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

如果您需要通过以下方式进行多组:


    const populate = (entireObj, keys, item) => {
    let keysClone = [...keys],
        currentKey = keysClone.shift();

    if (keysClone.length > 0) {
        entireObj[item[currentKey]] = entireObj[item[currentKey]] || {}
        populate(entireObj[item[currentKey]], keysClone, item);
    } else {
        (entireObj[item[currentKey]] = entireObj[item[currentKey]] || []).push(item);
    }
}

export const groupBy = (list, key) => {
    return list.reduce(function (rv, x) {

        if (typeof key === 'string') (rv[x[key]] = rv[x[key]] || []).push(x);

        if (typeof key === 'object' && key.length) populate(rv, key, x);

        return rv;

    }, {});
}

const myPets = [
    {name: 'yaya', type: 'cat', color: 'gray'},
    {name: 'bingbang', type: 'cat', color: 'sliver'},
    {name: 'junior-bingbang', type: 'cat', color: 'sliver'},
    {name: 'jindou', type: 'cat', color: 'golden'},
    {name: 'dahuzi', type: 'dog', color: 'brown'},
];

// run 
groupBy(myPets, ['type', 'color']));

// you will get object like: 

const afterGroupBy = {
    "cat": {
        "gray": [
            {
                "name": "yaya",
                "type": "cat",
                "color": "gray"
            }
        ],
        "sliver": [
            {
                "name": "bingbang",
                "type": "cat",
                "color": "sliver"
            },
            {
                "name": "junior-bingbang",
                "type": "cat",
                "color": "sliver"
            }
        ],
        "golden": [
            {
                "name": "jindou",
                "type": "cat",
                "color": "golden"
            }
        ]
    },
    "dog": {
        "brown": [
            {
                "name": "dahuzi",
                "type": "dog",
                "color": "brown"
            }
        ]
    }
};

其他回答

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}
]

GroupBy one liner,ES2021解决方案

const groupBy = (x,f)=>x.reduce((a,b,i)=>((a[f(b,i,x)]||=[]).push(b),a),{});

TypeScript(类型脚本)

const groupBy = <T>(array: T[], predicate: (value: T, index: number, array: T[]) => string) =>
  array.reduce((acc, value, index, array) => {
    (acc[predicate(value, index, array)] ||= []).push(value);
    return acc;
  }, {} as { [key: string]: T[] });

示例

const groupBy = (x,f)=>x.reduce((a,b,i)=>((a[f(b,i,x)]||=[]).push(b),a),{});
// f -> should must return string/number because it will be use as key in object

// for demo

groupBy([1, 2, 3, 4, 5, 6, 7, 8, 9], v => (v % 2 ? "odd" : "even"));
// { odd: [1, 3, 5, 7, 9], even: [2, 4, 6, 8] };
const colors = [
  "Apricot",
  "Brown",
  "Burgundy",
  "Cerulean",
  "Peach",
  "Pear",
  "Red",
];

groupBy(colors, v => v[0]); // group by colors name first letter
// {
//   A: ["Apricot"],
//   B: ["Brown", "Burgundy"],
//   C: ["Cerulean"],
//   P: ["Peach", "Pear"],
//   R: ["Red"],
// };
groupBy(colors, v => v.length); // group by length of color names
// {
//   3: ["Red"],
//   4: ["Pear"],
//   5: ["Brown", "Peach"],
//   7: ["Apricot"],
//   8: ["Burgundy", "Cerulean"],
// }

const data = [
  { comment: "abc", forItem: 1, inModule: 1 },
  { comment: "pqr", forItem: 1, inModule: 1 },
  { comment: "klm", forItem: 1, inModule: 2 },
  { comment: "xyz", forItem: 1, inModule: 2 },
];

groupBy(data, v => v.inModule); // group by module
// {
//   1: [
//     { comment: "abc", forItem: 1, inModule: 1 },
//     { comment: "pqr", forItem: 1, inModule: 1 },
//   ],
//   2: [
//     { comment: "klm", forItem: 1, inModule: 2 },
//     { comment: "xyz", forItem: 1, inModule: 2 },
//   ],
// }

groupBy(data, x => x.forItem + "-" + x.inModule); // group by module with item
// {
//   "1-1": [
//     { comment: "abc", forItem: 1, inModule: 1 },
//     { comment: "pqr", forItem: 1, inModule: 1 },
//   ],
//   "1-2": [
//     { comment: "klm", forItem: 1, inModule: 2 },
//     { comment: "xyz", forItem: 1, inModule: 2 },
//   ],
// }

按映射分组

const groupByToMap = (x, f) =>
  x.reduce((a, b, i, x) => {
    const k = f(b, i, x);
    a.get(k)?.push(b) ?? a.set(k, [b]);
    return a;
  }, new Map());

TypeScript(类型脚本)

const groupByToMap = <T, Q>(array: T[], predicate: (value: T, index: number, array: T[]) => Q) =>
  array.reduce((map, value, index, array) => {
    const key = predicate(value, index, array);
    map.get(key)?.push(value) ?? map.set(key, [value]);
    return map;
  }, new Map<Q, T[]>());

我从underscore.js fiddler那里借用了这个方法

window.helpers=(function (){
    var lookupIterator = function(value) {
        if (value == null){
            return function(value) {
                return value;
            };
        }
        if (typeof value === 'function'){
                return value;
        }
        return function(obj) {
            return obj[value];
        };
    },
    each = function(obj, iterator, context) {
        var breaker = {};
        if (obj == null) return obj;
        if (Array.prototype.forEach && obj.forEach === Array.prototype.forEach) {
            obj.forEach(iterator, context);
        } else if (obj.length === +obj.length) {
            for (var i = 0, length = obj.length; i < length; i++) {
                if (iterator.call(context, obj[i], i, obj) === breaker) return;
            }
        } else {
            var keys = []
            for (var key in obj) if (Object.prototype.hasOwnProperty.call(obj, key)) keys.push(key)
            for (var i = 0, length = keys.length; i < length; i++) {
                if (iterator.call(context, obj[keys[i]], keys[i], obj) === breaker) return;
            }
        }
        return obj;
    },
    // An internal function used for aggregate "group by" operations.
    group = function(behavior) {
        return function(obj, iterator, context) {
            var result = {};
            iterator = lookupIterator(iterator);
            each(obj, function(value, index) {
                var key = iterator.call(context, value, index, obj);
                behavior(result, key, value);
            });
            return result;
        };
    };

    return {
      groupBy : group(function(result, key, value) {
        Object.prototype.hasOwnProperty.call(result, key) ? result[key].push(value) :              result[key] = [value];
        })
    };
})();

var arr=[{a:1,b:2},{a:1,b:3},{a:1,b:1},{a:1,b:2},{a:1,b:3}];
 console.dir(helpers.groupBy(arr,"b"));
 console.dir(helpers.groupBy(arr,function (el){
   return el.b>2;
 }));

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;)

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”]));