We Keep Coding

Why is bubble sort running faster than selection sort?

I am working on a project that compares the time bubble and selection sort take. I made two separate programs and combined them into one and now bubble sort is running much faster than selection sort. I checked to make sure that the code wasn't just giving me 0s because of some conversion error and was running as intended. I am using System.Diagnostics; to measure the time. I also checked that the machine was not the problem, I ran it on Replit and got similar results.
{
class Program
{
public static int s1 = 0;
public static int s2 = 0;
static decimal bubblesort(int[] arr1)
{
int n = arr1.Length;
var sw1 = Stopwatch.StartNew();
for (int i = 0; i < n - 1; i++)
{
for (int j = 0; j < n - i - 1; j++)
{
if (arr1[j] > arr1[j + 1])
{
int tmp = arr1[j];
// swap tmp and arr[i] int tmp = arr[j];
arr1[j] = arr1[j + 1];
arr1[j + 1] = tmp;
s1++;
}
}
}
sw1.Stop();
// Console.WriteLine(sw1.ElapsedMilliseconds);
decimal a = Convert.ToDecimal(sw1.ElapsedMilliseconds);
return a;
}
static decimal selectionsort(int[] arr2)
{
int n = arr2.Length;
var sw1 = Stopwatch.StartNew();
// for (int e = 0; e < 1000; e++)
// {
for (int x = 0; x < arr2.Length - 1; x++)
{
int minPos = x;
for (int y = x + 1; y < arr2.Length; y++)
{
if (arr2[y] < arr2[minPos])
minPos = y;
}
if (x != minPos && minPos < arr2.Length)
{
int temp = arr2[minPos];
arr2[minPos] = arr2[x];
arr2[x] = temp;
s2++;
}
}
// }
sw1.Stop();
// Console.WriteLine(sw1.ElapsedMilliseconds);
decimal a = Convert.ToDecimal(sw1.ElapsedMilliseconds);
return a;
}
static void Main(string[] args)
{
Console.WriteLine("Enter the size of n");
int n = Convert.ToInt32(Console.ReadLine());
Random rnd = new System.Random();
decimal bs = 0M;
decimal ss = 0M;
int s = 0;
int[] arr1 = new int[n];
int tx = 1000; //tx is a variable that I can use to adjust sample size
decimal tm = Convert.ToDecimal(tx);
for (int i = 0; i < tx; i++)
{
for (int a = 0; a < n; a++)
{
arr1[a] = rnd.Next(0, 1000000);
}
ss += selectionsort(arr1);
bs += bubblesort(arr1);
}
bs = bs / tm;
ss = ss / tm;
Console.WriteLine("Bubble Sort took " + bs + " miliseconds");
Console.WriteLine("Selection Sort took " + ss + " miliseconds");
}
}
}
What is going on? What is causing bubble sort to be fast or what is slowing down Selection sort? How can I fix this?
I found that the problem was that the Selection Sort was looping 1000 times per method run in addition to the 1000 runs for sample size, causing the method to perform significantly worse than bubble sort. Thank you guys for help and thank you TheGeneral for showing me the benchmarking tools. Also, the array that was given as a parameter was a copy instead of a reference, as running through the loop manually showed me that the bubble sort was doing it's job and not sorting an already sorted array.

