Get invoice total from a collection with arrays - mongodb

I have a collection with this structure:
db.shops.insert({
"customer": "21c3",
"shopDate": new Date("2019-06-03T23:00:00Z"),
"shopId" : "Supermarket",
"items" : [
{
"productName": "Water",
"price": 3,
"quantity": 2
},
{
"productName": "Candies",
"price": 1,
"quantity": 5
}
]
});
I need a query to get the total amount of each shopId.
This is what I have done, but it is not working:
db.shops.aggregate(
[
{
$group : {
_id : $shopName,
totalSold: { $sum: { $multiply: [ "$price", "$quantity" ] } },
}
}
]
);

Here is how to do it:
db.shops.aggregate(
[
{
"$unwind": "$items"
},
{
"$group" : {
_id : "$shopId",
totalSold: { $sum: { $multiply: [ "$items.price", "$items.quantity" ] } },
}
}
]
);

Related

Grouping into array in MongoDB

I have MongoDB collection with below documents:
[
{
"productType":"Bike",
"company":"yamaha",
"model":"y1"
},
{
"productType":"Bike",
"company":"bajaj",
"model":"b1"
},
{
"productType":"Bike",
"company":"yamaha",
"model":"y1"
},
{
"productType":"Car",
"company":"Maruti",
"model":"m1"
},
{
"productType":"Bike",
"company":"yamaha",
"model":"y2"
},
{
"productType":"Car",
"company":"Suzuki",
"model":"s1"
}
]
I want my output to be like :
{
"productType": [
{
"name": "Bike",
"count": 4,
"companies": [
{
"name": "Yamaha",
"count": 3,
"models": [
{
"name": "y1",
"count": 2
},
{
"name": "y2",
"count": 1
}
]
},
{
"name": "Bajaj",
"count": 1,
"models": [
{
"name": "b1",
"count": 1
}
]
}
]
},
{
"name": "Car",
"count": 2,
"companies": [
{
"name": "Maruti",
"count": 1,
"models": [
{
"name": "m1",
"count": 1
}
]
},
{
"name": "Suzuki",
"count": 1,
"models": [
{
"name": "s1",
"count": 1
}
]
}
]
}
]
}
I am not able to understand how to create arrays inside existing array using $push. I know we can create an array using $push but how to create array of array with it ?
In future, I might want to add "metaData" field also along with name and count.
You have to run multiple $group stages, one for each level:
db.collection.aggregate([
{
$group: {
_id: { company: "$company", productType: "$productType", model: "$model" },
count: { $sum: 1 }
}
},
{
$group: {
_id: { productType: "$_id.productType", company: "$_id.company" },
models: { $push: { name: "$_id.model", count: "$count" } },
count: { $sum: "$count" }
}
},
{
$group: {
_id: "$_id.productType",
companies: { $push: { company: "$_id.company", models: "$models", count: "$count" } },
count: { $sum: "$count" }
}
},
{ $set: { name: "$_id", _id: "$$REMOVE" } },
{
$group: {
_id: null,
productType: { $push: "$$ROOT" }
}
}
])
Mongo Playground
Try this:
db.testCollection.aggregate([
{
$group: {
_id: {
name: "$productType",
company: "$company",
model: "$model"
},
count: { $sum: 1 }
}
},
{
$group: {
_id: {
name: "$_id.name",
company: "$_id.company"
},
count: { $sum: "$count" },
models: {
$push: {
name: "$_id.model",
count: "$count"
}
}
}
},
{
$group: {
_id: { name: "$_id.name" },
count: { $sum: "$count" },
companies: {
$push: {
name: "$_id.company",
count: "$count",
models: "$models"
}
}
}
},
{
$group: {
_id: null,
productType: {
$push: {
name: "$_id.name",
count: "$count",
companies: "$companies"
}
}
}
},
{
$project: { _id: 0 }
}
]);
Output:
{
"productType" : [
{
"name" : "Car",
"count" : 2,
"companies" : [
{
"name" : "Suzuki",
"count" : 1,
"models" : [
{
"name" : "s1",
"count" : 1
}
]
},
{
"name" : "Maruti",
"count" : 1,
"models" : [
{
"name" : "m1",
"count" : 1
}
]
}
]
},
{
"name" : "Bike",
"count" : 4,
"companies" : [
{
"name" : "yamaha",
"count" : 3,
"models" : [
{
"name" : "y2",
"count" : 1
},
{
"name" : "y1",
"count" : 2
}
]
},
{
"name" : "bajaj",
"count" : 1,
"models" : [
{
"name" : "b1",
"count" : 1
}
]
}
]
}
]
}

