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

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}
]

其他回答

常量动物=[{type:'狗',品种:“水坑”},{type:'狗',品种:“拉布拉多”},{类型:'cat',品种:“暹罗”},{type:'狗',品种:“法国斗牛犬”},{类型:'cat',品种:'泥'}];var groupBy=(arr,prop)=>{return arr.reduce((objs,obj)=>{const key=obj[prop];if(键){让fi=objs.findIndex(x=>x.key==key);如果(fi>=0){objs[fi].values=[…objs[fi].values,obj];}其他{对象.推送({key:键,值:[obj]})}}返回对象;}, []);}console.log(groupBy(动物,“类型”))

下面的函数允许对任意字段进行groupBy(和求和值-OP需要的)。在解决方案中,我们定义cmp函数来根据分组字段比较两个对象。在设w=。。。我们创建子集对象x字段的副本。在y[sumBy]=+y[sumBy]+(+x[sumBy])中,我们使用“+”将字符串转换为数字。

function groupBy(data, fields, sumBy='Value') {
  let r=[], cmp= (x,y) => fields.reduce((a,b)=> a && x[b]==y[b], true);
  data.forEach(x=> {
    let y=r.find(z=>cmp(x,z));
    let w= [...fields,sumBy].reduce((a,b) => (a[b]=x[b],a), {})
    y ? y[sumBy]=+y[sumBy]+(+x[sumBy]) : r.push(w);
  });
  return r;
}

常量d=[{阶段:“阶段1”,步骤:“步骤1”,任务:“任务1”,值:“5”},{阶段:“阶段1”,步骤:“步骤1”,任务:“任务2”,值:“10”},{阶段:“阶段1”,步骤:“步骤2”,任务:“任务1”,值:“15”},{阶段:“阶段1”,步骤:“步骤2”,任务:“任务2”,值:“20”},{阶段:“阶段2”,步骤:“步骤1”,任务:“任务1”,值:“25”},{阶段:“阶段2”,步骤:“步骤1”,任务:“任务2”,值:“30”},{阶段:“阶段2”,步骤:“步骤2”,任务:“任务1”,值:“35”},{阶段:“阶段2”,步骤:“步骤2”,任务:“任务2”,值:“40”}];函数groupBy(数据,字段,sumBy='Value'){设r=[],cmp=(x,y)=>fields.reduce((a,b)=>a&&x[b]==y[b],true);data.forEach(x=>{设y=r.find(z=>cmp(x,z));设w=[…fields,sumBy].reduce((a,b)=>(a[b]=x[b],a),{})yy[sumBy]=+y[sumBy]+(+x[sumBy]):r.push(w);});返回r;}//测试let p=(t,o)=>console.log(t,JSON.stringify(o));console.log('GROUP BY:');p(“相”,组By(d,[“相”]));p(“步骤”,组By(d,[“步骤”]));p(“阶段-步骤”,组By(d,[“阶段”,“步骤”]));p(“阶段任务”,groupBy(d,[“阶段”,“任务”]));p(“步骤任务”,groupBy(d,[“步骤”,“任务”]));p(“阶段-步骤-任务”,groupBy(d,[“阶段”,“步骤”,“任务”]));

使用linq.js可能更容易做到这一点,它是linq在JavaScript(DEMO)中的真正实现:

var linq = Enumerable.From(data);
var result =
    linq.GroupBy(function(x){ return x.Phase; })
        .Select(function(x){
          return {
            Phase: x.Key(),
            Value: x.Sum(function(y){ return y.Value|0; })
          };
        }).ToArray();

结果:

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

或者,更简单地使用基于字符串的选择器(DEMO):

linq.GroupBy("$.Phase", "",
    "k,e => { Phase:k, Value:e.Sum('$.Value|0') }").ToArray();

具有排序功能

export const groupBy = function groupByArray(xs, key, sortKey) {
      return xs.reduce(function(rv, x) {
        let v = key instanceof Function ? key(x) : x[key];
        let el = rv.find(r => r && r.key === v);

        if (el) {
          el.values.push(x);
          el.values.sort(function(a, b) {
            return a[sortKey].toLowerCase().localeCompare(b[sortKey].toLowerCase());
          });
        } else {
          rv.push({ key: v, values: [x] });
        }

        return rv;
      }, []);
    };

示例:

var state = [
    {
      name: "Arkansas",
      population: "2.978M",
      flag:
  "https://upload.wikimedia.org/wikipedia/commons/9/9d/Flag_of_Arkansas.svg",
      category: "city"
    },{
      name: "Crkansas",
      population: "2.978M",
      flag:
        "https://upload.wikimedia.org/wikipedia/commons/9/9d/Flag_of_Arkansas.svg",
      category: "city"
    },
    {
      name: "Balifornia",
      population: "39.14M",
      flag:
        "https://upload.wikimedia.org/wikipedia/commons/0/01/Flag_of_California.svg",
      category: "city"
    },
    {
      name: "Florida",
      population: "20.27M",
      flag:
        "https://upload.wikimedia.org/wikipedia/commons/f/f7/Flag_of_Florida.svg",
      category: "airport"
    },
    {
      name: "Texas",
      population: "27.47M",
      flag:
        "https://upload.wikimedia.org/wikipedia/commons/f/f7/Flag_of_Texas.svg",
      category: "landmark"
    }
  ];
console.log(JSON.stringify(groupBy(state,'category','name')));

想象一下,你有这样的东西:

〔{id:1,cat:'sedan'},{id:2,cat:'sport‘},{id:3,cat:'sport‘},{id:4,cat:'sadan‘}〕

通过这样做:const categories=[…new Set(cars.map((car)=>car.cat))]

你会得到这个:[“sadan”,“port”]

说明:1.首先,我们通过传递一个数组来创建一个新的Set。由于Set仅允许唯一值,因此将删除所有重复项。

现在重复项消失了,我们将使用扩展运算符将其转换回数组。。。

设置文档:https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Set排列运算符文档:https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Spread_syntax