按数组中的对象分组最有效的方法是什么?

例如,给定此对象数组:

[ 
    { Phase: "Phase 1", Step: "Step 1", Task: "Task 1", Value: "5" },
    { Phase: "Phase 1", Step: "Step 1", Task: "Task 2", Value: "10" },
    { Phase: "Phase 1", Step: "Step 2", Task: "Task 1", Value: "15" },
    { Phase: "Phase 1", Step: "Step 2", Task: "Task 2", Value: "20" },
    { Phase: "Phase 2", Step: "Step 1", Task: "Task 1", Value: "25" },
    { Phase: "Phase 2", Step: "Step 1", Task: "Task 2", Value: "30" },
    { Phase: "Phase 2", Step: "Step 2", Task: "Task 1", Value: "35" },
    { Phase: "Phase 2", Step: "Step 2", Task: "Task 2", Value: "40" }
]

我正在表格中显示这些信息。我想通过不同的方法进行分组,但我想对值求和。

我将Undercore.js用于其groupby函数,这很有用,但并不能完成全部任务,因为我不希望它们“拆分”,而是“合并”,更像SQL groupby方法。

我要找的是能够合计特定值(如果需要)。

因此,如果我按阶段分组,我希望收到:

[
    { Phase: "Phase 1", Value: 50 },
    { Phase: "Phase 2", Value: 130 }
]

如果我组了阶段/步骤,我会收到:

[
    { Phase: "Phase 1", Step: "Step 1", Value: 15 },
    { Phase: "Phase 1", Step: "Step 2", Value: 35 },
    { Phase: "Phase 2", Step: "Step 1", Value: 55 },
    { Phase: "Phase 2", Step: "Step 2", Value: 75 }
]

是否有一个有用的脚本,或者我应该坚持使用Undercore.js,然后遍历生成的对象,自己计算总数?


当前回答

从@mortb、@jmarceli的回答和这篇文章中,

我利用JSON.stringify()作为分组依据的PRIMITIVE VALUE多列的标识。

无第三方

function groupBy(list, keyGetter) {
    const map = new Map();
    list.forEach((item) => {
        const key = keyGetter(item);
        if (!map.has(key)) {
            map.set(key, [item]);
        } else {
            map.get(key).push(item);
        }
    });
    return map;
}

const pets = [
    {type:"Dog", age: 3, name:"Spot"},
    {type:"Cat", age: 3, name:"Tiger"},
    {type:"Dog", age: 4, name:"Rover"}, 
    {type:"Cat", age: 3, name:"Leo"}
];

const grouped = groupBy(pets,
pet => JSON.stringify({ type: pet.type, age: pet.age }));

console.log(grouped);

使用Lodash第三方

const pets = [
    {type:"Dog", age: 3, name:"Spot"},
    {type:"Cat", age: 3, name:"Tiger"},
    {type:"Dog", age: 4, name:"Rover"}, 
    {type:"Cat", age: 3, name:"Leo"}
];

let rslt = _.groupBy(pets, pet => JSON.stringify(
 { type: pet.type, age: pet.age }));

console.log(rslt);

其他回答

我会检查一下lodash组,它似乎正是你想要的。它也很轻,非常简单。

Fiddle示例:https://jsfiddle.net/r7szvt5k/

如果数组名称为arr,则带有lodash的groupBy仅为:

import groupBy from 'lodash/groupBy';
// if you still use require:
// const groupBy = require('lodash/groupBy');

const a = groupBy(arr, function(n) {
  return n.Phase;
});
// a is your array grouped by Phase attribute

我想建议一下我的方法。首先,分开分组和聚合。让我们声明原型“groupby”函数。它需要另一个函数为要分组的每个数组元素生成“哈希”字符串。

Array.prototype.groupBy = function(hash){
  var _hash = hash ? hash : function(o){return o;};

  var _map = {};
  var put = function(map, key, value){
    if (!map[_hash(key)]) {
        map[_hash(key)] = {};
        map[_hash(key)].group = [];
        map[_hash(key)].key = key;

    }
    map[_hash(key)].group.push(value); 
  }

  this.map(function(obj){
    put(_map, obj, obj);
  });

  return Object.keys(_map).map(function(key){
    return {key: _map[key].key, group: _map[key].group};
  });
}

分组完成后,您可以根据需要聚合数据

data.groupBy(function(o){return JSON.stringify({a: o.Phase, b: o.Step});})
    /* aggreagating */
    .map(function(el){ 
         var sum = el.group.reduce(
           function(l,c){
             return l + parseInt(c.Value);
           },
           0
         );
         el.key.Value = sum; 
         return el.key;
    });

一般来说,它是有效的。我已经在chrome控制台中测试了这段代码。并随时改进和发现错误;)

