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

我对公认的答案进行了扩展,包括按多个财产分组,然后再加上,使其完全起作用,没有变异。观看演示https://stackblitz.com/edit/typescript-ezydzv

export interface Group {
  key: any;
  items: any[];
}

export interface GroupBy {
  keys: string[];
  thenby?: GroupBy;
}

export const groupBy = (array: any[], grouping: GroupBy): Group[] => {
  const keys = grouping.keys;
  const groups = array.reduce((groups, item) => {
    const group = groups.find(g => keys.every(key => item[key] === g.key[key]));
    const data = Object.getOwnPropertyNames(item)
      .filter(prop => !keys.find(key => key === prop))
      .reduce((o, key) => ({ ...o, [key]: item[key] }), {});
    return group
      ? groups.map(g => (g === group ? { ...g, items: [...g.items, data] } : g))
      : [
          ...groups,
          {
            key: keys.reduce((o, key) => ({ ...o, [key]: item[key] }), {}),
            items: [data]
          }
        ];
  }, []);
  return grouping.thenby ? groups.map(g => ({ ...g, items: groupBy(g.items, grouping.thenby) })) : groups;
};

为了补充Scott Sauyet的答案,一些人在评论中询问如何使用他的函数按值1、值2等分组,而不是仅对一个值分组。

只需编辑他的求和函数:

DataGrouper.register("sum", function(item) {
    return _.extend({}, item.key,
        {VALUE1: _.reduce(item.vals, function(memo, node) {
        return memo + Number(node.VALUE1);}, 0)},
        {VALUE2: _.reduce(item.vals, function(memo, node) {
        return memo + Number(node.VALUE2);}, 0)}
    );
});

保持主组(DataGrouper)不变:

var DataGrouper = (function() {
    var has = function(obj, target) {
        return _.any(obj, function(value) {
            return _.isEqual(value, target);
        });
    };

    var keys = function(data, names) {
        return _.reduce(data, function(memo, item) {
            var key = _.pick(item, names);
            if (!has(memo, key)) {
                memo.push(key);
            }
            return memo;
        }, []);
    };

    var group = function(data, names) {
        var stems = keys(data, names);
        return _.map(stems, function(stem) {
            return {
                key: stem,
                vals:_.map(_.where(data, stem), function(item) {
                    return _.omit(item, names);
                })
            };
        });
    };

    group.register = function(name, converter) {
        return group[name] = function(data, names) {
            return _.map(group(data, names), converter);
        };
    };

    return group;
}());

我不认为给出的答案是对问题的回应,我认为以下内容应回答第一部分:

常量arr=[{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”}]const groupBy=(key)=>arr.sort((a,b)=>a[key].localeCompare(b[key])).reduce((total,currentValue)=>{const newTotal=总计;如果(总长度&&总计[total.length-1][key]==当前值[key])新总计[total.length-1]={…总计[总长度-1],…当前值,值:parseInt(total[total.length-1].Value)+parseInt(currentValue.Value,};else newTotal[total.length]=当前值;return newTotal;}, []);console.log(groupBy(“阶段”));//=>[{阶段:“阶段1”,值:50},{阶段“阶段2”,值130}]console.log(groupBy(“步骤”));//=>[{步骤:“步骤1”,值:70},{步骤“步骤2”,值为110}]

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;)

var newArr = data.reduce((acc, cur) => {
    const existType = acc.find(a => a.Phase === cur.Phase);
    if (existType) {
        existType.Value += +cur.Value;
        return acc;
    }

    acc.push({
        Phase: cur.Phase,
        Value: +cur.Value
    });
    return acc;
}, []);