We Keep Coding

How can the rows of a list be divided into the largest possible parts (according to the row limit) and the most equal row packages?

RowLimit: 4
Example 1:
List with 10 rows
The desired result: 4, 3, 3
Example 2:
List with 9 rows
The desired result: 3, 3, 3
Example 3:
List with 8 rows
The desired result: 4, 4
Example 4:
List with 7 rows
The desired result: 4, 3
At the moment I simply divide the rows according to the rows limit
public List<List<string>> TextWithRowLimit(List<string> TextRows, int RowLimit)
{
List<List<string>> list = new List<List<string>>();
int RowLimitCounter = 1;
List<string> TextRowPackages = new List<string>();
for (int row = 0; row < TextRows.Count; ++row)
{
TextRowPackages.Add($"{TextRows[row]} ");
if (RowLimitCounter == RowLimit)
{
list.Add(TextRowPackages);
RowLimitCounter = 0;
TextRowPackages = new List<string>();
}
RowLimitCounter++;
}
if(TextRowPackages.Count>0)
list.Add(TextRowPackages);
return list;
}

Probably not the prettiest code, but I think this will work for you.
using System.Linq;
using System.Collections.Generic;
public class Program
{
public static void Main()
{
var initialList = Enumerable.Range(1, 10).Select(i => i.ToString()).ToList();
var limit = 4;
var bucketUtility = new BucketUtility();
var list = bucketUtility.TextWithRowLimit(initialList, limit);
}
}
public sealed class BucketUtility
{
public List<List<string>> TextWithRowLimit(List<string> textRows, int rowLimit)
{
var totalRowsCount = textRows.Count;
var remainder = textRows.Count % rowLimit;
var totalBucketsNeeded = remainder == 0 ? totalRowsCount / rowLimit : (totalRowsCount / rowLimit) + 1;
// calculate how many would fill buckets
var initialFillCount = totalBucketsNeeded * rowLimit;
// this can be negative
var remainingToFill = totalRowsCount - initialFillCount;
// size the buckets correctly
var buckets = SizeBuckets(totalBucketsNeeded, rowLimit, remainingToFill);
// assign text values to buckets
int skip = 0;
var result = buckets.Select((bucketSize, i) =>
{
var result = textRows.Select(t => t).Skip(skip).Take(bucketSize).ToList();
skip += bucketSize;
return result;
}).ToList();
return result;
}
private List<int> SizeBuckets(int totalBucketsNeeded, int rowLimit, int remainingToFill)
{
var totalBuckets = Enumerable.Range(0, totalBucketsNeeded).ToList();
var buckets = new List<int>();
for (int i = 0; i < totalBuckets.Count; i++)
{
int bucketSize = rowLimit;
if (remainingToFill > 0)
{
bucketSize++;
remainingToFill--;
}
if (remainingToFill < 0)
{
bucketSize--;
remainingToFill++;
}
buckets.Add(bucketSize);
}
// order them in correct order
return buckets.OrderByDescending(i => i).ToList();
}
}
Can run it here
https://dotnetfiddle.net/CxdHaO

C# LINQ - SkipWhile() in reverse, without calling Reverse()?