To solve your initial problem you just need to copy your arrays, you can do this easily with ToArray():
Creates an array from a IEnumerable.
ss += selectionsort(arr1.ToArray());
bs += bubblesort(arr1.ToArray());
However let's learn how to do a more reliable benchmark with BenchmarkDotNet:
BenchmarkDotNet Nuget
Official Documentation
Given
public class Sort
{
public static void BubbleSort(int[] arr1)
{
int n = arr1.Length;
for (int i = 0; i < n - 1; i++)
{
for (int j = 0; j < n - i - 1; j++)
{
if (arr1[j] > arr1[j + 1])
{
int tmp = arr1[j];
// swap tmp and arr[i] int tmp = arr[j];
arr1[j] = arr1[j + 1];
arr1[j + 1] = tmp;
}
}
}
}
public static void SelectionSort(int[] arr2)
{
int n = arr2.Length;
for (int x = 0; x < arr2.Length - 1; x++)
{
int minPos = x;
for (int y = x + 1; y < arr2.Length; y++)
{
if (arr2[y] < arr2[minPos])
minPos = y;
}
if (x != minPos && minPos < arr2.Length)
{
int temp = arr2[minPos];
arr2[minPos] = arr2[x];
arr2[x] = temp;
}
}
}
}
Benchmark code
[SimpleJob(RuntimeMoniker.Net50)]
[MemoryDiagnoser()]
public class SortBenchmark
{
private int[] data;
[Params(100, 1000)]
public int N;
[GlobalSetup]
public void Setup()
{
var r = new Random(42);
data = Enumerable
.Repeat(0, N)
.Select(i => r.Next(0, N))
.ToArray();
}
[Benchmark]
public void Bubble() => Sort.BubbleSort(data.ToArray());
[Benchmark]
public void Selection() => Sort.SelectionSort(data.ToArray());
}
Usage
static void Main(string[] args)
{
BenchmarkRunner.Run<SortBenchmark>();
}
Results
Method
N
Mean
Error
StdDev
Bubble
100
8.553 us
0.0753 us
0.0704 us
Selection
100
4.757 us
0.0247 us
0.0231 us
Bubble
1000
657.760 us
7.2581 us
6.7893 us
Selection
1000
300.395 us
2.3302 us
2.1796 us
Summary
What have we learnt? Your bubble sort code is slower ¯\_(ツ)_/¯

It looks like you're passing in the sorted array into Bubble Sort. Because arrays are passed by reference, the sort that you're doing on the array is editing the same contents of the array that will be eventually passed into bubble sort.
Make a second array and pass the second array into bubble sort.

2d_array random numbers (10Rows, 6 COLS) not repeated to file C#

I need to streamwrite into a file.txt a 10 random numbers combinations (NOT REPEATED) like lottery program. I got everything except Non-repeated random numbers. it has to be seen (file.txt) like a 2D array with 10 combinations thx.
class Matriz
{
private int[,] array;
private int nfilas, ncols;
public void Ingresar()
{
Random aleatori = new Random();
nfilas = 10;
ncols = 6;
Console.WriteLine("\n");
array = new int[nfilas, ncols];
for (int filas = 0; filas < nfilas; filas++)
{
for (int columnas = 0; columnas < ncols; columnas++)
array[filas, columnas] = aleatori.Next(0, 50);
}
}
public void Imprimir()
{
StreamWriter fitxer = new StreamWriter(#"C:\andres\lotto649.txt");
int contador = 0;
for (int f = 0; f < nfilas; f++)
{
for (int c = 0; c < ncols; c++)
fitxer.Write(array[f, c] + " ");
fitxer.WriteLine();
contador++;
}
fitxer.WriteLine($"\n\n\tHay {contador} combinaciones de la Loteria 6/49");
fitxer.Close();
}
static void Main(string[] args)
{
Matriz array_menu = new Matriz();
array_menu.Ingresar();
array_menu.Imprimir();
}
}

Something like this should work.
Before inserting the new number in the given position, check the row thus far if the same number is already in there and if so, repeat the process until you get a number that isn't yet in there.
for (int filas = 0; filas < nfilas; filas++)
{
for (int columnas = 0; columnas < ncols; columnas++)
{
bool cont = true;
while(cont)
{
cont = false;
int newRand = aleatori.Next(0, 50);
for(int i = 0; i < columnas; i++)
if(array[filas, i] == newRand)
cont = true;
if(cont)
continue;
array[filas, columnas] = newRand;
break;
}
}
}
Alternatively, since the number is small you could also work with a list of ints and remove the given value from there.
This has the advantage, that you'll never have to redo your random number as it will always produce a valid result. The above example could (theoretically) run indefinitely long.
for (int filas = 0; filas < nfilas; filas++)
{
List<int> nums = new List<int>(49);
for(int i = 0; i < 49; i++)
nums.Add(i + 1); //num 1...49
for (int columnas = 0; columnas < ncols; columnas++)
{
int index = aleatori.Next(0, nums.Count)
array[filas, columnas] = nums[index];
nums.RemoveAt(index);
}
}

