Group and Sum DataTable - c#

I have Data Table with the following data
Number Type Order count
1 1 R 1
1 1 R 1
1 1 R 1
1 2 R 1
I am looking to get to this result
Number Type Order count
1 1 R 3
1 2 R 1
How can I group by three columns
var result = dt.AsEnumerable()
.GroupBy(x => {x.Field<string>("Number"))//need to group by Type and order also need to sum te total counts

rgoal
Your question made me curious, so I did some digging on Stack Overflow.
esc's answer appears will also solve your issue. It is posted under: How do I use SELECT GROUP BY in DataTable.Select(Expression)?:
Applying his method to your problem gave me this solution:
DataTable dt2 = dt.AsEnumerable()
.GroupBy(r => new { Number = r["Number"], Type = r["Type"], Order = r["Order"] })
.Select(g =>
{
var row = dt.NewRow();
row["Number"] = g.Key.Number;
row["Type"] = g.Key.Type;
row["Order"] = g.Key.Order;
row["Count"] = g.Count();
return row;
}).CopyToDataTable();
This will return a DataTable matching the schema of the input DataTable with the grouping and counts you requested.
Here is the full code I use to verify in LINQPad:
DataTable dt = new DataTable("Demo");
dt.Columns.AddRange
(
new DataColumn[]
{
new DataColumn ( "Number", typeof ( int ) ),
new DataColumn ( "Type", typeof ( int ) ),
new DataColumn ( "Order", typeof ( string ) ),
new DataColumn ( "Count", typeof ( int ) )
}
);
dt.Rows.Add(new object[] { 1,1,"R", 1 });
dt.Rows.Add(new object[] { 1,1,"R", 1 });
dt.Rows.Add(new object[] { 1,1,"R", 1 });
dt.Rows.Add(new object[] { 1,2,"R", 1 });
DataTable dt2 = dt.AsEnumerable()
.GroupBy(r => new { Number = r["Number"], Type = r["Type"], Order = r["Order"] })
.Select(g =>
{
var row = dt.NewRow();
row["Number"] = g.Key.Number;
row["Type"] = g.Key.Type;
row["Order"] = g.Key.Order;
row["Count"] = g.Count();
return row;
}).CopyToDataTable();
foreach (DataRow row in dt2.Rows)
{
for (int i = 0; i < dt2.Columns.Count; i++)
Console.Write("{0}{1}",
row[i], // Print column data
(i < dt2.Columns.Count - 1)? " " : Environment.NewLine); // Print column or row separator
}
Here are the results:
1 1 R 3
1 2 R 1

Related

Use formula in LINQ selection

I have a datatable that looks like this:
Row Side Value
1 A 34.8
1 B 33.9
1 C 33.1
2 A 32.6
2 B 32.0
2 C 35.7
3 A 34.6
3 B 34.0
3 C 33.5
One thing I needed to do was compute the average of each Row which I did like:
var avg = (from row in dt.AsEnumerable()
group row by new { RowMeas = row.Field<string>("Row") } into grp
select new
{
RowMeas = grp.Key.RowMeas,
AVG = grp.Average(r => r.Field<double>("Value"))
}).ToList();
Now I need to do something similar but instead of just taking the average I want to use a formula for each row like 4*A + 3*B + 2*C
Can I do this using LINQ like above but instead of AVG somehow work this formula in? In other software we do this calculation manually by transposing the datatable so that there are A, B, C columns which can then be used in an formula on a new column. Since there's not an easy way to transpose in C# I'm hoping I can do this using LINQ.
var dt = new DataTable();
dt.Columns.Add("Row", typeof(string));
dt.Columns.Add("Side", typeof(string));
dt.Columns.Add("Value", typeof(double));
dt.Rows.Add(1, "A", 34.8);
dt.Rows.Add(1, "B", 33.9);
dt.Rows.Add(1, "C", 33.1);
dt.Rows.Add(2, "A", 32.6);
dt.Rows.Add(2, "B", 32.0);
dt.Rows.Add(2, "C", 35.7);
dt.Rows.Add(3, "A", 34.6);
dt.Rows.Add(3, "B", 34.0);
dt.Rows.Add(3, "C", 33.5);
var query = dt
.AsEnumerable()
.GroupBy(x => x.Field<string>("Row"))
.Select(x => new
{
Row = x.Key,
A = x.Where(y => y.Field<string>("Side") == "A").Select(z => z.Field<double>("Value")).FirstOrDefault(),
B = x.Where(y => y.Field<string>("Side") == "B").Select(z => z.Field<double>("Value")).FirstOrDefault(),
C = x.Where(y => y.Field<string>("Side") == "C").Select(z => z.Field<double>("Value")).FirstOrDefault()
})
.Select(x => new
{
Row = x.Row,
Result = 4 * x.A + 3 * x.B + 2 * x.C
})
;
foreach (var q in query)
Console.WriteLine("Row = {0}, Result = {1}", q.Row, q.Result);
Result in LinqPad.