In this code:
for (e = 0; e <= collection.Count - 2; e++)
{
var itm = collection.Read()
var itm_price = itm.Price
var forwards_satisfied_row = collection
.Skip(e + 1)
.SkipWhile(x => x.Price < ex_price)
.FirstOrDefault();
var backwards_satisfied_row = collection
.Reverse()
.Skip(collection.Count - e)
.SkipWhile(x => x.Price < ex_price)
.FirstOrDefault();
}
Suppose the collection contains millions of items and a Reverse() is too expensive, what would be the best way to achieve the same outcome as 'backwards_satisfied_row' ?
Edit:
For each item in the collection, it should find the first preceding item that matches the SkipWhile predicate.
For context I'm finding the distance a price extrema (minima or maxima) is from a horizontal clash with the price. This gives a 'strength' value for each Minima and Maxima, which determines the importance of it, and to help marry it up with extremas of a similar strength.
Edit 2
This chart shows the data in the reproc code below, note the dip in the middle at item #22, this item has a distance of 18.
Bear in mind this operation will be iterated millions of times.
So I'm trying not to read into memory, and to only evaluate the items needed.
When I run this on a large dataset r_ex takes 5 ms per row, whereas l_ex takes up to a second.
It might be tempting to iterate backwards and check that way, but there could be millions of previous records, being read from a binary file.
Many types of searches like Binary search wouldn't be practical here, since the values aren't ordered.
static void Main(string[] args)
{
var dict_dists = new Dictionary<Int32, Int32>();
var dict = new Dictionary<Int32, decimal> {
{1, 410},{2, 474},{3, 431},
{4, 503},{5, 461},{6, 535},
{7, 488},{8, 562},{9, 508},
{10, 582},{11, 522},{12, 593},
{13, 529},{14, 597},{15, 529},
{16, 593},{17, 522},{18, 582},
{19, 510},{20, 565},{21, 492},
{22, 544},{23, 483},{24, 557},
{25, 506},{26, 580},{27, 524},
{28, 598},{29, 537},{30, 609},
{31, 543},{32, 612},{33, 542},
{34, 607},{35, 534},{36, 594},
{37, 518},{38, 572},{39, 496},
{40, 544},{41, 469},{42, 511},
{43, 437},{44, 474},{45, 404},
{46, 462},{47, 427},{48, 485},
{49, 441},{50, 507}};
var i = 0;
for (i = 0; i <= dict.Count - 2; i++)
{
var ele = dict.ElementAt(i);
var current_time = ele.Key;
var current_price = ele.Value;
var is_maxima = current_price > dict.ElementAt(i + 1).Value;
//' If ele.Key = 23 Then here = True
var shortest_dist = Int32.MaxValue;
var l_ex = new KeyValuePair<int, decimal>();
var r_ex = new KeyValuePair<int, decimal>();
if (is_maxima)
{
l_ex = dict.Reverse().Skip(dict.Count - 1 - i + 1).SkipWhile(x => x.Value < current_price).FirstOrDefault();
r_ex = dict.Skip(i + 1).SkipWhile(x => x.Value < current_price).FirstOrDefault();
}
else
{ // 'Is Minima
l_ex = dict.Reverse().Skip(dict.Count - 1 - i + 1).SkipWhile(x => x.Value > current_price).FirstOrDefault();
r_ex = dict.Skip(i + 1).SkipWhile(x => x.Value > current_price).FirstOrDefault();
}
if (l_ex.Key > 0)
{
var l_dist = (current_time - l_ex.Key);
if ( l_dist < shortest_dist ) {
shortest_dist = l_dist;
};
}
if (r_ex.Key > 0)
{
var r_dist = (r_ex.Key - current_time);
if ( r_dist < shortest_dist ) {
shortest_dist = r_dist;
};
}
dict_dists.Add(current_time, shortest_dist);
}
var dist = dict_dists[23];
}
Edit: As a workaround I'm writing a reversed temp file for the left-seekers.
for (i = file.count - 1; i >= 0; i += -1)
{
file.SetPointerToItem(i);
temp_file.Write(file.Read());
}

You could make it more efficient by selecting the precedent of each item in one pass. Lets make an extension method for enumerables that selects a precedent for each element:
public static IEnumerable<T> SelectPrecedent<T>(this IEnumerable<T> source,
Func<T, bool> selector)
{
T selectedPrecedent = default;
foreach (var item in source)
{
if (selector(item)) selectedPrecedent = item;
yield return selectedPrecedent;
}
}
You could then use this method, and select the precedent and the subsequent of each element by doing only two Reverse operations in total:
var precedentArray = collection.SelectPrecedent(x => x.Price < ex_price).ToArray();
var subsequentArray = collection.Reverse()
.SelectPrecedent(x => x.Price < ex_price).Reverse().ToArray();
for (int i = 0; i < collection.Count; i++)
{
var current = collection[i];
var precedent = precedentArray[i];
var subsequent = subsequentArray[i];
// Do something with the current, precedent and subsequent
}

