前言

数组去重其实是个很常见的面试题，比如在数据分析中，有时候因为一些原因会有重复的记录，因此需要去重。如果重复的那些行是每一列懂相同的，删除多余的行只保留相同行中的一行就可以了。

其实不管前端还是后端，都是可以进行数组去重的，但数据处理一般都在后端，所以本文对List对象去重的方法进行总结和性能分析。

一、List对象去重的方法总结

1.循环去除重复

使用循环去除重复，需要新实例化一个List<T>，再循环判断数组对象里是否有这个对象，如果有没有重复添加到这个集合对象，否则不添加。

1、模型类代码：

public class Customer
{
    public int id { get; set; }
    public string name { get; set; }
    public string email { get; set; }
    public int age { get; set; }
}

2、主程序代码：

using ConsoleTest;
using System.Diagnostics;

Stopwatch swatch = new Stopwatch();
swatch.Start(); //计时开始

var rel = new List<Customer>();//新new一个对象，
foreach (var item in GetCustomer())
{   //判断是否存在，不存在添加
    if (rel.Where(w => w.id == item.id & w.name == item.name && w.age == item.age && w.email == item.email).Count() == 0)
        rel.Add(item);//不存在新增
}

foreach (var item in rel)
{ 
    Console.WriteLine(item.name); 
}


swatch.Stop(); //计时结束
string time = swatch.ElapsedMilliseconds.ToString(); //获取代码段执行时间

Console.WriteLine($"=========代码执行时间：{time}=============");
swatch.Reset(); //第二次计时时进行重置


//获取数据
static List<Customer> GetCustomer()
{
    List<Customer> list = new List<Customer>();
    list.Add(new Customer { id = 1, name = "刘德华", age = 56, email = "ldh@net.cn" });
    list.Add(new Customer { id = 2, name = "张学友", age = 52, email = "zxy@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    list.Add(new Customer { id = 4, name = "郭富城", age = 60, email = "gfc@net.cn" });
    list.Add(new Customer { id = 4, name = "古天乐", age = 55, email = "gtl@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    return list;
}

3、运行程序：

可以看出代码执行时间：34

2.使用Linq中GroupBy去重

linq是个好东西，对于对象的操作很方便，GroupBy类似数据库中的group by。这个例子就不需要循环了，直接一句代码解决，简便多了。

1、模型类代码：

public class Customer
{
    public int id { get; set; }
    public string name { get; set; }
    public string email { get; set; }
    public int age { get; set; }
}

2、主程序代码：

using ConsoleTest;
using System.Diagnostics;

Stopwatch swatch = new Stopwatch();
swatch.Start(); //计时开始

var rel = GetCustomer().GroupBy(g => new { g.id, g.name, g.age, g.email });
foreach (var item in rel)
{
    Console.WriteLine(item.Key.name);
}


swatch.Stop(); //计时结束
string time = swatch.ElapsedMilliseconds.ToString(); //获取代码段执行时间

Console.WriteLine($"=========代码执行时间：{time}=============");
swatch.Reset(); //第二次计时时进行重置


//获取数据
static List<Customer> GetCustomer()
{
    List<Customer> list = new List<Customer>();
    list.Add(new Customer { id = 1, name = "刘德华", age = 56, email = "ldh@net.cn" });
    list.Add(new Customer { id = 2, name = "张学友", age = 52, email = "zxy@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    list.Add(new Customer { id = 4, name = "郭富城", age = 60, email = "gfc@net.cn" });
    list.Add(new Customer { id = 4, name = "古天乐", age = 55, email = "gtl@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    return list;
}

3、运行程序：

可以看出代码执行时间：35

3.使用Linq中Distinct去重

Distinct跟数据库中的Distinct还是有一定的区别，对于对象集合去除重复需要自定义客户对象的Comparer方法。

1、模型类代码：

public class Customer
{
    public int id { get; set; }
    public string name { get; set; }
    public string email { get; set; }
    public int age { get; set; }
}

2、比较器：

//需要继承IEqualityComparer，先判断第一个字段，如果有重复再做对比。
public class CustomerComparer : IEqualityComparer<Customer>
{
    public bool Equals(Customer x, Customer y)
    {
        if (x == null)
            return y == null;
        return x.id == y.id && x.name == y.name && x.age == y.age && x.email == y.email;
    }
    public int GetHashCode(Customer obj)
    {
        if (obj == null)
            return 0;
        return obj.id.GetHashCode();
    }
}

3、主程序代码：

using ConsoleTest;
using System.Diagnostics;

Stopwatch swatch = new Stopwatch();
swatch.Start(); //计时开始

var rel = GetCustomer().Distinct(new CustomerComparer());
foreach (var item in rel)
{
    Console.WriteLine(item.name);
}


swatch.Stop(); //计时结束
string time = swatch.ElapsedMilliseconds.ToString(); //获取代码段执行时间

Console.WriteLine($"=========代码执行时间：{time}=============");
swatch.Reset(); //第二次计时时进行重置


//获取数据
static List<Customer> GetCustomer()
{
    List<Customer> list = new List<Customer>();
    list.Add(new Customer { id = 1, name = "刘德华", age = 56, email = "ldh@net.cn" });
    list.Add(new Customer { id = 2, name = "张学友", age = 52, email = "zxy@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    list.Add(new Customer { id = 4, name = "郭富城", age = 60, email = "gfc@net.cn" });
    list.Add(new Customer { id = 4, name = "古天乐", age = 55, email = "gtl@net.cn" });
    list.Add(new Customer { id = 3, name = "黎明", age = 58, email = "lm@net.cn" });
    return list;
}

3、运行程序：

可以看出代码执行时间：25

总结

综上测试，Distinct是效率性能最高的。