Year 3, Semester 2 (Jan. 2025 - Jun. 2025)}
\oldstylenums{\arabic{FancyVerbLine}}}}
% Sets the bibliography style to IEEE
\bibliographystyle{IEEEtran}
% \bibliographystyle{IEEEtran}
% Disables the no citations error
\nocite{*}
% \nocite{*}

38
process-track-name.sh Executable file
View File

@@ -0,0 +1,38 @@
#!/bin/bash
if [ -z "$1" ]; then
echo "Usage: $0 <program_name>"
exit 1
fi
PROGRAM_NAME=$1
OUTPUT_FILE="process_stats.log"
touch $OUTPUT_FILE
echo "DATE TIME %CPU %MEM CMD" >> $OUTPUT_FILE
while true; do
PIDS=$(pgrep -x $PROGRAM_NAME | grep -v $$ | grep -v $(pgrep -x pgrep))
if [ -n "$PIDS" ]; then
# Get the first PID found
PID=$(echo $PIDS | awk '{print $1}')
echo "Found process $PROGRAM_NAME with PID $PID"
# Track the found process
while kill -0 $PID 2>/dev/null; do
TIMESTAMP=$(date "+%Y-%m-%d %H:%M:%S")
echo -n "$TIMESTAMP " >> $OUTPUT_FILE
ps -p $PID -o %cpu,%mem,cmd --no-headers >> $OUTPUT_FILE
sleep 0.1
done
echo "Process $PROGRAM_NAME with PID $PID has terminated"
exit 0
fi
sleep 0.1
done