Lodash _.filter - 过滤数组以返回大多数出现

Question

我有以下数组：

{ id: 19531285,
   domain: 'fjuhsd.org',
   alexa_rank: 458835,
   country: 236,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 2657031,
   domain: 'deporlovers.
   alexa_rank: 470687,
   country: 209,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 1846092,
   domain: 'lehighsports
   alexa_rank: 477376,
   country: 236,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 41443846,
   domain: 'blacklightsl
   alexa_rank: 477964,
   country: 0,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 3881608,
   domain: 'audubonportl
   alexa_rank: 478643,
   country: 236,
   employees: '2',
   revenue: '2',
   industry_id: '39' },
 { id: 32704527,
   domain: 'lowryparkzoo
   alexa_rank: 488859,
   country: 236,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 1907473,
   domain: 'citymb.info'
   alexa_rank: 490285,
   country: 236,
   employees: '4',
   revenue: '4',
   industry_id: '53' },
 { id: 8716166,
   domain: 'terrainracin
   alexa_rank: 490404,
   country: 0,
   employees: '0',
   revenue: '0',
   industry_id: '0' },
 { id: 935439,
   domain: 'triatlonchan
   alexa_rank: 491953,
   country: 83,
   employees: '0',
   revenue: '0',
   industry_id: '0' }

我正在使用 Lodash _.filter() 函数尝试对以下数组进行排序，以仅返回值等于收入、行业 ID 和雇员出现次数最多的元素。

在这种情况下，出现最多的数字（基于查看数组）

是收入：0，行业 ID：0 和员工：0

我将如何过滤数组以使用 _.filter 执行此操作？我还没有想办法做到这一点。

谢谢。

Answer 1

您需要首先找到必要字段的最常见值。您可以查看this 了解如何操作。

一旦你拥有最常用的字段，你就可以这样做 -

_.filter(records, record => {
    return record.revenue === mostFrequentRevenue &&
        record.industry_id === mostFrequentIndustryId &&
        record.employees === mostFrequentEmployees;
})

Answer 2

您可以使用地图来记录发生次数。

function sortExtract(data) {
  var sorted = data.sort((a, b) => {
    return a.revenue > b.revenue || a.industry_id > b.industry_id || a.employees > b.employees;
  })

  var count = new Map();
  for (let l of sorted) {
    var m = l.revenue + l.employees;
    if (count.has(m)) {
      var val = count.get(m);
      val.push(l)
    } else count.set(m, [l]);
  }
  var len = 0;
  var obj = 0
  var len = Array.from(count, (x, y) => {
    if (x[1].length > len) {
      len = x[1].length;
      obj = x[1]
    }
  })
  return obj[0];
}

var data = [{
    id: 19531285,
    domain: 'fjuhsd.org',
    alexa_rank: 458835,
    country: 236,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 2657031,
    domain: 'deporlovers',
    alexa_rank: 470687,
    country: 209,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 1846092,
    domain: 'lehighsport',
    alexa_rank: 477376,
    country: 236,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 41443846,
    domain: 'blacklights',
    alexa_rank: 477964,
    country: 0,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 3881608,
    domain: 'audubonport',
    alexa_rank: 478643,
    country: 236,
    employees: '2',
    revenue: '2',
    industry_id: '39'
  },
  {
    id: 32704527,
    domain: 'lowryparkzoo',
    alexa_rank: 488859,
    country: 236,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 1907473,
    domain: 'citymb.info',
    alexa_rank: 490285,
    country: 236,
    employees: '4',
    revenue: '4',
    industry_id: '53'
  },
  {
    id: 8716166,
    domain: 'terrainraci',
    alexa_rank: 490404,
    country: 0,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  },
  {
    id: 935439,
    domain: 'triatloncha',
    alexa_rank: 491953,
    country: 83,
    employees: '0',
    revenue: '0',
    industry_id: '0'
  }
];

console.log(sortExtract(data));

Answer 3

通过结合收入、行业ID和员工值，为每个项目创建一个“id”，计算数据中出现的次数，并获得最高的“id”。

使用此 id 过滤数据。

const data = [{"id":19531285,"domain":"fjuhsd.org","alexa_rank":458835,"country":236,"employees":"0","revenue":"0","industry_id":"0"},{"id":2657031,"domain":"deporlovers","alexa_rank":470687,"country":209,"employees":"0","revenue":"0","industry_id":"0"},{"id":1846092,"domain":"lehighsport","alexa_rank":477376,"country":236,"employees":"0","revenue":"0","industry_id":"0"},{"id":41443846,"domain":"blacklights","alexa_rank":477964,"country":0,"employees":"0","revenue":"0","industry_id":"0"},{"id":3881608,"domain":"audubonport","alexa_rank":478643,"country":236,"employees":"2","revenue":"2","industry_id":"39"},{"id":32704527,"domain":"lowryparkzoo","alexa_rank":488859,"country":236,"employees":"0","revenue":"0","industry_id":"0"},{"id":1907473,"domain":"citymb.info","alexa_rank":490285,"country":236,"employees":"4","revenue":"4","industry_id":"53"},{"id":8716166,"domain":"terrainraci","alexa_rank":490404,"country":0,"employees":"0","revenue":"0","industry_id":"0"},{"id":935439,"domain":"triatloncha","alexa_rank":491953,"country":83,"employees":"0","revenue":"0","industry_id":"0"}];

const getId = ({ revenue, industry_id, employees }) => `${revenue}-${industry_id}-${employees}`; // create the id of the element by combining the required properties

const mostOccurring = _.get(_(data)
  .countBy(getId) // count the number of items that have the same "id"
  .entries() // get the entries
  .maxBy(([_, v]) => v), 0); // find the maximum, and use get to take the id
  
const result = data.filter((o) => getId(o) === mostOccurring); // filter all items by the most occuring id

console.log(result);

<script src="https://cdnjs.cloudflare.com/ajax/libs/lodash.js/4.17.4/lodash.min.js"></script>