Index Of Longest Run C#

I am trying to solve this question:
Write a function that finds the zero-based index of the longest run in a string. A run is a consecutive sequence of the same character. If there is more than one run with the same length, return the index of the first one.
For example, IndexOfLongestRun("abbcccddddcccbba") should return 6 as the longest run is dddd and it first appears on index 6.
Following what i have done:
private static int IndexOfLongestRun(string str)
{
char[] array1 = str.ToCharArray();
//Array.Sort(array1);
Comparer comparer = new Comparer();
int counter =1;
int maxCount = 0;
int idenxOf = 0;
for (int i =0; i<array1.Length-1 ; i++)
{
if (comparer.Compare(array1[i],array1[i+1]) == 0)
{
counter++;
}
else {
if(maxCount < counter)
{
maxCount = counter;
idenxOf = i - counter + 1;
}
counter = 1;
}
}
return idenxOf ;
}
}
public class Comparer : IComparer<char>
{
public int Compare(char firstChar, char nextChar)
{
return firstChar.CompareTo(nextChar);
}
}
The problem is that when i get to the last index for example "abbccaaaaaaaaaa"
which is a in this case, and when i=14 (taking this string as example) and when i<array1.Length-1 statment is false, the for loop jumps directrly to return indexOf; and return the wrong index, I am trying to find out how to push the forloop to continue the implementation so idenxOf could be changed to the right index. Any help please?

You could check whether a new best score is achieved for each iteration when current == previous. Minimally slower, but it allows you to write shorter code by omitting an extra check after the loop:
int IndexOfLongestRun(string input)
{
int bestIndex = 0, bestScore = 0, currIndex = 0;
for (var i = 0; i < input.Length; ++i)
{
if (input[i] == input[currIndex])
{
if (bestScore < i - currIndex)
{
bestIndex = currIndex;
bestScore = i - currIndex;
}
}
else
{
currIndex = i;
}
}
return bestIndex;
}

Promote the loop variable i to method scope and repeat the conditional block if (maxCount < counter) { ... } right after the loop exit. Thus, it executes one more time after the loop completes
private static int IndexOfLongestRun(string str)
{
char[] array1 = str.ToCharArray();
//Array.Sort(array1);
Comparer comparer = new Comparer();
int counter = 1;
int maxCount = 0;
int idenxOf = 0;
int i;
for (i = 0; i < array1.Length - 1; i++)
{
if (comparer.Compare(array1[i], array1[i + 1]) == 0)
{
counter++;
}
else
{
if (maxCount < counter)
{
maxCount = counter;
idenxOf = i - counter + 1;
}
counter = 1;
}
}
if (maxCount < counter)
{
maxCount = counter;
idenxOf = i - counter + 1;
}
return idenxOf;
}

As usual late, but joining the party. A natural classic algorithm:
static int IndexOfLongestRun(string input)
{
int longestRunStart = -1, longestRunLength = 0;
for (int i = 0; i < input.Length; )
{
var runValue = input[i];
int runStart = i;
while (++i < input.Length && input[i] == runValue) { }
int runLength = i - runStart;
if (longestRunLength < runLength)
{
longestRunStart = runStart;
longestRunLength = runLength;
}
}
return longestRunStart;
}
At the end you have both longest run index and length.

public static int IndexOfLongestRun(string str)
{
var longestRunCount = 1;
var longestRunIndex = 0;
var isNew = false;
var dic = new Dictionary<int, int>();
for (var i = 0; i < str.Length - 1; i++)
{
if (str[i] == str[i + 1])
{
if (isNew) longestRunIndex = i;
longestRunCount++;
isNew = false;
}
else
{
isNew = true;
dic.Add(longestRunIndex, longestRunCount);
longestRunIndex = 0;
longestRunCount = 1;
}
}
return dic.OrderByDescending(x => x.Value).First().Key;
}

This will return -1 if the string is empty and you have the flexibility of returning the index and the count depending on your specification.
string myStr = "aaaabbbbccccccccccccdeeeeeeeee";
var longestIndexStart = -1;
var longestCount = 0;
var currentCount = 1;
var currentIndexStart = 0;
for (var idx = 1; idx < myStr.Length; idx++)
{
if (myStr[idx] == myStr[currentIndexStart])
currentCount++;
else
{
if (currentCount > longestCount)
{
longestIndexStart = currentIndexStart;
longestCount = currentCount;
}
currentIndexStart = idx;
currentCount = 1;
}
}
return longestIndexStart;

