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

这里有一个使用ES6的讨厌的、难以阅读的解决方案:

export default (arr, key) => 
  arr.reduce(
    (r, v, _, __, k = v[key]) => ((r[k] || (r[k] = [])).push(v), r),
    {}
  );

对于那些询问这是如何工作的人,这里有一个解释:

在这两个=>中,您可以获得免费回报Array.prototype.reduce函数最多包含4个参数。这就是为什么要添加第五个参数,这样我们就可以使用默认值在参数声明级别为组(k)创建一个廉价的变量声明。(是的,这是巫术)如果我们的当前组在上一次迭代中不存在,我们将创建一个新的空数组((r[k]||(r[k]=[]))。这将计算到最左边的表达式,换句话说,一个现有数组或一个空数组,这就是为什么在该表达式之后会立即推送,因为无论哪种方式都会得到一个数组。当有一个返回时,逗号运算符将丢弃最左边的值,返回该场景中经过调整的前一组。

更容易理解的版本是:

export default (array, key) => 
  array.reduce((previous, currentItem) => {
    const group = currentItem[key];
    if (!previous[group]) previous[group] = [];
    previous[group].push(currentItem);
    return previous;
  }, {});

编辑:

TS版本:

const groupBy = <T, K extends keyof any>(list: T[], getKey: (item: T) => K) =>
  list.reduce((previous, currentItem) => {
    const group = getKey(currentItem);
    if (!previous[group]) previous[group] = [];
    previous[group].push(currentItem);
    return previous;
  }, {} as Record<K, T[]>);
_.groupBy([{tipo: 'A' },{tipo: 'A'}, {tipo: 'B'}], 'tipo');
>> Object {A: Array[2], B: Array[1]}

发件人:http://underscorejs.org/#groupBy

let x  = [
  {
    "id": "6",
    "name": "SMD L13",
    "equipmentType": {
      "id": "1",
      "name": "SMD"
    }
  },
  {
    "id": "7",
    "name": "SMD L15",
    "equipmentType": {
      "id": "1",
      "name": "SMD"
    }
  },
  {
    "id": "2",
    "name": "SMD L1",
    "equipmentType": {
      "id": "1",
      "name": "SMD"
    }
  }
];

function groupBy(array, property) {
  return array.reduce((accumulator, current) => {
    const object_property = current[property];
    delete current[property]

    let classified_element = accumulator.find(x => x.id === object_property.id);
    let other_elements = accumulator.filter(x => x.id !== object_property.id);

   if (classified_element) {
     classified_element.children.push(current)
   } else {
     classified_element = {
       ...object_property, 
       'children': [current]
     }
   }
   return [classified_element, ...other_elements];
 }, [])
}

console.log( groupBy(x, 'equipmentType') )

/* output 

[
  {
    "id": "1",
    "name": "SMD",
    "children": [
      {
        "id": "6",
        "name": "SMD L13"
      },
      {
        "id": "7",
        "name": "SMD L15"
      },
      {
        "id": "2",
        "name": "SMD L1"
      }
    ]
  }
]

*/

无突变:

const groupBy = (xs, key) => xs.reduce((acc, x) => Object.assign({}, acc, {
  [x[key]]: (acc[x[key]] || []).concat(x)
}), {})

console.log(groupBy(['one', 'two', 'three'], 'length'));
// => {3: ["one", "two"], 5: ["three"]}

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;
}());