Firebird group by period

I am pulling some historical data from Firebird database as below:
Product_ID Date Price
1 2001-01-01 10
1 2001-02-01 10
1 2001-03-01 15
1 2001-04-01 10
1 2001-05-01 20
1 2001-06-01 20
What I am trying to do is to extract the first for occurrence every price change.
Example of expected data set:
Product_ID Date Price
1 2001-01-01 10
1 2001-03-01 15
1 2001-04-01 10
1 2001-05-01 20
I know that on MSSQL I could leverage LAG for that. Is it possible to do that with Firebird?
You can try this, but be aware I didn't tested it:
CREATE PROCEDURE SP_Test
RETURNS (
Product_ID INTEGER,
Date DATE,
Price INTEGER
)
AS
DECLARE VARIABLE Last_Product_ID INTEGER;
DECLARE VARIABLE Last_Date DATE;
DECLARE VARIABLE Last_Price INTEGER;
BEGIN
FOR SELECT Product_ID, Date, Price
FROM xxxx
ORDER BY Product_ID, Date
INTO Product_ID, Date, Price
DO BEGIN
IF ((:Last_Product_ID IS NULL) OR
(:Last_Date IS NULL) OR
(:Last_Price IS NULL) OR
(:Product_ID <> :Last_Product_ID) OR
(:Price <> :Last_Price)) THEN
SUSPEND;
Last_Product_ID = :Product_ID;
Last_Date = :Date;
Last_Price = :Price;
END;
END;
in MoreLinq there is a Lag extension method but it is supported only in Linq to Objects...
What you can do, if you are looking for a C# linq answer for that you can:
Basically order your data the correct way and then add a row index for while price (and product_id) is still the same. Then group by it and select the min date.
int groupingIndex = 0;
int previousPrice = 0;
var response = data
.OrderBy(item => item.Product_ID)
.ThenBy(item => item.Date)
.Select(item =>
{
if (item.Price != previousPrice)
{
previousPrice = item.Price;
groupingIndex++;
}
return new { Index = groupingIndex, Item = item };
})
.GroupBy(item => new { item.Index, item.Item.Product_ID, item.Item.Price } )
.Select(group => new Record
{
Product_ID = group.Key.Product_ID,
Price = group.Key.Price,
Date = group.Min(item => item.Item.Date)
}).ToList();
And if you don't mind doing the operation in the C# and not the DB (and using a beta version of the MoreLinq) then:
int index = 0;
var result2 = data
.OrderBy(item => item.Product_ID)
.ThenBy(item => item.Date)
.Lag(1, (current, previous) => new { Index = (current.Price == previous?.Price ? index : ++index), Item = current })
.GroupBy(item => new { item.Index, item.Item.Product_ID, item.Item.Price })
.Select(group => new Record { Product_ID = group.Key.Product_ID, Price = group.Key.Price, Date = group.Min(item => item.Item.Date) })
.ToList();
This is a little complicated but it works
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Data;
namespace ConsoleApplication6
{
class Program
{
static void Main(string[] args)
{
DataTable dt = new DataTable();
dt.Columns.Add("Product_ID", typeof(int));
dt.Columns.Add("Date", typeof(DateTime));
dt.Columns.Add("Price", typeof(int));
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-01-01"), 10});
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-02-01"), 10});
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-03-01"), 15});
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-04-01"), 10});
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-05-01"), 20});
dt.Rows.Add(new object[] {1, DateTime.Parse("2001-06-01"), 20});
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-01-01"), 10 });
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-02-01"), 10 });
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-03-01"), 15 });
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-04-01"), 10 });
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-05-01"), 20 });
dt.Rows.Add(new object[] { 2, DateTime.Parse("2001-06-01"), 20 });
dt = dt.AsEnumerable().OrderBy(x => x.Field<DateTime>("Date")).CopyToDataTable();
List<DataRow> results = dt.AsEnumerable()
.GroupBy(g => g.Field<int>("Product_ID"))
.Select(g1 => g1.Select((x, i) => new { row = x, dup = (i == 0) || ((i > 0) && (g1.Skip(i - 1).FirstOrDefault().Field<int>("Price") != g1.Skip(i).FirstOrDefault().Field<int>("Price"))) ? false : true })
.Where(y => y.dup == false).Select(z => z.row)).SelectMany(m => m).ToList();
}
}
}