The accepted answer from Kvam works great for small strings, but as the length approaches 100,000 characters (and perhaps this isn't needed), its efficiency wains.
public static int IndexOfLongestRun(string str)
{
Dictionary<string, int> letterCount = new Dictionary<string, int>();
for (int i = 0; i < str.Length; i++)
{
string c = str.Substring(i, 1);
if (letterCount.ContainsKey(c))
letterCount[c]++;
else
letterCount.Add(c, 1);
}
return letterCount.Values.Max();
}
This solution is twice as fast as Kvam's with large strings. There are, perhaps, other optimizations.

fastest way to make an element in a list as the first element

I have list and I want a short and fast way to make one of its element as the first.
I have in mind to use the code below to select the 10th element and make it first. But looking for a better soln
tempList.Insert(0, tempList[10]);
tempList.RemoveAt(11);

if you don't mind the ordering of the rest, you actually could swap the two items at position 0 and 10, believe it's better than doing insertion and deletion:
var other = tempList[0];
tempList[0]=tempList[10];
tempList[10] = other;
and you can even make this an extension of List for ease of use, something like:
public static void Swap<T>(this List<T> list, int oldIndex, int newIndex)
{
// place the swap code here
}

There are some special cases when you could get better performance (for the sake of simplicity, I'm assuming that the value is always inserted before the position where it was taken from):
class Program
{
const int Loops = 10000;
const int TakeLoops = 10;
const int ItemsCount = 100000;
const int Multiplier = 500;
const int InsertAt = 0;
static void Main(string[] args)
{
var tempList = new List<int>();
var tempDict = new Dictionary<int, int>();
for (int i = 0; i < ItemsCount; i++)
{
tempList.Add(i);
tempDict.Add(i, i);
}
var limit = 0;
Stopwatch
sG = new Stopwatch(),
s1 = new Stopwatch(),
s2 = new Stopwatch();
TimeSpan
t1 = new TimeSpan(),
t2 = new TimeSpan();
for (int k = 0; k < TakeLoops; k++)
{
var takeFrom = k * Multiplier + InsertAt;
s1.Restart();
for (int i = 0; i < Loops; i++)
{
tempList.Insert(InsertAt, tempList[takeFrom]);
tempList.RemoveAt(takeFrom + 1);
}
s1.Stop();
t1 += s1.Elapsed;
s2.Restart();
for (int i = 0; i < Loops; i++)
{
var e = tempDict[takeFrom];
for (int j = takeFrom - InsertAt; j > InsertAt; j--)
{
tempDict[InsertAt + j] = tempDict[InsertAt + j - 1];
}
tempDict[InsertAt] = e;
}
s2.Stop();
t2 += s2.Elapsed;
if (s2.Elapsed > s1.Elapsed || limit == 0)
limit = takeFrom;
}
sG.Start();
for (int k = 0; k < TakeLoops; k++)
{
var takeFrom = k * Multiplier + InsertAt;
if (takeFrom >= limit)
{
for (int i = 0; i < Loops; i++)
{
tempList.Insert(InsertAt, tempList[takeFrom]);
tempList.RemoveAt(takeFrom + 1);
}
}
else
{
for (int i = 0; i < Loops; i++)
{
var e = tempDict[takeFrom];
for (int j = takeFrom - InsertAt; j > InsertAt; j--)
{
tempDict[InsertAt + j] = tempDict[InsertAt + j - 1];
}
tempDict[InsertAt] = e;
}
}
}
sG.Stop();
Console.WriteLine("List: {0}", t1);
Console.WriteLine("Dictionary: {0}", t2);
Console.WriteLine("Optimized: {0}", sG.Elapsed);
/***************************
List: 00:00:11.9061505
Dictionary: 00:00:08.9502043
Optimized: 00:00:08.2504321
****************************/
}
}
In the example above, a Dictionary<int,int> is being used to store the index of each element. You will get better results if the gap between insertAt and takeFrom is smaller. As this interval increases, the performance will degrade. I guess you might want to evaluate this gap and take the optimal branch based on it's value.