我已经改进了答案。此函数获取组字段数组并返回分组对象,该对象的键也是组字段的对象。

function(xs, groupFields) {
        groupFields = [].concat(groupFields);
        return xs.reduce(function(rv, x) {
            let groupKey = groupFields.reduce((keyObject, field) => {
                keyObject[field] = x[field];
                return keyObject;
            }, {});
            (rv[JSON.stringify(groupKey)] = rv[JSON.stringify(groupKey)] || []).push(x);
            return rv;
        }, {});
    }



let x = [
{
    "id":1,
    "multimedia":false,
    "language":["tr"]
},
{
    "id":2,
    "multimedia":false,
    "language":["fr"]
},
{
    "id":3,
    "multimedia":true,
    "language":["tr"]
},
{
    "id":4,
    "multimedia":false,
    "language":[]
},
{
    "id":5,
    "multimedia":false,
    "language":["tr"]
},
{
    "id":6,
    "multimedia":false,
    "language":["tr"]
},
{
    "id":7,
    "multimedia":false,
    "language":["tr","fr"]
}
]

groupBy(x, ['multimedia','language'])

//{
//{"multimedia":false,"language":["tr"]}: Array(3), 
//{"multimedia":false,"language":["fr"]}: Array(1), 
//{"multimedia":true,"language":["tr"]}: Array(1), 
//{"multimedia":false,"language":[]}: Array(1), 
//{"multimedia":false,"language":["tr","fr"]}: Array(1)
//}

发帖是因为即使这个问题已经7年了,我仍然没有看到一个符合原始标准的答案:

我不希望它们“拆分”,而是“合并”,更像SQL组方法

我最初发表这篇文章是因为我想找到一种方法来减少对象数组(例如,当您从csv中读取时创建的数据结构),并通过给定索引聚合以生成相同的数据结构。我正在寻找的返回值是另一个对象数组,而不是我在这里看到的嵌套对象或映射。

下面的函数获取一个数据集(对象数组)、一个索引列表(数组)和一个reducer函数,并将reducer功能应用于索引的结果作为一个对象数组返回。

function agg(data, indices, reducer) {

  // helper to create unique index as an array
  function getUniqueIndexHash(row, indices) {
    return indices.reduce((acc, curr) => acc + row[curr], "");
  }

  // reduce data to single object, whose values will be each of the new rows
  // structure is an object whose values are arrays
  // [{}] -> {{}}
  // no operation performed, simply grouping
  let groupedObj = data.reduce((acc, curr) => {
    let currIndex = getUniqueIndexHash(curr, indices);

    // if key does not exist, create array with current row
    if (!Object.keys(acc).includes(currIndex)) {
      acc = {...acc, [currIndex]: [curr]}
    // otherwise, extend the array at currIndex
    } else {
      acc = {...acc, [currIndex]: acc[currIndex].concat(curr)};
    }

    return acc;
  }, {})

  // reduce the array into a single object by applying the reducer
  let reduced = Object.values(groupedObj).map(arr => {
    // for each sub-array, reduce into single object using the reducer function
    let reduceValues = arr.reduce(reducer, {});

    // reducer returns simply the aggregates - add in the indices here
    // each of the objects in "arr" has the same indices, so we take the first
    let indexObj = indices.reduce((acc, curr) => {
      acc = {...acc, [curr]: arr[0][curr]};
      return acc;
    }, {});

    reduceValues = {...indexObj, ...reduceValues};


    return reduceValues;
  });


  return reduced;
}

我将创建一个返回count(*)和sum(Value)的reducer:

reducer = (acc, curr) => {
  acc.count = 1 + (acc.count || 0);
  acc.value = +curr.Value + (acc.value|| 0);
  return acc;
}

最后,使用我们的reducer将agg函数应用于原始数据集会生成一个应用了适当聚合的对象数组:

agg(tasks, ["Phase"], reducer);
// yields:
Array(2) [
  0: Object {Phase: "Phase 1", count: 4, value: 50}
  1: Object {Phase: "Phase 2", count: 4, value: 130}
]

agg(tasks, ["Phase", "Step"], reducer);
// yields:
Array(4) [
  0: Object {Phase: "Phase 1", Step: "Step 1", count: 2, value: 15}
  1: Object {Phase: "Phase 1", Step: "Step 2", count: 2, value: 35}
  2: Object {Phase: "Phase 2", Step: "Step 1", count: 2, value: 55}
  3: Object {Phase: "Phase 2", Step: "Step 2", count: 2, value: 75}
]

让我们生成一个通用的Array.protocol.groupBy()工具。为了多样化,让我们在递归方法上使用ES6 fancyty扩展运算符进行Haskell式模式匹配。同样,让我们让Array.prototype.groupBy()接受一个回调,该回调将项(e)、索引(i)和应用的数组(a)作为参数。

Array.prototype.groupBy=函数(cb){返回函数迭代([x,…xs],i=0,r=[[],[]]){cb(x,i,[x,…xs])?(r[0].推(x),r):(r[1].推(x),r);是否返回xs.length?迭代(xs,++i,r):r;}(本);};var arr=[0,1,2,3,4,5,6,7,8,9],res=arr.groupBy(e=>e<5);console.log(res);