什么是从表数据中删除列的最佳方法?

时间:2015-04-21 07:49:41

标签: javascript underscore.js

考虑以下数据:

[
  { time: '5:00', name: 'bran', fruit: 'pear', numEaten: 3},
  { time: '5:00', name: 'rickon', fruit: 'apple', numEaten: 2},
  { time: '6:00', name: 'bran', fruit: 'apple', numEaten: 5},
  { time: '6:00', name: 'rickon', fruit: 'grape', numEaten: 1},
  { time: '6:00', name: 'bran', fruit: 'pear', numEaten: 2},
  { time: '6:00', name: 'eddard', fruit: 'pear', numEaten: 2},
  { time: '7:00', name: 'rickon', fruit: 'apple', numEaten: 7}
]

我想要做的是删除一个列,然后添加' numEaten'所有具有匹配列的行。所以想象一下:当你吃水果时,你实际上并不关心,你只想知道谁吃了多少。所以输出表看起来像:

[
  {name: 'bran', fruit: 'pear', numEaten: 5},
  {name: 'bran', fruit: 'apple', numEaten: 2},
  {name: 'rickon', fruit: 'apple', numEaten: 9},
  {name: 'rickon', fruit: 'grape', numEaten: 1},
  {name: 'eddard', fruit: 'pear', numEaten: 2},
]

我一直在查看下划线中的各种javascript数组原型函数和扩展,但我无法看到一种特别优雅的方法来执行此操作。我想要一个原型功能:

function aggregate(data, column, aggregateColumn) // aggregate(data, 'time', 'numEaten')

将执行此操作。从概念上讲,我正在考虑为每个 _.groupBy()column的列运行aggregateColumn,但这样做似乎有点蠢蠢欲动。还有更好的方法吗?

修改

似乎没有针对此问题的单行解决方案:在收集以下解决方案的反馈后,发布我想出的内容。请注意,与原始问题不同,这会使列保持,而不是删除,并适用于任何架构。

  var aggregate = function(data, aggregateColumn, keepColumns) {
    keepColumns = keepColumns || [];
    if(!Array.isArray(keepColumns)) {
      keepColumns = [ keepColumns ];
    }

    var removeColumns = _.difference(_.keys(data[0]), keepColumns.concat(aggregateColumn));
    var grouped = _.groupBy(data, function(d) {
      return _.reduce(keepColumns, function(o, col) {
        return o + d[col] + '-';
      }, '');      
    });

    return _.map(grouped, function(mapData) {
      var reduced = _.reduce(keepColumns, function(o, col) {
          o[col] = mapData[0][col];
          return o;
        }, {}
      );

      reduced[aggregateColumn] = _.reduce(mapData, function(o, aggrData) {
          return o + aggrData[aggregateColumn];
        }, 0
      );

      return reduced;
    });
  }

4 个答案:

答案 0 :(得分:2)

这是在下划线中执行此操作的一种方法

让我们定义像

这样的初始数据
var data = [
  { time: '5:00', name: 'bran', fruit: 'pear', numEaten: 3},
  { time: '5:00', name: 'rickon', fruit: 'apple', numEaten: 2},
  { time: '6:00', name: 'bran', fruit: 'apple', numEaten: 5},
  { time: '6:00', name: 'rickon', fruit: 'grape', numEaten: 1},
  { time: '6:00', name: 'bran', fruit: 'pear', numEaten: 2},
  { time: '6:00', name: 'eddard', fruit: 'pear', numEaten: 2},
  { time: '7:00', name: 'rickon', fruit: 'apple', numEaten: 7}
]

然后,通过加入来创建基于namefruit的群组。

var groups = _.groupBy(data, function(value){
        return value.name+ '#' + value.fruit;
    });

我们稍后会在汇总时使用此自定义sum功能。

function sum(numbers) {
    return _.reduce(numbers, function(result, current) {
        return result + parseFloat(current);
    }, 0);
}

现在,通过提取map并取出numEaten

sum这些群组
var out = _.map(groups, function(group){
        return {
            name: group[0].name,
            fruit: group[0].fruit,
            numEaten: sum(_.pluck(group, 'numEaten'))
        }
    });

最后,我们得到了像

这样的输出
out
[
  {name: 'bran', fruit: 'pear', numEaten: 5},
  {name: 'bran', fruit: 'apple', numEaten: 5},
  {name: 'rickon', fruit: 'apple', numEaten: 9},
  {name: 'rickon', fruit: 'grape', numEaten: 1},
  {name: 'eddard', fruit: 'pear', numEaten: 2},
]

答案 1 :(得分:2)

使用纯JavaScript时,通用解决方案很简单,但我想使用下划线提供此解决方案,因为有时会让人感到兴奋!