How to select max and min value of any column of datagridview

I have a datagridview control on my windows form.
Now i need to select max and min value of a column.
In data-table we can do this by using this
Code
int maxID = curriculmDataTable.AsEnumerable().Max(r => r.Field<int>("Id"));
How can i achieve this in datagridview.
You can try:
var MaxID = dataGridView1.Rows.Cast<DataGridViewRow>()
.Max(r => Convert.ToInt32(r.Cells["Id"].Value));
Make sure your Id cell has int type value, otherwise use Int.TryParse like:
int temp;
var MaxID2 = dataGridView1.Rows.Cast<DataGridViewRow>()
.Max(r => int.TryParse(r.Cells["Id"].Value.ToString(), out temp) ?
temp : 0 );
If your datasource is a datatable this sample can help you.
DataTable dtDataSource = new DataTable();
dtDataSource.Columns.Add("Value");
dtDataSource.Columns.Add("Display");
dtDataSource.Rows.Add(new object[] { 1, 1});
dtDataSource.Rows.Add(new object[] { 2, 2 });
dtDataSource.Rows.Add(new object[] { 3, 3 });
dtDataSource.Rows.Add(new object[] { 4, 4 });
dtDataSource.Rows.Add(new object[] { 5, 5 });
var results = dtDataSource.AsEnumerable().Max(row => Convert.ToInt32(row["Value"]));
datatable dt=datagridview1.datasource as datatable
int total = dt.Compute("Sum ( ColumnName ) ", "Criteria");

how to fill each Column in datatable

I am iterating on a lot of strings and I want to fill my first(and only) 3 Columns with each result and then start again in a new row. like:
A | B | C
------+--------+------
"DOG" | "CAT" | "FISH"
"FDF" | "AAA" | "RRR"
AND SO ON....
Basically after each row is "full" open new row.
HtmlNodeCollection tables = doc.DocumentNode.SelectNodes("//table");
HtmlNodeCollection rows = tables[2].SelectNodes(".//tr");
DataTable dataTable = new DataTable();
dataTable.Columns.Add("A", typeof(string));
dataTable.Columns.Add("B", typeof(string));
dataTable.Columns.Add("C", typeof(string))
try like this
for (int i = 0; i < rows .Count(); i++)
{
DataRow datarowObj= dataTable .NewRow();
datarowObj["A"] = yourValue;
datarowObj["B"] = yourValue;
datarowObj["C"] = yourValue;
dataTable.Rows.Add(datarowObj);
}
You could use Linq's GroupBy to split the long list into groups of 3:
sample-data:
DataTable table = new DataTable();
table.Columns.Add("Col1");
table.Columns.Add("Col2");
table.Columns.Add("Col3");
List<string> longList = Enumerable.Range(1, 99).Select(i => "row " + i).ToList();
group the long list into parts of three:
var groupsWithThree = longList
.Select((s, i) => new { Str = s, Index = i })
.GroupBy(x => x.Index / 3);
add them to the table:
foreach (var group3 in groupsWithThree)
table.Rows.Add(group3.First().Str, group3.ElementAt(1).Str, group3.Last().Str);
Note that it presumes that the list is divisible by three.
Manage with DataRoxw, for instance, after adding an empty DataRow to your DataTable :
DataRow row = table.Rows[0];
foreach (object item in row.ItemArray)
{
?
dataTable.Rows.Add(new object[] { "A1", "B1", "C1" })
// Alternatively
object[] arr = new object[] { "A2", "B2", "C2" };
dataTable.Rows.Add(arr);

