1.group隻支援單機分組,不支援多分片叢集分組,這是個大坑
2.aggregate支援多分片叢集,新版本建議使用aggregate
3.資料模闆
{
"_id": "2204000000429520201204000000000",
"mp_id": "22040000004295",
"create_time": ISODate("2020-12-04T16:10:03.627Z"),
"data_day": NumberInt("20201204"),
"data_time": ISODate("2021-03-11T01:29:55.095Z"),
"gd_id": "125F58D3-B632-43B0-B6D8-1EA90977F33C",
"mn": "20150724000002",
"protocol": "0",
"update_time": ISODate("2020-12-04T16:10:03.627Z"),
"values": [
{
"cou_value": null,
"flag": null,
"avg_value": null,
"mstatus": NumberInt("6"),
"pollutant_code": "001",
"min_value": null,
"avg_zs": null,
"estatus": NumberInt("0"),
"astatus": NumberInt("0"),
"outlet_standard": "20",
"max_zs": null,
"min_zs": null,
"max_value": null,
"sstatus": NumberInt("0")
},
{
"cou_value": null,
"flag": null,
"avg_value": null,
"mstatus": NumberInt("6"),
"pollutant_code": "002",
"min_value": null,
"avg_zs": null,
"estatus": NumberInt("0"),
"astatus": NumberInt("0"),
"outlet_standard": "80",
"max_zs": null,
"min_zs": null,
"max_value": null,
"sstatus": NumberInt("0")
},
{
"cou_value": null,
"flag": null,
"avg_value": null,
"mstatus": NumberInt("6"),
"pollutant_code": "003",
"min_value": null,
"avg_zs": null,
"estatus": NumberInt("0"),
"astatus": NumberInt("0"),
"outlet_standard": "250",
"max_zs": null,
"min_zs": null,
"max_value": null,
"sstatus": NumberInt("0")
},
{
"cou_value": null,
"flag": null,
"avg_value": null,
"mstatus": NumberInt("6"),
"pollutant_code": "004",
"min_value": null,
"avg_zs": null,
"estatus": NumberInt("0"),
"astatus": NumberInt("0"),
"outlet_standard": "80",
"max_zs": null,
"min_zs": null,
"max_value": null,
"sstatus": NumberInt("0")
},
{
"cou_value": null,
"flag": null,
"avg_value": null,
"mstatus": NumberInt("6"),
"pollutant_code": "008",
"min_value": null,
"avg_zs": null,
"estatus": NumberInt("0"),
"astatus": NumberInt("0"),
"outlet_standard": "50",
"max_zs": null,
"min_zs": null,
"max_value": null,
"sstatus": NumberInt("0")
},
{
"pollutant_code": "B02",
"cou_value": null,
"min_value": null,
"flag": null,
"avg_value": null,
"outlet_standard": null,
"max_value": null
}
]
}
4.group分組(cond篩選條件,key是分組的字段,1标示true按此字段分組, initial初始化字段值,reduce對分組資料進行循環處理,item代表分組的每行資料,out包含要輸出的字段,item.values.length代表子集的總數);
var start_time = ISODate("2021-03-10T16:05:46.186+0800");
var end_time = ISODate("2021-03-30T16:06:01.666+0800");
db.collection.group({
cond: {
"$and": [
{
"data_time": {
"$gte": start_time
}
},
{
"data_time": {
"$lte": end_time
}
}
]
},
key: {
"mp_id": 1,
"total": 1,
"type": 1
},
initial: {
"total": 0,
"type": "day_air"
},
reduce: function Reduce(item, out) {
if (item.values != null) {
out.total += item.values.length
}
}
});
查詢結果如下
[
{
"mp_id" : "1101050031132015",
"total" : 64,
"type" : "day_air"
},
{
"mp_id" : "13810000000645",
"total" : 208,
"type" : "day_air"
},
{
"mp_id" : "13810000000665",
"total" : 208,
"type" : "day_air"
},
{
"mp_id" : "138200000001115",
"total" : 208,
"type" : "day_air"
},
{
"mp_id" : "14010600000115",
"total" : 208,
"type" : "day_air"
}
]
5.aggregate管道聚合方式($match篩選條件,group為分組條件,id必選,可以為空或者Null,total則是自定義聚合字段,我這取的子集的size,$values代表子集,$addFields可以添加自定義的字段,out:輸出的指定文檔)。
var start_time = ISODate("2021-03-10T16:05:46.186+0800");
var end_time = ISODate("2021-03-30T16:06:01.666+0800");
db.collection.aggregate([{ $match : {"$and": [
{
"data_time": {
"$gte": start_time
}
},
{
"data_time": {
"$lte": end_time
}
}
] }},
{
$group: {
_id: "$mp_id",
total: {
$sum: {
$size: "$values"
}
}
}
},
{
$addFields: {
"type": "day_air"
}
},{
$out:"temp"
}
]);
輸出結果為