由于下划线不提供删除重复项的适当功能,因此我使用_.uniqJSON.stringify函数混合。

以下是成功测试的aggregate函数

  var objs = [
    { time: '5:00', name: 'bran', fruit: 'pear', numEaten: 3},
    { time: '6:00', name: 'bran', fruit: 'pear', numEaten: 2},  
    { time: '6:00', name: 'bran', fruit: 'apple', numEaten: 5},  
    { time: '5:00', name: 'rickon', fruit: 'apple', numEaten: 2},
    { time: '7:00', name: 'rickon', fruit: 'apple', numEaten: 7},  
    { time: '6:00', name: 'rickon', fruit: 'grape', numEaten: 1},  
    { time: '6:00', name: 'eddard', fruit: 'pear', numEaten: 2}
    ];

function aggregate(data, column, aggregateColumn){
var res=[];
_.map(data, function(item){
            var comparer={},
                compared={};

            for(var k in item){
                if(k!=column){
                compared[k]=item[k];
                if(k!=aggregateColumn)
                    comparer[k]=item[k];                    
                }
            }
_.each(_.where(_.without(data,item), comparer),function(aggregable){                    
                compared[aggregateColumn]+=aggregable[aggregateColumn];
                return compared;
                });
                res.push(compared);
            });
    return _.uniq(res,function(item){return JSON.stringify(item);})
}

    ///usage
    var o=aggregate(objs, 'time', 'numEaten');
    console.log({'o':o});

Have a look at this Fiddle

答案 2 :(得分:1)

你在谈论“专栏”的事实表明,当你正在处理一系列字符串地图时,你会想到一张桌子。
由于JavaScript是基于原型的事实,因此没有“漂亮”或开箱即用的解决方案(不仅是,而且还有)。

您可以选择for循环和Array.forEach。我更喜欢前者 此外,我在这里返回一个新数组,而不是原位修改旧数组。

function aggregate(data, column, aggregateColumn)
{
    var array = [];
    // Just work the array
    for(var i = 0; i < data.length; i++)
    {
        var currentOld = data[i];
        var found = false;
        // Label the loop, so we can control it
        outside:
        // Check if the current type already exists in the new array
        for(var j = 0; j < array.length; j++)
        {
            var currentNew = array[j];
            // Check if all properties match
            for(var property in currentOld)
            {
                // Skip properties that match column or aggregateColumn
                if(property == column || property == aggregateColumn)
                {
                    continue;
                }
                // Now check if their values match
                if(currentOld[property] != currentNew[property])
                {
                    // If they don't match, continue the outer loop
                    continue outside;
                }
            }
            // At this point, all properties matched, so we aggregate
            currentNew[aggregateColumn] += currentOld[aggregateColumn];
            // Set the flag to indicate that we found it
            found = true;
            // And end the loop
            break;
        }
        // If the current type is not yet in the new array, we need to put it there
        if(!found)
        {
            // Create a copy of it (assuming your data are trivial objects)
            var copy = JSON.parse(JSON.stringify(currentOld));
            // Remove your "column"
            delete copy[column];
            // And add it
            array.push(copy);
        }
    }
    return array;
}

测试函数输出你想要的相同数组,只是按照不同的顺序,因为它保持原始数组的顺序而不是排序。
我假设您知道如何对数组进行排序。 ;)

答案 3 :(得分:1)

使用John Galt的优秀答案中的sum函数,这是一个通用版本

function aggregate(data, aggregateColumn, keepColumns){

   var groups = _.groupBy(data, function(item){
      return _.values(_.pick(item, keepColumns)).join('#')
   });

   return _.map(groups, function(group){
       return _.extend( _.pick(group[0], keepColumns), 
          _.object([aggregateColumn], [sum(_.pluck(group, aggregateColumn))]));
   }); 
}