Make column value as Header Columns

My Table1 has some Header and Values:
KundeID KundeName Produkt Comment
1 Michael Jogurt "nichts"
2 Raj "Ich bin cool"
3 Gary Fanta "yahoo"
4 Miky Sprite
I want to change to Table2, make Values from Produkt as Header Columns:
KundeID KundeName Comment Jogurt Fanta Sprite
1 Michael "nichts" x
2 Raj "Ich bin cool"
3 Gary "yahoo" x
4 Miky x
My code for Table1:
DataTable table = new DataTable("Kunde");
table.Columns.Add("KundeID", typeof(Int32));
table.Columns.Add("KundeName", typeof(String));
table.Columns.Add("Produkt", typeof(String));
DataTable comment = new DataTable("Comment");
comment.Columns.Add("KundeName", typeof(String));
comment.Columns.Add("Comment", typeof(String));
DataSet ds = new DataSet("DataSet");
ds.Tables.Add(table);
ds.Tables.Add(comment);
object[] o1 = { 1, "Michael", "Jogurt" };
object[] o2 = { 2, "Raj" };
object[] o3 = { 3, "Gary", "Fanta" };
object[] o4 = { 4, "Miky", "Sprite" };
object[] c1 = { "Raj", "Ich bin cool" };
object[] c2 = { "Gary", "yahoo" };
object[] c3 = { "Michael", "nichts" };
table.Rows.Add(o1);
table.Rows.Add(o2);
table.Rows.Add(o3);
table.Rows.Add(o4);
comment.Rows.Add(c1);
comment.Rows.Add(c2);
comment.Rows.Add(c3);
var results = from table1 in table.AsEnumerable()
join table2 in comment.AsEnumerable()
on table1.Field<string>("KundeName") equals table2.Field<string>("KundeName") into prodGroup
from table4 in prodGroup.DefaultIfEmpty()
select new
{
KundeID = table1.Field<Int32?>("KundeID"),
KundeName = table1.Field<String>("KundeName"),
Produkt = table1.Field<String>("Produkt"),
Comment = table4 != null ? table4.Field<String>("Comment") : null,
};
dataGridView1.DataSource = results.ToList();
How can I take Value from "Produkt" and make it Header? thank you guys for helping
This should do the trick regardless of how many different products come up. It's pretty short and concise.
// build the new data table
var result = new DataTable();
result.Columns.Add("KundeID", typeof(Int32));
result.Columns.Add("KundeName", typeof(String));
result.Columns.Add("Comment", typeof(String));
result.Columns.AddRange(
(from c in
(from r in table.AsEnumerable()
where !r.IsNull("Produkt") && !string.IsNullOrEmpty(r.Field<string>("Produkt"))
select r.Field<string>("Produkt")).Distinct() // added DISTINCT
select new DataColumn(c, typeof(bool))).ToArray()
);
foreach (var r in results)
{
var productIndex = result.Columns.IndexOf(r.Produkt);
var vals = new List<object>() { r.KundeID, r.KundeName, r.Comment };
for (int i = 3; i < result.Columns.Count; i++)
{
if (i == productIndex)
{
vals.Add(true);
}
else
{
vals.Add(false);
}
}
result.LoadDataRow(vals.ToArray(), true);
}
var products = table.AsEnumerable()
.GroupBy(c => c["Produkt"])
.Where(g => !(g.Key is DBNull))
.Select(g => (string)g.Key)
.ToList();
var newtable = table.Copy();
products.ForEach(p=>newtable.Columns.Add(p,typeof(bool)));
foreach (var row in newtable.AsEnumerable())
{
if (!(row["Produkt"] is DBNull)) row[(string)row["Produkt"]] = true;
}
newtable.Columns.Remove("Produkt");
Try following...this may help you....
DataTable table = new DataTable("Kunde");
table.Columns.Add("KundeID", typeof(Int32));
table.Columns.Add("KundeName", typeof(String));
table.Columns.Add("Produkt", typeof(String));
table.Columns.Add("Comment", typeof(String));
object[] o1 = { 1, "Michael", "Jogurt", "nichts" };
object[] o2 = { 2, "Raj","","Ich bin cool" };
object[] o3 = { 3, "Gary", "Fanta","yahoo" };
object[] o4 = { 4, "Miky", "Sprite","" };
table.Rows.Add(o1);
table.Rows.Add(o2);
table.Rows.Add(o3);
table.Rows.Add(o4);
Dictionary<int,string> dictObj=new Dictionary<int, string>();
for (int i = 0; i < table.Rows.Count; i++)
{
dictObj.Add(Convert.ToInt32(table.Rows[i][0].ToString()), table.Rows[i][2].ToString());
}
foreach (var obj in dictObj)
{
if (string.IsNullOrEmpty(obj.Value))
{
table.Columns.Add(obj.Value, typeof(String));
DataRow row = table.Rows[obj.Key];
row[obj.Value] = "X";
}
}

Categories