No need to do .Reverse() and then FirstOrDefault(), just use LastOrDefault(). Instead of Skip(collection.Count - e) use .Take(e) elements
var backwards_satisfied_row = collection
.SkipWhile(x => x.Price < ex_price) //Skip till x.Price < ex_price
.Skip(e+1) //Skip first e+1 elements
.LastOrDefault(); //Get Last or default value
You can make your code more efficient by storing collection and then just get FirstOrDefault() and LastOrDefault() for forwards_satisfied_row and backwards_satisfied_row respectively.
like,
for (e = 0; e <= collection.Count - 2; e++)
{
var itm = collection.Read()
var itm_price = itm.Price
var satisfied_rows = collection
.SkipWhile(x => x.Price < ex_price)
.Skip(e + 1)
.ToList();
var forwards_satisfied_row = satisfied_rows.FirstOrDefault();
var backwards_satisfied_row = satisfied_rows.LastOrDefault();
}

Using variables in LINQ Entity Framework expression inside a loop gets the last value [duplicate]

This question already has an answer here:
Captured Closure (Loop Variable) in C# 5.0
(1 answer)
Closed 2 years ago.
I am trying to create a SQL query using C# Entity framework LINQ which result in a similar SQL like this:
select * from centros
where SUBSTRING(UPPER(c_nombre),1,1)='M'
and (SUBSTRING(UPPER(c_nombre),2,1)='A' OR SUBSTRING(UPPER(c_nombre),2,1)='Á')
and SUBSTRING(UPPER(c_nombre),3,1)='L'
order by c_nombre
limit 10
This is my code:
public List<Entidad> SearchByDescServer(string desc, int limit)
{
List<Entidad> entidades = new List<Entidad>();
IQueryable<IEntidad> models = entitySet.AsNoTracking();
for (int index = 0; index < desc.Length; index++) {
string currentChar = desc.Substring(index,1).ToUpper();
models = models.Where(e=>e.Descripcion.Substring(index,1).ToUpper()==currentChar);
}
models = models.OrderBy(e => e.Descripcion).Take(limit);
foreach (IEntidad m in models.ToList()) {
entidades.Add(m.ToEntidad());
}
return entidades;
}
The thing is easy, I am adding where clauses to the IQueryable object in a loop. I am using a PostgreSQL database. The debug show me this:
Executed DbCommand (12ms) [
Parameters=[
#__8__locals1_index_0='3',
#__currentChar_1='A' (Size = 150),
#__8__locals1_index_2='3',
#__currentChar_3='A' (Size = 150),
#__8__locals1_index_4='3',
#__currentChar_5='A' (Size = 150),
#__p_6='10'
], CommandType='Text', CommandTimeout='30']
SELECT e.c_id, e.c_activo, e.c_codigo, e.c_nombre
FROM centros AS e
WHERE ((UPPER(SUBSTRING(e.c_nombre, #__8__locals1_index_0 + 1, 1)) = #__currentChar_1) AND (UPPER(SUBSTRING(e.c_nombre, #__8__locals1_index_2 + 1, 1)) = #__currentChar_3)) AND (UPPER(SUBSTRING(e.c_nombre, #__8__locals1_index_4 + 1, 1)) = #__currentChar_5)
ORDER BY e.c_nombre
LIMIT #__p_6
So what is happening is that index parameters are always the last value of index variable after the loop. Can anyone explain me this behavior??
Thanks

Introduce temporary variable and use it in lambda:
for (int index = 0; index < desc.Length; index++)
{
var tmp = index;
string currentChar = desc.Substring(index, 1).ToUpper();
models = models.Where(e=>e.Descripcion.Substring(tmp, 1).ToUpper()==currentChar);
}
As for why - this is how C# closures in for loop work. In short - for your anonymous function e=>e.Descripcion.Substring(i, 1).ToUpper()==currentChar compiler generates special class which will hold captured i variable which will be updated from the first to the last value of index:
var actions = new List<Action>();
for (int i = 0; i < 10; i++)
{
actions.Add(() => Console.WriteLine(i));
}
// will print 10 times "10"
foreach (var a in actions)
{
a();
}
Bear in mind that foreach loop behaves differently:
var actions = new List<Action>();
foreach (var i in Enumerable.Range(0, 10))
{
actions.Add(() => Console.WriteLine(i));
}
// prints from 0 to 9
foreach (var a in actions)
{
a();
}
For more information you can read this answer by Jon Skeet and/or this article.

