elastic search中的bucket和metric
- 概念
bucket：按照某个字段进行bucket划分，那个字段的值相同的那些数据，就会被划分到一个bucket中；
metric：对一个bucket执行的某种聚合分析的操作，比如说求平均值，求最大值，求最小值
对这两个与sql语句进行类比：
select count(*) from access_log group by user_id
bucket：group by user_id --> 那些user_id相同的数据，就会被划分到一个bucket中
metric：count(*)，对每个user_id bucket中所有的数据，计算一个数量
- 聚合数据分析一：
PUT /tvs
{
"mappings": {
"sales": {
"properties": {
"price": {
"type": "long"
},
"color": {
"type": "keyword"
},
"brand": {
"type": "keyword"
},
"sold_date": {
"type": "date"
}
}
}
}
}
POST /tvs/sales/_bulk
{ "index": {}}
{ "price" : 1000, "color" : "红色", "brand" : "长虹", "sold_date" : "2016-10-28" }
{ "index": {}}
{ "price" : 2000, "color" : "红色", "brand" : "长虹", "sold_date" : "2016-11-05" }
{ "index": {}}
{ "price" : 3000, "color" : "绿色", "brand" : "小米", "sold_date" : "2016-05-18" }
{ "index": {}}
{ "price" : 1500, "color" : "蓝色", "brand" : "TCL", "sold_date" : "2016-07-02" }
{ "index": {}}
{ "price" : 1200, "color" : "绿色", "brand" : "TCL", "sold_date" : "2016-08-19" }
{ "index": {}}
{ "price" : 2000, "color" : "红色", "brand" : "长虹", "sold_date" : "2016-11-05" }
{ "index": {}}
{ "price" : 8000, "color" : "红色", "brand" : "三星", "sold_date" : "2017-01-01" }
{ "index": {}}
{ "price" : 2500, "color" : "蓝色", "brand" : "小米", "sold_date" : "2017-02-12" }2、统计哪种颜色的电视销量最高
GET /tvs/sales/_search
{
"size" : 0,
"aggs" : {
"popular_colors" : {
"terms" : {
"field" : "color"
}
}
}
}
size：只获取聚合结果，而不要执行聚合的原始数据
aggs：固定语法，要对一份数据执行分组聚合操作
popular_colors：就是对每个aggs，都要起一个名字，这个名字是随机的
terms：根据字段的值进行分组
field：根据指定的字段的值进行分组
返回结果：
{
"took" : 3,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : 8,
"max_score" : 0.0,
"hits" : [ ]
},
"aggregations" : {
"popular_color" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "红色",
"doc_count" : 4
},
{
"key" : "绿色",
"doc_count" : 2
},
{
"key" : "蓝色",
"doc_count" : 2
}
]
}
}
}默认的排序规则：按照doc_count降序排序
3、统计每种颜色电视的平均价格
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"popular_color": {
"terms": {
"field": "color",
"size": 10
},
"aggs": {
"ave_price": {
"avg": {
"field": "price"
}
}
}
}
}
}3、多层次下钻分析
下钻分析：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
例子：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
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"popular_color": {
"terms": {
"field": "color",
"size": 10
},
"aggs": {
"ave_price": {
"avg": {
"field": "price"
}
},
"group_by_brand": {
"terms": {
"field": "brand",
"size": 10
},
"aggs":{
"brand_avg_price":{
"avg": {
"field": "price"
}
}
}
}
}
}
}
}4、统计每种颜色电视的最大最小价格
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_color": {
"terms": {
"field": "color",
"size": 10
},
"aggs": {
"max_price": {
"max": {
"field": "price"
}
},
"min_price":{
"min": {
"field": "price"
}
},
"sum_price":{
"sum": {
"field": "price"
}
}
}
}
}
}4、使用histogram按价格区间统计电视销量和销售额
histogram：类似于terms，也是进行bucket分组操作，接收一个field，按照这个field的值的各个范围区间，进行bucket分组操作
"histogram":{
"field": "price",
"interval": 2000
},
interval：2000，划分范围，0~2000，2000~4000，4000~6000，6000~8000，8000~10000，buckets
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"price": {
"histogram": {
"field": "price",
"interval": 2000
},
"aggs": {
"revenue": {
"sum": {
"field": "price"
}
}
}
}
}
}5、使用date_histogram统计每月电视的销量
按照我们指定的某个date类型的日期field，以及日期interval，按照一定的日期间隔，去划分bucket；
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_soldDate": {
"date_histogram": {
"field": "sold_date",
"interval": "month",
"format": "yyyy-MM-dd",
"min_doc_count": 0,
"extended_bounds": {
"min": "2017-01-01",
"max": "2017-12-31"
}
}
}
}
}
min_doc_count：即使某个日期interval，2017-01-01~2017-01-31中，一条数据都没有，那么这个区间也是要返回的，不然默认是会过滤掉这个区间的
extended_bounds，min，max：划分bucket的时候，会限定在这个起始日期，和截止日期内
6、统计每季度每个品牌的销售额
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_quarter": {
"date_histogram": {
"field": "sold_date",
"interval": "quarter",
"format": "yyyy-MM-dd",
"min_doc_count": 0,
"extended_bounds": {
"min": "2016-01-01",
"max": "2017-12-31"
}
},
"aggs":{
"group_by_brand":{
"terms": {
"field": "brand"
},
"aggs": {
"per_brand_price": {
"sum": {
"field": "price"
}
}
}
},
"total_sum_quarter":{
"sum": {
"field": "price"
}
}
}
}
}
}7、统计指定品牌下每种颜色的销量
GET /tvs/sales/_search
{
"size": 0,
"query": {
"term": {
"brand": {
"value": "小米"
}
}
},
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
}
}
}
}7、_global bucket：单个品牌与所有品牌销量对比
GET /tvs/sales/_search
{
"size": 0,
"query": {
"term": {
"brand": {
"value": "长虹"
}
}
},
"aggs": {
"changhong_avg_price": {
"avg": {
"field": "price"
}
},
"all":{
"global": {},
"aggs": {
"all_brand_ave_price":{
"avg": {
"field": "price"
}
}
}
}
}
}8、过滤+聚合，统计价格大于1200的平均价格
GET /tvs/sales/_search
{
"size": 0,
"query": {
"constant_score": {
"filter": {
"range": {
"price": {
"gte": 1200
}
}
},
"boost": 1
}
},
"aggs": {
"avg_price": {
"avg": {
"field": "price"
}
}
}
}9、统计品牌最近一个月的平均价格
GET /tvs/sales/_search
{
"size": 0,
"query": {
"term": {
"brand": {
"value": "长虹"
}
}
},
"aggs": {
"recent_150d": {
"filter": {
"range": {
"sold_date": {
"gte": "now-3000d"
}
}
},
"aggs": {
"recent_3000d_ave_price": {
"avg": {
"field": "price"
}
}
}
}
}
}10、统计出来每个颜色的电视的销售额，需要按照销售额降序排序
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_color": {
"terms": {
"field": "color",
"order": {
"avg_price": "desc"
}
},
"aggs": {
"avg_price": {
"avg": {
"field": "price"
}
}
}
}
}
}11、按下钻最深层次的metric排序
GET /tvs/sales/_search
{
"size": 0,
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
},
"aggs": {
"group_by_brand": {
"terms": {
"field": "brand",
"order": {
"avg_price": "desc"
}
},
"aggs": {
"avg_price": {
"avg": {
"field": "price"
}
}
}
}
}
}
}
}