累积基数聚合
编辑累积基数聚合
编辑一个父管道聚合，它计算父直方图（或 date_histogram）聚合中的累积基数。指定的指标必须是基数聚合，并且包含的直方图必须将min_doc_count设置为0（histogram聚合的默认值）。
cumulative_cardinality聚合对于查找“新增项目总数”非常有用，例如每天访问您网站的新访客数量。常规的基数聚合会告诉您每天有多少唯一访客，但不会区分“新”访客或“回头”访客。累积基数聚合可用于确定每天的唯一访客中有多少是“新增”的。
语法
编辑单独的cumulative_cardinality聚合如下所示
{
"cumulative_cardinality": {
"buckets_path": "my_cardinality_agg"
}
}
表 60. cumulative_cardinality 参数
| 参数名称 | 描述 | 必填 | 默认值 |
|---|---|---|---|
|
我们需要查找累积基数的基数聚合的路径（有关更多详细信息，请参阅 |
必填 |
|
|
DecimalFormat 模式，用于输出值。如果指定，则格式化的值将返回在聚合的 |
可选 |
|
以下代码片段计算每日users总数的累积基数
resp = client.search(
index="user_hits",
size=0,
aggs={
"users_per_day": {
"date_histogram": {
"field": "timestamp",
"calendar_interval": "day"
},
"aggs": {
"distinct_users": {
"cardinality": {
"field": "user_id"
}
},
"total_new_users": {
"cumulative_cardinality": {
"buckets_path": "distinct_users"
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'user_hits',
body: {
size: 0,
aggregations: {
users_per_day: {
date_histogram: {
field: 'timestamp',
calendar_interval: 'day'
},
aggregations: {
distinct_users: {
cardinality: {
field: 'user_id'
}
},
total_new_users: {
cumulative_cardinality: {
buckets_path: 'distinct_users'
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "user_hits",
size: 0,
aggs: {
users_per_day: {
date_histogram: {
field: "timestamp",
calendar_interval: "day",
},
aggs: {
distinct_users: {
cardinality: {
field: "user_id",
},
},
total_new_users: {
cumulative_cardinality: {
buckets_path: "distinct_users",
},
},
},
},
},
});
console.log(response);
GET /user_hits/_search
{
"size": 0,
"aggs": {
"users_per_day": {
"date_histogram": {
"field": "timestamp",
"calendar_interval": "day"
},
"aggs": {
"distinct_users": {
"cardinality": {
"field": "user_id"
}
},
"total_new_users": {
"cumulative_cardinality": {
"buckets_path": "distinct_users"
}
}
}
}
}
}
以下可能是响应
{
"took": 11,
"timed_out": false,
"_shards": ...,
"hits": ...,
"aggregations": {
"users_per_day": {
"buckets": [
{
"key_as_string": "2019-01-01T00:00:00.000Z",
"key": 1546300800000,
"doc_count": 2,
"distinct_users": {
"value": 2
},
"total_new_users": {
"value": 2
}
},
{
"key_as_string": "2019-01-02T00:00:00.000Z",
"key": 1546387200000,
"doc_count": 2,
"distinct_users": {
"value": 2
},
"total_new_users": {
"value": 3
}
},
{
"key_as_string": "2019-01-03T00:00:00.000Z",
"key": 1546473600000,
"doc_count": 3,
"distinct_users": {
"value": 3
},
"total_new_users": {
"value": 4
}
}
]
}
}
}
请注意，第二天，2019-01-02，有两个不同的用户，但累积管道聚合生成的total_new_users指标仅增加到三个。这意味着当天只有两个用户中的一个用户是新用户，另一个用户在之前的一天就已经出现过。这种情况在第三天再次发生，三天中只有三个用户中的一个用户是完全新增的。
增量累积基数
编辑cumulative_cardinality聚合将显示自查询时间段开始以来的总 distinct 计数。但是，有时查看“增量”计数也很有用。这意味着每天新增多少用户，而不是总累积计数。
这可以通过向我们的查询中添加derivative聚合来实现
resp = client.search(
index="user_hits",
size=0,
aggs={
"users_per_day": {
"date_histogram": {
"field": "timestamp",
"calendar_interval": "day"
},
"aggs": {
"distinct_users": {
"cardinality": {
"field": "user_id"
}
},
"total_new_users": {
"cumulative_cardinality": {
"buckets_path": "distinct_users"
}
},
"incremental_new_users": {
"derivative": {
"buckets_path": "total_new_users"
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'user_hits',
body: {
size: 0,
aggregations: {
users_per_day: {
date_histogram: {
field: 'timestamp',
calendar_interval: 'day'
},
aggregations: {
distinct_users: {
cardinality: {
field: 'user_id'
}
},
total_new_users: {
cumulative_cardinality: {
buckets_path: 'distinct_users'
}
},
incremental_new_users: {
derivative: {
buckets_path: 'total_new_users'
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "user_hits",
size: 0,
aggs: {
users_per_day: {
date_histogram: {
field: "timestamp",
calendar_interval: "day",
},
aggs: {
distinct_users: {
cardinality: {
field: "user_id",
},
},
total_new_users: {
cumulative_cardinality: {
buckets_path: "distinct_users",
},
},
incremental_new_users: {
derivative: {
buckets_path: "total_new_users",
},
},
},
},
},
});
console.log(response);
GET /user_hits/_search
{
"size": 0,
"aggs": {
"users_per_day": {
"date_histogram": {
"field": "timestamp",
"calendar_interval": "day"
},
"aggs": {
"distinct_users": {
"cardinality": {
"field": "user_id"
}
},
"total_new_users": {
"cumulative_cardinality": {
"buckets_path": "distinct_users"
}
},
"incremental_new_users": {
"derivative": {
"buckets_path": "total_new_users"
}
}
}
}
}
}
以下可能是响应
{
"took": 11,
"timed_out": false,
"_shards": ...,
"hits": ...,
"aggregations": {
"users_per_day": {
"buckets": [
{
"key_as_string": "2019-01-01T00:00:00.000Z",
"key": 1546300800000,
"doc_count": 2,
"distinct_users": {
"value": 2
},
"total_new_users": {
"value": 2
}
},
{
"key_as_string": "2019-01-02T00:00:00.000Z",
"key": 1546387200000,
"doc_count": 2,
"distinct_users": {
"value": 2
},
"total_new_users": {
"value": 3
},
"incremental_new_users": {
"value": 1.0
}
},
{
"key_as_string": "2019-01-03T00:00:00.000Z",
"key": 1546473600000,
"doc_count": 3,
"distinct_users": {
"value": 3
},
"total_new_users": {
"value": 4
},
"incremental_new_users": {
"value": 1.0
}
}
]
}
}
}