Getting the sum per hour from 2 datatable

I'm writing a txt file from 2 data table.
Following is the 2 data table.
dt1
Transaction No. Time Amount Date
1 10:00:00 200.00 03/05/2020
2 10:30:11 250.00 03/05/2020
3 11:05:22 140.00 03/05/2020
4 11:45:33 230.00 03/05/2020
5 12:15:10 220.00 03/05/2020
dt2
Transaction No. Added Amount Date
1 40.00 03/05/2020
2 25.00 03/05/2020
3 40.00 03/05/2020
4 30.00 03/05/2020
5 30.00 03/05/2020
following is my code
using (StreamWriter sw = File.AppendText(fileName))
{
for (int a = 6; a <= 23; a++)
{
string aa = a.ToString().PadLeft(2, '0');
double salex = double.Parse(dt1.Rows[0]["Amount"].ToString());
if (salex.Equals(""))
{
salex = 0;
}
else
{
salex = double.Parse(dt1.Rows[0]["Amount"].ToString());
}
double vatx = double.Parse(dt2.Rows[0]["Added Amount"].ToString());
if (vatx.Equals(""))
{
vatx = 0;
}
else
{
vatx = double.Parse(dt2.Rows[0]["Added Amount"].ToString());
}
double dailysaleHRLY = -salex + -vatx;
sw.Write(dtpDate.Value.ToString("MM/dd/yyyy") + ",");
sw.Write(aa + ":00" + ",");
sw.Write(dailysaleHRLY.ToString("0.00") + ",");
}
for (int a = 0; a <= 5; a++)
{
string aa = a.ToString().PadLeft(2, '0');
double salex = double.Parse(dt1.Rows[0]["Amount"].ToString());
if (salex.Equals(""))
{
salex = 0;
}
else
{
salex = double.Parse(dt1.Rows[0]["Amount"].ToString());
}
double vatx = double.Parse(dt2.Rows[0]["Added Amount"].ToString());
if (vatx.Equals(""))
{
vatx = 0;
}
else
{
vatx = double.Parse(dt2.Rows[0]["Added Amount"].ToString());
}
double dailysaleHRLY = -salex + -vatx;
sw.Write(dtpDate.Value.ToString("MM/dd/yyyy") + ",");
sw.Write(aa + ":00" + ",");
sw.Write(dailysaleHRLY.ToString("0.00") + ",");
}
MessageBox.Show("Txt File succesfully created!", "SYSTEM", MessageBoxButtons.OK, MessageBoxIcon.Information);
}
This is the output of my code.
Date, Time, Sum
03/05/2020,06:00,515.00
03/05/2020,07:00,515.00
03/05/2020,08:00,515.00
03/05/2020,09:00,515.00
03/05/2020,10:00,515.00
03/05/2020,11:00,515.00
03/05/2020,12:00,515.00
03/05/2020,13:00,515.00
03/05/2020,14:00,515.00
03/05/2020,15:00,515.00
03/05/2020,16:00,515.00
03/05/2020,17:00,515.00
03/05/2020,18:00,515.00
03/05/2020,19:00,515.00
03/05/2020,20:00,515.00
03/05/2020,21:00,515.00
03/05/2020,22:00,515.00
03/05/2020,23:00,515.00
03/05/2020,00:00,515.00
03/05/2020,01:00,515.00
03/05/2020,02:00,515.00
03/05/2020,03:00,515.00
03/05/2020,04:00,515.00
03/05/2020,05:00,515.00
I just want to get the sum of Amount and Added Amount base on hour. Like this.
Date, Time, Sum
03/05/2020,06:00,0.00
03/05/2020,07:00,0.00
03/05/2020,08:00,0.00
03/05/2020,09:00,0.00
03/05/2020,10:00,515.00
03/05/2020,11:00,440.00
03/05/2020,12:00,250.00
03/05/2020,13:00,0.00
03/05/2020,14:00,0.00
03/05/2020,15:00,0.00
03/05/2020,16:00,0.00
03/05/2020,17:00,0.00
03/05/2020,18:00,0.00
03/05/2020,19:00,0.00
03/05/2020,20:00,0.00
03/05/2020,21:00,0.00
03/05/2020,22:00,0.00
03/05/2020,23:00,0.00
03/05/2020,00:00,0.00
03/05/2020,01:00,0.00
03/05/2020,02:00,0.00
03/05/2020,03:00,0.00
03/05/2020,04:00,0.00
03/05/2020,05:00,0.00