Need to optimise counting positive and negative values

I need to optimise code that counts pos/neg values and remove non-qualified values by time.
I have queue of values with time-stamp attached.
I need to discard values which are 1ms old and count negative and positive values. here is pseudo code
list<val> l;
v = q.dequeue();
deleteold(l, v.time);
l.add(v);
negcount = l.count(i => i.value < 0);
poscount = l.count(i => i.value >= 0);
if(negcount == 10) return -1;
if(poscount == 10) return 1;
I need this code in c# working with max speed. No need to stick to the List. In fact arrays separated for neg and pos values are welcome.
edit: probably unsafe arrays will be the best. any hints?
EDIT: thanks for the heads up.. i quickly tested array version vs list (which i already have) and the list is faster: 35 vs 16 ms for 1 mil iterations...
Here is the code for fairness sake:
class Program
{
static int LEN = 10;
static int LEN1 = 9;
static void Main(string[] args)
{
Var[] data = GenerateData();
Stopwatch sw = new Stopwatch();
for (int i = 0; i < 30; i++)
{
sw.Reset();
ArraysMethod(data, sw);
Console.Write("Array: {0:0.0000}ms ", sw.ElapsedTicks / 10000.0);
sw.Reset();
ListMethod(data, sw);
Console.WriteLine("List: {0:0.0000}ms", sw.ElapsedTicks / 10000.0);
}
Console.ReadLine();
}
private static void ArraysMethod(Var[] data, Stopwatch sw)
{
int signal = 0;
int ni = 0, pi = 0;
Var[] n = new Var[LEN];
Var[] p = new Var[LEN];
for (int i = 0; i < LEN; i++)
{
n[i] = new Var();
p[i] = new Var();
}
sw.Start();
for (int i = 0; i < DATALEN; i++)
{
Var v = data[i];
if (v.val < 0)
{
int x = 0;
ni = 0;
// time is not sequential
for (int j = 0; j < LEN; j++)
{
long diff = v.time - n[j].time;
if (diff < 0)
diff = 0;
// too old
if (diff > 10000)
x = j;
else
ni++;
}
n[x] = v;
if (ni >= LEN1)
signal = -1;
}
else
{
int x = 0;
pi = 0;
// time is not sequential
for (int j = 0; j < LEN; j++)
{
long diff = v.time - p[j].time;
if (diff < 0)
diff = 0;
// too old
if (diff > 10000)
x = j;
else
pi++;
}
p[x] = v;
if (pi >= LEN1)
signal = 1;
}
}
sw.Stop();
}
private static void ListMethod(Var[] data, Stopwatch sw)
{
int signal = 0;
List<Var> d = new List<Var>();
sw.Start();
for (int i = 0; i < DATALEN; i++)
{
Var v = data[i];
d.Add(new Var() { time = v.time, val = v.val < 0 ? -1 : 1 });
// delete expired
for (int j = 0; j < d.Count; j++)
{
if (v.time - d[j].time < 10000)
d.RemoveAt(j--);
else
break;
}
int cnt = 0;
int k = d.Count;
for (int j = 0; j < k; j++)
{
cnt += d[j].val;
}
if ((cnt >= 0 ? cnt : -cnt) >= LEN)
signal = 9;
}
sw.Stop();
}
static int DATALEN = 1000000;
private static Var[] GenerateData()
{
Random r = new Random(DateTime.Now.Millisecond);
Var[] data = new Var[DATALEN];
Var prev = new Var() { val = 0, time = DateTime.Now.TimeOfDay.Ticks};
for (int i = 0; i < DATALEN; i++)
{
int x = r.Next(20);
data[i] = new Var() { val = x - 10, time = prev.time + x * 1000 };
}
return data;
}
class Var
{
public int val;
public long time;
}
}

To get negcount and poscount, you are traversing the entire list twice.
Instead, traverse it once (to compute negcount), and then poscount = l.Count - negcount.

Some ideas:
Only count until max(negcount,poscount) becomes 10, then quit (no need to count the rest). Only works if 10 is the maximum count.
Count negative and positive items in 1 go.
Calculate only negcount and infer poscount from count-negcount which is easier to do than counting them both.
Whether any of them are faster than what you have now, and which is fastest, depends among other things on what the data typically looks like. Is it long? Short?
Some more about 3:
You can use trickery to avoid branches here. You don't have to test whether the item is negative, you can add its negativity to a counter. Supposing the item is x and it is an int, x >> 31 is 0 for positive x and -1 for negative x. So counter -= x >> 31 will give negcount.
Edit: unsafe arrays can be faster, but shouldn't be in this case, because the loop would be of the form
for (int i = 0; i < array.Length; i++)
do something with array[i];
Which is optimized by the JIT compiler.