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

如果希望避免使用外部库,可以简洁地实现groupBy()的普通版本,如下所示:

var groupBy=函数(xs,key){返回xs.reduce(函数(rv,x){(rv[x[key]]=rv[x[键]]| |[]).push(x);返回rv;}, {});};console.log(groupBy(['one','two','three'],'length'));//=>{“3”:[“1”,“2”],“5”:[”3“]}

其他回答

虽然linq的回答很有趣,但它也很重。我的方法有些不同:

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;
}());

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

您可以在JSBin上看到它的作用。

我在Undercore中没有看到任何东西可以做已经做的事情,尽管我可能会错过它。它与_.incontains非常相似,但使用_.isEqual而不是==进行比较。除此之外,其余部分都是针对具体问题的,尽管只是试图通用。

现在DataGrouper.sum(data,[“Phase”])返回

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

DataGrouper.sum(data,[“Phase”,“Step”])返回

[
    {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}
]

但和在这里只是一个势函数。您可以根据需要注册其他人:

DataGrouper.register("max", function(item) {
    return _.extend({}, item.key, {Max: _.reduce(item.vals, function(memo, node) {
        return Math.max(memo, Number(node.Value));
    }, Number.NEGATIVE_INFINITY)});
});

现在DataGrouper.max(data,[“Phase”,“Step”])将返回

[
    {Phase: "Phase 1", Step: "Step 1", Max: 10},
    {Phase: "Phase 1", Step: "Step 2", Max: 20},
    {Phase: "Phase 2", Step: "Step 1", Max: 30},
    {Phase: "Phase 2", Step: "Step 2", Max: 40}
]

或者如果您注册了:

DataGrouper.register("tasks", function(item) {
    return _.extend({}, item.key, {Tasks: _.map(item.vals, function(item) {
      return item.Task + " (" + item.Value + ")";
    }).join(", ")});
});

然后调用DataGrouper.tasks(data,[“Phase”,“Step”])将得到

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

DataGrouper本身是一个函数。可以用数据和要分组的财产列表来调用它。它返回一个数组,该数组的元素是具有两个财产的对象:key是分组财产的集合,vals是包含不在key中的其余财产的对象数组。例如,DataGrouper(data,[“Phase”,“Step”])将产生:

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

DataGrouper.register接受一个函数并创建一个新函数,该函数接受初始数据和分组依据的财产。然后,这个新函数采用上述输出格式,并依次对每个输出格式运行函数,返回一个新数组。生成的函数根据您提供的名称存储为DataGrouper的属性,如果您只需要本地引用,也会返回。

这是很多解释。我希望代码相当简单!

在Joseph Nields的回答之后,有一个polyfill用于将对象分组https://github.com/padcom/array-prototype-functions#arrayprototypegroupbyfieldormapper.因此,您可能希望使用现有的内容,而不是一次又一次地编写这些内容。

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;
 }));

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}
]
var arr = [ 
    { Phase: "Phase 1", `enter code here`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" }
];

创建并清空对象。循环遍历arr并添加使用Phase作为obj的唯一键。在循环遍历arr时,保持更新obj中的键总数。

const obj = {};
arr.forEach((item) => {
  obj[item.Phase] = obj[item.Phase] ? obj[item.Phase] + 
  parseInt(item.Value) : parseInt(item.Value);
});

结果如下:

{ "Phase 1": 50, "Phase 2": 130 }

循环通过obj形成表单和resultArr。

const resultArr = [];
for (item in obj) {
  resultArr.push({ Phase: item, Value: obj[item] });
}
console.log(resultArr);