Assuming that you have two DataTable-s and you have them filled with the mentioned data.
var dt1 = new DataTable();
var dt2 = new DataTable();
dt1.Columns.AddRange(new[]
{
new DataColumn("Transaction No.", typeof(int)),
new DataColumn("Time", typeof(DateTime)),
new DataColumn("Amount", typeof(decimal)),
new DataColumn("Date", typeof(DateTime)),
});
dt2.Columns.AddRange(new[]
{
new DataColumn("Transaction No.", typeof(int)),
new DataColumn("Added Amount", typeof(decimal)),
new DataColumn("Date", typeof(DateTime)),
});
Note: The double types have been replaced with decimal types since its the right type to be used when dealing with money.
As I understand the problem, you want to group the rows of dt1 by hour part of the Time field, sum the Amount, and add to the sum the Added Amount from dt2 rows where their Transaction No. equals to any Transaction No. of the grouped rows of dt1.
This will do:
var group = dt1.AsEnumerable().GroupBy(x => x.Field<DateTime>(1).Hour);
var sb = new StringBuilder();
sb.Append("Date,");
sb.Append("Time,".PadLeft(12, ' '));
sb.AppendLine("Sum".PadLeft(5, ' '));
//if PadLeft is not required in the output, then just:
//sb.AppendLine($"Date, Time, Sum");
foreach (var g in group)
{
var sum = 0M;
foreach (var r in g)
sum += r.Field<decimal>(2) + dt2.AsEnumerable()
.Where(x => x.Field<int>(0) == r.Field<int>(0))
.Sum(x => x.Field<decimal>(1));
sb.AppendLine($"{g.First().Field<DateTime>(3).ToString("MM/dd/yyyy")}, {g.Key.ToString("00")}:00, {sum.ToString("0.00")}");
}
Note: You can use the fields names instead of their indexes.
The output is:
Date, Time, Sum
03/05/2020, 10:00, 515.00
03/05/2020, 11:00, 440.00
03/05/2020, 12:00, 250.00
I don't know whether the DataTable-s already contain the required data to generate the output mentioned in the last quote block or you want to append the rest before writing to the text file. In case of the second scenario, you can do something like:
var group = dt1.AsEnumerable().GroupBy(x => x.Field<DateTime>(1).Hour);
var sb = new StringBuilder();
sb.AppendLine($"Date, Time, Sum");
for (var i = 0; i < 24; i++)
{
var g = group.FirstOrDefault(x => x.Key == i);
if (g != null)
{
var sum = 0M;
foreach (var r in g)
sum += r.Field<decimal>(2) + dt2.AsEnumerable()
.Where(x => x.Field<int>(0) == r.Field<int>(0))
.Sum(x => x.Field<decimal>(1));
sb.AppendLine($"{g.First().Field<DateTime>(3).ToString("MM/dd/yyyy")}, {g.Key.ToString("00")}:00, {sum.ToString("0.00")}");
}
else
sb.AppendLine($"{group.First().First().Field<DateTime>(3).ToString("MM/dd/yyyy")}, {i.ToString("00")}:00, 0.00");
}
If you need to preserve the same order of the hours:
for (var ii = 6; ii < 30; ii++)
{
var i = ii > 23 ? ii % 24 : ii;
var g = group.FirstOrDefault(x => x.Key == i);
if (g != null)
{
//The same...
}
Finally, to create or overwrite the text file (fileName):
File.WriteAllText(fileName, sb.ToString());
Or to append the output:
File.AppendAllText(fileName, sb.ToString());