How to Implement $bucket to group by multiple fields

At first bucket by age and boundaries is [0,20,30,40,50,200]
db.user.aggregate(
{$project: {_id:0, age:{$subtract:[{$year:new Date()}, {$year:"$birthDay"}]} } },
{$bucket:{
groupBy:"$age",
boundaries:[0,20,30,40,50,200]
}},
{ $project:{ _id:0,age:"$_id",count:1 } }
)
got below result
{ "count" : 5, "age" : 20 }
{ "count" : 1, "age" : 30 }
then further I want to stat every age range count of each city
{ city : "SH", age: 20, count: 2 }
{ city : "BJ", age: 20, count: 3 }
{ city : "BJ", age: 30, count: 1 }
So in this case how to implement it ?
In addition
db.user.aggregate(
{ $project: {_id:0, city:1, age:{$subtract:[{$year:new Date()}, {$year:"$birthDay"}]} } },
{ $group: { _id:"$city",ages:{$push:"$age"} } },
{ $project: {_id:0, city:"$_id",ages:1} }
)
{ "city" : "SH", "ages" : [ 26, 26 ] }
{ "city" : "BJ", "ages" : [ 27, 26, 26, 36 ] }
What you are talking about is actually implemented with $switch, within a regular $group stage:
db.user.aggregate([
{ "$group": {
"_id": {
"city": "$city",
"age": {
"$let": {
"vars": {
"age": { "$subtract" :[{ "$year": new Date() },{ "$year": "$birthDay" }] }
},
"in": {
"$switch": {
"branches": [
{ "case": { "$lt": [ "$$age", 20 ] }, "then": 0 },
{ "case": { "$lt": [ "$$age", 30 ] }, "then": 20 },
{ "case": { "$lt": [ "$$age", 40 ] }, "then": 30 },
{ "case": { "$lt": [ "$$age", 50 ] }, "then": 40 },
{ "case": { "$lt": [ "$$age", 200 ] }, "then": 50 }
]
}
}
}
}
},
"count": { "$sum": 1 }
}}
])
With the results:
{ "_id" : { "city" : "BJ", "age" : 30 }, "count" : 1 }
{ "_id" : { "city" : "BJ", "age" : 20 }, "count" : 3 }
{ "_id" : { "city" : "SH", "age" : 20 }, "count" : 2 }
The $bucket pipeline stage only takes a single field path. You can have multiple accumulators via the "output" option, but the "groupBy" is a single expression.
Note you can also use $let here in preference to a separate $project pipeline stage to calculate the "age".
N.B If you actually throw some erroneous expressions to $bucket you will get errors about $switch, which should hint to you that this is how it is implemented internally.
If you are worried about coding in the $switch then just generate it:
var ranges = [0,20,30,40,50,200];
var branches = [];
for ( var i=1; i < ranges.length; i++) {
branches.push({ "case": { "$lt": [ "$$age", ranges[i] ] }, "then": ranges[i-1] });
}
db.user.aggregate([
{ "$group": {
"_id": {
"city": "$city",
"age": {
"$let": {
"vars": {
"age": {
"$subtract": [{ "$year": new Date() },{ "$year": "$birthDay" }]
}
},
"in": {
"$switch": { "branches": branches }
}
}
}
},
"count": { "$sum": 1 }
}}
])
Supply another implementation by using Map-Reduce
db.user.mapReduce(
function(){
var age = new Date().getFullYear() - this.birthDay.getFullYear();
var ages = [0,20,30,40,50,200]
for(var i=1; i<ages.length; i++){
if(age < ages[i]){
emit({city:this.city,age:ages[i-1]},1);
break;
}
}
},
function(key, counts){
return Array.sum(counts);
},
{ out: "user_city_age_count" }
)

