C++(15)——关联容器和海量数据查重

关联容器

关联容器也是用来存放数据的，但是和顺序容器有很大的区别。
关联容器的底层数据结构是红黑树

分类

有序关联容
set:单集合容器
multiset:多集合容器
map:单映射容器
multimap:多重映射容器

无序关联容器
unordered_set 单重集合
unordered_multiset 多重集合
unordered_map 单重映射表
unordered_multimap 多重映射表

方法

find查找函数：二分查找
count函数：返回容器中值为x的元素个数
clear函数：清空容器元素

set

set单集合，存放元素value，不允许重复，不允许修改，按照顺序存储。
增删改查
插入元素 insert(val) 将元素val插入set，插入后会自动调整排序
给指定位置插入元素 insert(index,val) 位置无效，只是为了和前面顺序容器兼容，你传入了位置，不一样插入指定的位置，因为存在自动调整
插入区间元素 insert(first,last) 在set中插入（first，last）区间的元素

查询依旧是采用迭代器或者for each

删除使用find方法查找元素并删除

int main()
{
	unordered_set<int>set1;
	for (int i = 0;i < 50;++i)
	{
		set1.insert(rand() % 100);
	}
	cout << set1.size() << endl;
	cout << set1.count(1) << endl;
	for (int i = 0;i < 50;++i)
	{
		set1.insert(i);
	}
	auto it1 = set1.find(20);
	//若20存在，返回值为20位置的迭代器，若不存在，则返回末尾元素的迭代器
	unordered_set<int>::iterator fit = find(set1.begin(), set1.end(), 41);
	//若失败返回末尾元素后继位置迭代器
	it1 = set1.begin();
	for (int i = 0;i < set1.size();i++)
	{
		cout <<  *it1 << " ";
		it1++;
	}
	cout << endl<<set1.count(1) << endl;

	
		return 0;
}

//有序关联容器
class Student
{
public:
	Student(int id = 0, string name = nullptr)
		:_id(id), _name(name)
	{}
	bool operator<(const Student &stu)const
	{
		return this->_id < stu._id;
	}
private:
	int _id;
	string _name;
	friend ostream& operator<<(ostream &out, const Student &stu);

};
ostream& operator<<(ostream &out, const Student &stu)
{
	out << "id: " << stu._id << "name: " << stu._name << endl;
	return out;
}
int main()
{
	set<int>set1;
	for (int i = 0;i < 20;++i)
	{
		set1.insert(rand() % 100);
	}
	for (int v : set1)
	{
		cout << v << " ";
	}
	cout << endl;


	multiset<Student>set2;
	set2.insert(Student(1, "wyl"));
	set2.insert(Student(2, "yyz"));
	set2.insert(Student(1, "wyl"));
	for (auto it = set2.begin();it != set2.end();it++)
	{
		cout << *it << endl;
	}
	return 0;
}

**总结：
1、单集合容器不允许关键字重复，多集合容器允许重复
2、在容器中不能修改元素
3、有序关联容器会进行排序，无序关联容器不会进行排序
**

map

map底层存放的是键值对[key，value]

struct std::pqir<int const,int>
	{
		int const key; 
	    int value;
	}

增

map1.insert(make_pair(1000, "wyl"));
map1.insert({ 1001,"wyl1" });
map1.insert(pair<int,string>(10, "we"));

map的下标运算符重载函数分为两步：
1、查询是否存在
2、如果不存在则插入一对键值对。
其余操作和set无差别

class Student
{
public:
	Student(int id = 0, string name = nullptr)
		:_id(id), _name(name)
	{}
	bool operator<(const Student &stu)const
	{
		return this->_id < stu._id;
	}
private:
	int _id;
	string _name;
	friend ostream& operator<<(ostream &out, const Student &stu);

};
ostream& operator<<(ostream &out, const Student &stu)
{
	out << "id: " << stu._id << "name: " << stu._name << endl;
	return out;
}
int main()
{
	map<int, Student>map1;
	map1.insert({ 1000,Student(1000,"wyl1") });
	map1.insert({ 1001,Student(1001,"wyl2") });
	map1.insert({ 1002,Student(1002,"wyl3") });
	map1.insert({ 1003,Student(1003,"wyl4") });
	cout << map1[1000] << endl;
	auto it5 = map1.find(1000);
	cout << it5->first<<it5->second << endl;
	it5 = map1.begin();
	for (;it5 != map1.end();it5++)
	{
		cout << "key:" << it5->first << "value:" << it5->second << endl;
	}

	unordered_map<int, string>map1;
	map1.insert(make_pair(1000, "wyl"));
	map1.insert({ 1001,"wyl1" });
	map1.insert(pair<int,string>(10, "we"));
	//返回键值表的个数
	cout << map1.size() << endl;
	cout << map1[1000] << endl;
	map1.erase(1001);
	//operator[]
	//1、查询
	//2、如果key不存在，他会插入一对数据[key,string()]
	map1[2000] = "王煜龙";
	cout << map1[2000] << endl;
	auto it2 = map1.find(1000);
	cout << it2->first << it2->second << endl;
	it2 = map1.begin();
	for (;it2 != map1.end();it2++)
	{
		cout << it2->first << ":" << it2->second << endl;
	}
		return 0;
}

海量数据查重去重

#define SIZE 100
int main()
{
	int arr[SIZE] = { 0 };
	for (int i = 0;i < SIZE;++i)
	{
		arr[i] = rand() % 10;
	}
	unordered_map<int, int>map1;
	for (int k : arr)
	{
		/*
		auto it = map1.find(k);
		if (it == map1.end())
		{
			map1.insert({ k,1 });
		}
		else
		{
			it->second++;
		}
		*/
		map1[k]++;
	}
	for (const pair<int, int>&p : map1)
	{
		
		if (p.second > 1)
		{
			cout << "key:" << p.first << "count:" << p.second << endl;
		}
		
	}
	auto it3 = map1.begin();
	for (;it3 != map1.end();it3++)
	{
		cout << "key:" << it3->first << "count:" << it3->second << endl;
	}

	//在上整数中去重
	unordered_set<int>set;
	for (int k : arr)
	{
		set.insert(k);

	}
	for (int k : set)
	{
		cout << k << " ";
	}
	return 0;
}