Question

I have the following dataset, I want to select distinct rows. since the data is flat.
I dont how can i do that with linq ?

Following is the code snippet who I am meeting my requirement, How can i optimize it ?

 VendorInvoiceStagingTable = new Program().ReadExcelFile(@"C:\Users\huzaifa.gain\Desktop\Vendor invoice import - sample data set.xlsx", "Sheet2");
        var InvoiceHeadercollection = VendorInvoiceStagingTable.AsEnumerable().Select(t=>t.Field<string>(VendInvoice.Number)).Distinct();

        VendorInvoiceTable =  new Program().CreateHeader();
        foreach (var InvoiceHeader in InvoiceHeadercollection)
        {
            IEnumerable<DataRow> query = from vendInv in VendorInvoiceStagingTable.AsEnumerable()
                                         where vendInv.Field<string>(VendInvoice.Number) == InvoiceHeader
                                         select vendInv;

            Object[] obj = new Object[10];
            var item = query.First();

            for (int idx = 0; idx < 10; idx++)
            {

                obj[idx] = item[idx];

            }

           VendorInvoiceTable.Rows.Add(obj);
        }

Answer 1

Not sure what you want, but maybe this can help you.

    var l = VendorInvoiceStagingTable.AsEnumerable().ToLookup(t => t.Field<string>(VendInvoice.Number));
    foreach (var item in l)
    {
        var itemToAdd = item.First();
        //Do add here
    }