Find values which sum to 0 in Excel with many items

I have to find each subset in a enough big list, 500/1000 items that are positive and negative and are decimal, whiches sum to 0. I'm not an expert so I read many and many articles and solutions, and then I wrote my code. Datas comes from Excel worksheet and I would to mark found sums there.
Code works in this way:
Initally I find all pair that sum to 0
Then I put the remains sums into a list and take the combinations within 20 items, beacause I know the it is not possible bigger combination sum to 0
In these combinations I search if one combinations sums to 0 and save it in result list, else save sum in dictionary as key and then I'll search if dictionary contains next sums (so I check pairs of these subsets)
I keep track of the index so I can reach and modify the cells
To found solutions is enough fast but when I want elaborate the results in Excel become really slow. I don't take care about find all solutions but I want to find as max as possible in a short time.
What do you think about this solution? How can I improve the speed? How can I skip easly the sums that are already taken? And how can mark the cells fastly in my worksheet, beacuse now here is the bottleneck of the program?
I hope it is enough clear :) Thanks to everybody for any help
Here my code of the combination's part:
List<decimal> listDecimal = new List<decimal>();
List<string> listRange = new List<string>();
List<decimal> resDecimal = new List<decimal>();
List<IEnumerable<decimal>> resDecimal2 = new List<IEnumerable<decimal>>();
List<IEnumerable<string>> resIndex = new List<IEnumerable<string>>();
Dictionary<decimal, int> dicSumma = new Dictionary<decimal, int>();
foreach (TarkistaSummat.CellsRemain el in list)
{
decimal sumDec = Convert.ToDecimal(el.Summa.Value);
listDecimal.Add(sumDec);
string row = el.Summa.Cells.Row.ToString();
string col = el.Summa.Cells.Column.ToString();
string range = el.Summa.Cells.Row.ToString() + ":" + el.Summa.Cells.Column.ToString();
listRange.Add(range);
}
var subsets = new List<IEnumerable<decimal>> { new List<decimal>() };
var subsetsIndex = new List<IEnumerable<string>> { new List<string>() };
for (int i = 0; i < list.Count; i++)
{
if (i > 20)
{
List<IEnumerable<decimal>> parSubsets = subsets.GetRange(i, i + 20);
List<IEnumerable<string>> parSubsetsIndex = subsetsIndex.GetRange(i, i + 20);
var Z = parSubsets.Select(x => x.Concat(new[] { listDecimal[i] }));
//var Zfound = Z.Select(x => x).Where(w => w.Sum() ==0);
subsets.AddRange(Z.ToList());
var Zr = parSubsetsIndex.Select(x => x.Concat(new[] { listRange[i] }));
subsetsIndex.AddRange(Zr.ToList());
}
else
{
var T = subsets.Select(y => y.Concat(new[] { listDecimal[i] }));
//var Tfound = T.Select(x => x).Where(w => w.Sum() == 0);
//resDecimal2.AddRange(Tfound);
//var TnotFound = T.Except(Tfound);
subsets.AddRange(T.ToList());
var Tr = subsetsIndex.Select(y => y.Concat(new[] { listRange[i] }));
subsetsIndex.AddRange(Tr.ToList());
}
for (int i = 0; i < subsets.Count; i++)
{
decimal sumDec = subsets[i].Sum();
if (sumDec == 0m)
{
resDecimal2.Add(subsets[i]);
resIndex.Add(subsetsIndex[i]);
continue;
}
else
{
if(dicSumma.ContainsKey(sumDec * -1))
{
dicSumma.TryGetValue(sumDec * -1, out int index);
IEnumerable<decimal> addComb = subsets[i].Union(subsets[index]);
resDecimal2.Add(addComb);
var indexComb = subsetsIndex[i].Union(subsetsIndex[index]);
resIndex.Add(indexComb);
}
else
{
if(!dicSumma.ContainsKey(sumDec))
{
dicSumma.Add(sumDec, i);
}
}
}
}
for (int i = 0; i < resIndex.Count; i++)
{
//List<Range> ranges = new List<Range>();
foreach(string el in resIndex[i])
{
string[] split = el.Split(':');
Range cell = actSheet.Cells[Convert.ToInt32(split[0]), Convert.ToInt32(split[1])];
cell.Interior.ColorIndex = 6;
}
}
}