Best approach to find duplicate employee from List<T> using LINQ

[Sudip_inn]

suppose i have many duplicate employee in List based on employee name and location id. tell me best approach to follow for this scenario. after my google search i found few approach but do not understand which i should use. here giving those approach.

code taken from C# LINQ find duplicates in List.

1)

var query = from s2 in (from s in someList group s by new { s.Column1, s.Column2 } into sg select sg) where s2.Count() > 1 select s2;

2)


var anyDuplicate = enumerable.GroupBy(x => x.Key).Any(g => g.Count() > 1);

OR

var duplicates = model.list
.GroupBy(s => s.SAME_ID)
.Where(g => g.Count() > 1).Count() > 0;
if(duplicates) {
doSomething();
}

3)

//Dummy class to compare in list
public class Person
{
public int Id { get; set; }
public string Name { get; set; }
public string Surname { get; set; }
public Person(int id, string name, string surname)
{
this.Id = id;
this.Name = name;
this.Surname = surname;
}
}


//The extention static class
public static class Extention
{
public static IEnumerable<T> getMoreThanOnceRepeated<T>(this IEnumerable<T> extList, Func<T, object> groupProps) where T : class
{ //Return only the second and next reptition
return extList
.GroupBy(groupProps)
.SelectMany(z => z.Skip(1)); //Skip the first occur and return all the others that repeats
}
public static IEnumerable<T> getAllRepeated<T>(this IEnumerable<T> extList, Func<T, object> groupProps) where T : class
{
//Get All the lines that has repeating
return extList
.GroupBy(groupProps)
.Where(z => z.Count() > 1) //Filter only the distinct one
.SelectMany(z => z);//All in where has to be retuned
}
}

//how to use it:
void DuplicateExample()
{
//Populate List
List<Person> PersonsLst = new List<Person>(){
new Person(1,"Ricardo","Figueiredo"), //fist Duplicate to the example
new Person(2,"Ana","Figueiredo"),
new Person(3,"Ricardo","Figueiredo"),//second Duplicate to the example
new Person(4,"Margarida","Figueiredo"),
new Person(5,"Ricardo","Figueiredo")//third Duplicate to the example
};

Console.WriteLine("All:");
PersonsLst.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
All:
1 -> Ricardo Figueiredo
2 -> Ana Figueiredo
3 -> Ricardo Figueiredo
4 -> Margarida Figueiredo
5 -> Ricardo Figueiredo
*/

Console.WriteLine("All lines with repeated data");
PersonsLst.getAllRepeated(z => new { z.Name, z.Surname })
.ToList()
.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
All lines with repeated data
1 -> Ricardo Figueiredo
3 -> Ricardo Figueiredo
5 -> Ricardo Figueiredo
*/
Console.WriteLine("Only Repeated more than once");
PersonsLst.getMoreThanOnceRepeated(z => new { z.Name, z.Surname })
.ToList()
.ForEach(z => Console.WriteLine("{0} -> {1} {2}", z.Id, z.Name, z.Surname));
/* OUTPUT:
Only Repeated more than once
3 -> Ricardo Figueiredo
5 -> Ricardo Figueiredo
*/
}




5) var unique = list.GroupBy(x => x.Key).All(g => g.Count() == 1);

6)

private static void Main()
{
List<Employee> empList = new List<Employee>();

empList.Add(new Employee() { ID = 1, FName = "John", Age=23, Sex='M' });
empList.Add(new Employee() { ID = 2, FName = "Mary", Age = 25, Sex = 'F' });
empList.Add(new Employee() { ID = 3, FName = "Amber", Age = 23, Sex = 'M' });
empList.Add(new Employee() { ID = 4, FName = "Kathy", Age=25, Sex='M'});
empList.Add(new Employee() { ID = 5, FName = "Lena", Age=27, Sex='F'});
empList.Add(new Employee() { ID = 6, FName = "John", Age = 28, Sex = 'M' });
empList.Add(new Employee() { ID = 7, FName = "Kathy", Age = 27, Sex = 'F' });
empList.Add(new Employee() { ID = 8, FName = "John", Age = 28, Sex = 'M' });

var dup = empList
.GroupBy(x => new { x.FName })
.Select(group => new { Name = group.Key, Count = group.Count() })
.OrderByDescending(x => x.Count);

foreach (var x in dup)
{
Response.Write(x.Count + " " + x.Name);
}
}


class Employee
{
public int ID { get; set; }
public string FName { get; set; }
public int Age { get; set; }
public char Sex { get; set; }
}
7)
string[] array = { "First", "Second", "Third", "First", "Third" };
var i= CheckforDuplicates(array);

public bool CheckforDuplicates(string[] array)
{
var duplicates = array
.GroupBy(p => p)
.Where(g => g.Count() > 1)
.Select(g => g.Key);


return (duplicates.Count() > 0);



}
which one i should follow. thanks

Continue reading...