标记内数据点的聚合

Question

使用 Vega-Lite 我可以在编码中使用聚合，如下所示：

{
  "data": {
    "name": "thedata",
    "values": [
      {"id": "house1", "no of rooms": 2},
      {"id": "house1", "no of rooms": 3},
      {"id": "house2", "no of rooms": 4},
      {"id": "house3", "no of rooms": 8}
    ]
  },
  "transform": [
    {"calculate": "datum['no of rooms'] <= 5 ? 'small' : 'large'", "as": "myType"}
  ],
  "mark": {
    "type": "circle"
  },
  "encoding": {
    "y": {
      "field": "id", "type": "nominal"
    },
    "x": {
      "field": "no of rooms", "type": "quantitative",
      "aggregate": "mean"
    },
    "size": {"value": 200}
  }
}

现在我想知道使用 Vega 是否可以实现这一点。或者我是否必须重新考虑我的方法并在转换内或标记部分内创建聚合？

我天真的方法是使用

"x": "signal": "scale(myscale, sum(datum['no of rooms']))"

您能给我一些指导吗？

Answer 1

答案是否定的。 VL 提供了更简洁的语法，可转换为 Vega。在这些情况下，查看正在生成的 Vega 是很有用的。在编辑器中，单击“编辑 Vega 规格”即可查看它。这里使用了聚合变换。

{
  "$schema": "https://vega.github.io/schema/vega/v5.json",
  "background": "white",
  "padding": 5,
  "width": 200,
  "style": "cell",
  "data": [
    {
      "name": "thedata",
      "values": [
        {"id": "house1", "no of rooms": 2},
        {"id": "house1", "no of rooms": 3},
        {"id": "house2", "no of rooms": 4},
        {"id": "house3", "no of rooms": 8}
      ]
    },
    {
      "name": "data_0",
      "source": "thedata",
      "transform": [
        {
          "type": "formula",
          "expr": "datum['no of rooms'] <= 5 ? 'small' : 'large'",
          "as": "myType"
        },
        {
          "type": "aggregate",
          "groupby": ["id"],
          "ops": ["mean"],
          "fields": ["no of rooms"],
          "as": ["mean_no of rooms"]
        },
        {
          "type": "filter",
          "expr": "isValid(datum[\"mean_no of rooms\"]) && isFinite(+datum[\"mean_no of rooms\"])"
        }
      ]
    }
  ],
  "signals": [
    {"name": "y_step", "value": 20},
    {
      "name": "height",
      "update": "bandspace(domain('y').length, 1, 0.5) * y_step"
    }
  ],
  "marks": [
    {
      "name": "marks",
      "type": "symbol",
      "style": ["circle"],
      "from": {"data": "data_0"},
      "encode": {
        "update": {
          "fill": {"value": "#4c78a8"},
          "ariaRoleDescription": {"value": "circle"},
          "description": {
            "signal": "\"Mean of no of rooms: \" + (format(datum[\"mean_no of rooms\"], \"\")) + \"; id: \" + (isValid(datum[\"id\"]) ? datum[\"id\"] : \"\"+datum[\"id\"])"
          },
          "x": {"scale": "x", "field": "mean_no of rooms"},
          "y": {"scale": "y", "field": "id"},
          "size": {"value": 200},
          "shape": {"value": "circle"}
        }
      }
    }
  ],
  "scales": [
    {
      "name": "x",
      "type": "linear",
      "domain": {"data": "data_0", "field": "mean_no of rooms"},
      "range": [0, {"signal": "width"}],
      "nice": true,
      "zero": true
    },
    {
      "name": "y",
      "type": "point",
      "domain": {"data": "data_0", "field": "id", "sort": true},
      "range": {"step": {"signal": "y_step"}},
      "padding": 0.5
    }
  ],
  "axes": [
    {
      "scale": "x",
      "orient": "bottom",
      "gridScale": "y",
      "grid": true,
      "tickCount": {"signal": "ceil(width/40)"},
      "domain": false,
      "labels": false,
      "aria": false,
      "maxExtent": 0,
      "minExtent": 0,
      "ticks": false,
      "zindex": 0
    },
    {
      "scale": "x",
      "orient": "bottom",
      "grid": false,
      "title": "Mean of no of rooms",
      "labelFlush": true,
      "labelOverlap": true,
      "tickCount": {"signal": "ceil(width/40)"},
      "zindex": 0
    },
    {"scale": "y", "orient": "left", "grid": false, "title": "id", "zindex": 0}
  ]
}