Elasticsearch高手进阶篇(36)
深入聚合数据分析_bucket嵌套实现颜色+品牌的多层下钻分析
下钻分析
从颜色到品牌进行下钻分析，每种颜色的平均价格，以及找到每种颜色每个品牌的平均价格
我们可以进行多层次的下钻
比如说，现在红色的电视有4台，同时这4台电视中，有3台是属于长虹的，1台是属于小米的
红色电视中的3台长虹的平均价格是多少？ 红色电视中的1台小米的平均价格是多少？
下钻的意思是，已经分了一个组了，比如说颜色的分组，然后还要继续对这个分组内的数据，再分组，比如一个颜色内，还可以分成多个不同的品牌的组，最后对每个最小粒度的分组执行聚合分析操作，这就叫做下钻分析
-
es，下钻分析，就要对bucket进行多层嵌套，多次分组
- 按照多个维度（颜色+品牌）多层下钻分析，而且学会了每个下钻维度（颜色，颜色+品牌），都可以对每个维度分别执行一次metric聚合操作
GET /waws_tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
},
"aggs": {
"color_avg_price": {
"avg": {
"field": "price"
}
},
"group_by_brand": {
"terms": {
"field": "brand"
},
"aggs": {
"brand_avg_price": {
"avg": {
"field": "price"
}
}
}
}
}
}
}
}
{
"took": 5,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 8,
"max_score": 0,
"hits": []
},
"aggregations": {
"group_by_color": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "红色",
"doc_count": 4,
"color_avg_price": {
"value": 3250
},
"group_by_brand": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "长虹",
"doc_count": 3,
"brand_avg_price": {
"value": 1666.6666666666667
}
},
{
"key": "三星",
"doc_count": 1,
"brand_avg_price": {
"value": 8000
}
}
]
}
},
{
"key": "绿色",
"doc_count": 2,
"color_avg_price": {
"value": 2100
},
"group_by_brand": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "TCL",
"doc_count": 1,
"brand_avg_price": {
"value": 1200
}
},
{
"key": "小米",
"doc_count": 1,
"brand_avg_price": {
"value": 3000
}
}
]
}
},
{
"key": "蓝色",
"doc_count": 2,
"color_avg_price": {
"value": 2000
},
"group_by_brand": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "TCL",
"doc_count": 1,
"brand_avg_price": {
"value": 1500
}
},
{
"key": "小米",
"doc_count": 1,
"brand_avg_price": {
"value": 2500
}
}
]
}
}
]
}
}
}
Elasticsearch高手进阶篇(37)
深入聚合数据分析_掌握更多metrics：统计每种颜色电视最大最小价格
更多metrics
- count：bucket，terms，自动就会有一个doc_count，就相当于是count
- avg：avg aggs，求平均值
- max：求一个bucket内，指定field值最大的那个数据
- min：求一个bucket内，指定field值最小的那个数据
- sum：求一个bucket内，指定field值的总和
一般来说，90%的常见的数据分析的操作，metric，无非就是count，avg，max，min，sum
GET /waws_tvs/sales/_search
{
"size" : 0,
"aggs": {
"colors": {
"terms": {
"field": "color"
},
"aggs": {
"avg_price": {"avg": {"field": "price"}},
"min_price" : {"min": {"field": "price"}},
"max_price" : {"max": {"field": "price"}},
"sum_price" : {"sum": {"field": "price"}}
}
}
}
}
求总和，就可以拿到一个颜色下的所有电视的销售总额
{
"took": 4,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 8,
"max_score": 0,
"hits": []
},
"aggregations": {
"colors": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "红色",
"doc_count": 4,
"max_price": {
"value": 8000
},
"min_price": {
"value": 1000
},
"avg_price": {
"value": 3250
},
"sum_price": {
"value": 13000
}
},
{
"key": "绿色",
"doc_count": 2,
"max_price": {
"value": 3000
},
"min_price": {
"value": 1200
},
"avg_price": {
"value": 2100
},
"sum_price": {
"value": 4200
}
},
{
"key": "蓝色",
"doc_count": 2,
"max_price": {
"value": 2500
},
"min_price": {
"value": 1500
},
"avg_price": {
"value": 2000
},
"sum_price": {
"value": 4000
}
}
]
}
}
}
