我在MongoDB中拥有文档的这种数据结构，并且从任何角度看，它都针对与不同操作的时间序列有关的复杂数据分析（固定数据日志）。我发现很难使用mongo查询提取每个文档的特定类型的更改之间的时间，然后应用$graphLookup函数（如下所示）很难。我是MongoDB的初学者，我需要查询方面的帮助以获取所需的数据。
单个文档的数据结构（示例）：
{
"_id":NumberInt(1),
"Creation": ISODate("2018-11-19T06:30:42Z"),
"Creator": NumberInt(1),
"Replies": NumberInt(10),
//... other aggregated properties
"CurrentProperties":{ // a copy of the last update signifying the current state
"StatusId": NumberInt(8),
"PriorityId": NumberInt(6),
"DepartmentId": NumberInt(5),
"TypeId": NumberInt(4),
"CategoryId": NumberInt(2),
"SubcategoryId": NumberInt(333),
"ChangeTime": ISODate("2018-11-19T10:17:20Z"),
"TimeDelta": NumberLong(3600000), //timespan from last change in MS
"ChangeType": NumberInt(4),
"UserId": NumberInt(1)
},
"ChangeHistory":[ // time series changes
{
"StatusId": NumberInt(8),
"PriorityId": NumberInt(6),
"DepartmentId": NumberInt(1),
"TypeId": NumberInt(4),
"CategoryId": NumberInt(2),
"SubcategoryId": NumberInt(333),
"ChangeTime": ISODate("2018-11-19T10:14:20Z"),
"TimeDelta": NumberLong(0), //timespan from last change in MS
"ChangeType": NumberInt(0), // the changed property identifier (0= creation)
"UserId": NumberInt(1)
},
{
"StatusId": NumberInt(8),
"PriorityId": NumberInt(6),
"DepartmentId": NumberInt(2),
"TypeId": NumberInt(4),
"CategoryId": NumberInt(2),
"SubcategoryId": NumberInt(333),
"ChangeTime": ISODate("2018-11-19T10:15:50Z"),
"TimeDelta": NumberLong(90000), //timespan from last change in MS
"ChangeType": NumberInt(4), // the changed property identifier (4= department)
"UserId": NumberInt(1)
},
{
"StatusId": NumberInt(2),
"PriorityId": NumberInt(6),
"DepartmentId": NumberInt(2),
"TypeId": NumberInt(4),
"CategoryId": NumberInt(2),
"SubcategoryId": NumberInt(333),
"ChangeTime": ISODate("2018-11-19T10:16:20Z"),
"TimeDelta": NumberLong(30000), //timespan from last change in MS
"ChangeType": NumberInt(2), // the changed property identifier (2= status)
"UserId": NumberInt(1)
},
{
"StatusId": NumberInt(2),
"PriorityId": NumberInt(6),
"DepartmentId": NumberInt(5),
"TypeId": NumberInt(4),
"CategoryId": NumberInt(2),
"SubcategoryId": NumberInt(333),
"ChangeTime": ISODate("2018-11-19T10:17:20Z"),
"TimeDelta": NumberLong(60000), //timespan from last change in MS
"ChangeType": NumberInt(4), // the changed property identifier (4= department)
"UserId": NumberInt(1)
}
]
}
部门的预期结果随时间变化：
[{
RecordID: 1,
Department: 1,
ChangeTime: ISODate("2018-11-19T10:15:50Z"),
TimeSpent: 90000
},
{
RecordID: 1,
Department: 2,
ChangeTime: ISODate("2018-11-19T10:17:20Z")
TimeSpent: 90000
},
{
RecordID: 1,
Department: 5,
ChangeTime: ISODate("2018-11-21T09:47:47Z") // Current Time
TimeSpent: 171027000 //difference between now and last change in departments
}]
以及状态：
[{
RecordID: 1,
Status: 8,
ChangeTime: ISODate("2018-11-19T10:16:20Z"),
TimeDelta: 120000
},
{
RecordID: 1,
Status: 2,
ChangeTime: ISODate("2018-11-21T09:47:47Z"), // Current Time
TimeDelta: 171087000 //difference between now and last change in status
}]
到目前为止我尝试过的事情
到目前为止，我得到的最好结果是使用以下聚合创建视图，然后在视图上应用$GraphLookup函数：
db.test.aggregate([
{$project: {
_id:0,
RecordID: "$_id",
history: {
$filter: {
input: "$ChangeHistory",
as: "changeHistory",
cond: {$or:[
{$eq:["$$changeHistory.ChangeType",0]},
{$eq:["$$changeHistory.ChangeType",4]}
]}
}
}
}},
{$unwind: {
path: "$history",
includeArrayIndex:"order"
}}, {$project: {
_id:"$RecordID",
"RecordID": "$RecordID",
"departmentID": "$history.DepartmentId",
"actionOrder":"$order",
"nextAction":{$add:["$order",1]},
"time":"$history.ChangeTime"
}}
])
然后应用以下内容：
db.TestView.aggregate([{
$graphLookup: {
from: 'TestView',
startWith: "$nextAction",
connectFromField: 'nextAction',
connectToField: 'actionOrder',
as: 'pair',
}
}, {
$unwind: {
path: "$pair"
}
}, {
$project: {
_id: 0,
RecordID: "$_id",
Department: "$departmentID",
ChangeTime: "$pair.time",
TimeSpent: {
$subtract: ["$pair.time", "$time"]
}
}
}
])
这样做的问题是，它混合了不同文档之间的动作配对，不包括到当前时间为止所花费的时间，并且除了在中间使用视图之外，还具有许多传播方式。
如果需要，可以稍微修改数据结构。
答案 0 :(得分：0)
在发布问题之前，我实际上花了2天的时间来解决这个问题，几个小时后我就解决了。
只想分享我的解决方案，如果有人可以针对性能或其他方面对其进行优化，请随时发布您的答案
解决方案
它使用$zip函数，以便在应用过滤器后通过传递事件的原始数组和该数组的另一个副本（第一个元素除外）来形成动作对，以便第一个元素与第二个匹配，第二个与第三个匹配，依此类推。我还添加了当前时间的默认值，以根据当前时间计算最后一个元素的变化量。
db.test.aggregate([{
$project: {
RecordID: "$_id",
history: {
$filter: {
input: "$ChangeHistory",
as: "changeHistory",
cond: {
$or: [{
$eq: ["$$changeHistory.ChangeType", 0]
},
{
$eq: ["$$changeHistory.ChangeType", 2]
}
]
}
}
}
}
},
{
$addFields: {
pairs: {
$zip: { // here is the trick
inputs: ["$history", {
$slice: ["$history", 1, {
$size: "$history"
}]
}],
useLongestLength: true,
defaults: [0, {
ChangeTime: new Date()
}]
}
}
}
},
{
$unwind: {
path: "$pairs"
}
},
{
$project: {
id: "$_id",
old: {
$arrayElemAt: ["$pairs", 0]
},
new: {
$arrayElemAt: ["$pairs", 1]
}
}
},
{
$project: {
RecordID: "$id",
Status: "$old.StatusId",
TimeDeltaMS: {
$subtract: ["$new.ChangeTime", "$old.ChangeTime"]
},
ChangeTime: "$new.ChangeTime"
}
},
])