1.ES聚合分析是什么
聚合分析是数据库中重要的功能特性，完成对⼀个查询的数据集中数据的聚合计算，如：找 出某字段（或计算表达式的结果）的最⼤值、最⼩值，计算和、平均值等。ES作为搜索引擎 兼数据库，同样提供了强⼤的聚合分析能⼒。
对⼀个数据集求最⼤、最⼩、和、平均值等指标的聚合，在ES中称为指标聚合
⽽关系型数据库中除了有聚合函数外，还可以对查询出的数据进⾏分组group by，再在组上 进⾏指标聚合。在ES中称为桶聚合
2.max min sum avg
求出⽕箭队球员的平均年龄
POST /nba/_search
{
"query": {
"match": {
"teamNameEn": "Rockets"
}
},
"aggs": {
"avgAge": {
"avg": {
"field": "playYear"
}
}
}
}
效果：
3.value_count 统计⾮空字段的⽂档数
求出⽕箭队中球员打球时间不为空的数量
POST /nba/_search
{
"query": {
"match": {
"teamNameEn": "Rockets"
}
},
"aggs": {
"countPlayreYear": {
"value_count": {
"field": "playYear"
}
}
},
"size": 1
}
加上size，效果：
{
"took" : 7,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 21,
"relation" : "eq"
},
"max_score" : 3.2723064,
"hits" : [
{
"_index" : "nba",
"_type" : "_doc",
"_id" : "86",
"_score" : 3.2723064,
"_source" : {
"countryEn" : "Switzerland",
"teamName" : "火箭",
"birthDay" : 769233600000,
"country" : "瑞士",
"teamCityEn" : "Houston",
"code" : "clint_capela",
"displayAffiliation" : "Switzerland/Switzerland",
"displayName" : "克林特 卡佩拉",
"schoolType" : "",
"teamConference" : "西部",
"teamConferenceEn" : "Western",
"weight" : "108.9 公斤",
"teamCity" : "休斯顿",
"playYear" : 5,
"jerseyNo" : "15",
"teamNameEn" : "Rockets",
"draft" : 2014,
"displayNameEn" : "Clint Capela",
"heightValue" : 2.08,
"birthDayStr" : "1994-05-18",
"position" : "中锋",
"age" : 25,
"playerId" : "203991"
}
}
]
},
"aggregations" : {
"countPlayreYear" : {
"value" : 21
}
}
}
4.Cardinality 值去重
计数 查出⽕箭队中年龄不同的数量
POST /nba/_search
{
"query":{
"term":{
"teamNameEn":{
"value":"Rockets"
}
}
},
"aggs":{
"counAget":{
"cardinality":{
"field":"age"
}
}
},
"size":0
}
5.stats 统计count max min avg sum 5个值
POST /nba/_search
{
"query": {
"match": {
"teamNameEn": "Rockets"
}
},
"aggs": {
"statsField": {
"stats": {
"field": "playYear"
}
}
},
"size": 1
}
效果：
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 21,
"relation" : "eq"
},
"max_score" : 3.2723064,
"hits" : [
{
"_index" : "nba",
"_type" : "_doc",
"_id" : "86",
"_score" : 3.2723064,
"_source" : {
"countryEn" : "Switzerland",
"teamName" : "火箭",
"birthDay" : 769233600000,
"country" : "瑞士",
"teamCityEn" : "Houston",
"code" : "clint_capela",
"displayAffiliation" : "Switzerland/Switzerland",
"displayName" : "克林特 卡佩拉",
"schoolType" : "",
"teamConference" : "西部",
"teamConferenceEn" : "Western",
"weight" : "108.9 公斤",
"teamCity" : "休斯顿",
"playYear" : 5,
"jerseyNo" : "15",
"teamNameEn" : "Rockets",
"draft" : 2014,
"displayNameEn" : "Clint Capela",
"heightValue" : 2.08,
"birthDayStr" : "1994-05-18",
"position" : "中锋",
"age" : 25,
"playerId" : "203991"
}
}
]
},
"aggregations" : {
"statsField" : {
"count" : 21,
"min" : 0.0,
"max" : 17.0,
"avg" : 5.333333333333333,
"sum" : 112.0
}
}
}
6.Extended stats ⽐stats多4个统计结果： 平⽅和、⽅差、标准差、平均值加/减两个标准差的区间
POST /nba/_search
{
"query": {
"match": {
"teamNameEn": "Rockets"
}
},
"aggs": {
"statsField": {
"extended_stats": {
"field": "playYear"
}
}
},
"size": 1
}
效果：
{
"took" : 8,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 21,
"relation" : "eq"
},
"max_score" : 3.2723064,
"hits" : [
{
"_index" : "nba",
"_type" : "_doc",
"_id" : "86",
"_score" : 3.2723064,
"_source" : {
"countryEn" : "Switzerland",
"teamName" : "火箭",
"birthDay" : 769233600000,
"country" : "瑞士",
"teamCityEn" : "Houston",
"code" : "clint_capela",
"displayAffiliation" : "Switzerland/Switzerland",
"displayName" : "克林特 卡佩拉",
"schoolType" : "",
"teamConference" : "西部",
"teamConferenceEn" : "Western",
"weight" : "108.9 公斤",
"teamCity" : "休斯顿",
"playYear" : 5,
"jerseyNo" : "15",
"teamNameEn" : "Rockets",
"draft" : 2014,
"displayNameEn" : "Clint Capela",
"heightValue" : 2.08,
"birthDayStr" : "1994-05-18",
"position" : "中锋",
"age" : 25,
"playerId" : "203991"
}
}
]
},
"aggregations" : {
"statsField" : {
"count" : 21,
"min" : 0.0,
"max" : 17.0,
"avg" : 5.333333333333333,
"sum" : 112.0,
"sum_of_squares" : 1140.0,
"variance" : 25.84126984126984,
"std_deviation" : 5.083430912412387,
"std_deviation_bounds" : {
"upper" : 15.500195158158107,
"lower" : -4.833528491491442
}
}
}
}
7.Percentiles 占⽐百分位对应的值统计，默认返回[ 1, 5, 25, 50, 75, 95, 99 ]分位上的值
查出⽕箭的球员的年龄占⽐
POST /nba/_search
{
"query": {
"term": {
"teamNameEn": {
"value": "Rockets"
}
}
},
"aggs": {
"percentAge": {
"percentiles": {
"field": "age",
"percents": [
20,
50,
75
]
}
}
},
"size": 0
}
效果：
{
"took" : 37,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 21,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"percentAge" : {
"values" : {
"20.0" : 21.7,
"50.0" : 25.0,
"75.0" : 30.25
}
}
}
}