MongoDB avoid duplicates using $addToSet in aggregation pipeline

there is aggregation pipeline:
db.getCollection('yourCollection').aggregate(
{
$unwind: {
path: "$dates",
includeArrayIndex: "idx"
}
},
{
$project: {
_id: 0,
dates: 1,
numbers: { $arrayElemAt: ["$numbers", "$idx"] },
goals: { $arrayElemAt: ["$goals", "$idx"] },
durations: { $arrayElemAt: ["$durations", "$idx"] }
}
}
)
which perform on the following data (sample documents):
{
"_id" : ObjectId("52d017d4b60fb046cdaf4851"),
"dates" : [
1399518702000,
1399126333000,
1399209192000,
1399027545000
],
"dress_number" : "4",
"name" : "J. Evans",
"numbers" : [
"5982",
"5983",
"5984",
"5985"
],
"goals": [
"1",
"0",
"4",
"2"
],
"durations": [
"78",
"45",
"90",
"90"
]
}
{
"_id" : ObjectId("57e250c1b60fb0213d06737c"),
"dates" : [
"1399027545000",
"1399101432000",
"1399026850000",
"1399904504000"
],
"dress_number" : "6",
"name" : K. Mitnick,
"numbers" : [
"0982",
"0981",
"0958",
"0982"
],
"durations" : [
98,
110,
66,
92
],
"goals" : [
"2",
"3",
"0",
"1"
]
}
The query works good, but there are duplicate records so I'm trying to use $addToSet operator to avoid duplicates:
db.getCollection('yourCollection').aggregate(
{
$match: {
"number": number
}
},
{
$unwind: {
path: "$dates",
includeArrayIndex: "idx"
}
},
$group: {
_id: '$_id',
dates: { $addToSet: '$dates' }
},
{
$project: {
_id: 0,
dates: 1,
numbers: { $arrayElemAt: ["$numbers", "$idx"] },
goals: { $arrayElemAt: ["$goals", "$idx"] },
durations: { $arrayElemAt: ["$durations", "$idx"] }
}
}
)
but I got only dates (other field are null)
{ dates:
[ '1399026850000',
'1399101432000',
'1399027545000',
'1399904504000',
'1399024474000',
'1399126333000' ],
numbers: null,
goals: null,
durations: null },
{ dates:
[ '1399027545000',
'1399024474000',
'1399518702000',
'1399126333000',
'1399209192000',
'1399356651000' ],
numbers: null,
goals: null,
conversation_durations: null },
{ dates:
[ '1399026850000',
'1399101432000',
'1399027545000',
'1399904504000',
'1399024474000' ],
numbers: null,
goals: null,
durations: null }
Does anybody know where is the problem?
You need to include the fields within the $group pipeline using the $first operator as follows:
db.getCollection('yourCollection').aggregate([
{ "$unwind": "$dates" },
{
"$group": {
"_id": "$_id",
"dates": { "$addToSet": "$dates" },
"numbers": { "$first": "$numbers" },
"goals": { "$first": "$goals" },
"durations": { "$first": "$durations" }
}
},
{ "$unwind": {
"path": "$dates",
"includeArrayIndex": "idx"
} },
{
"$project": {
"_id": 0,
"dates": 1,
"numbers": { "$arrayElemAt": ["$numbers", "$idx"] },
"goals": { "$arrayElemAt": ["$goals", "$idx"] },
"durations": { "$arrayElemAt": ["$durations", "$idx"] }
}
}
])
or using $setUnion to eliminate duplicates as:
db.getCollection('yourCollection').aggregate([
{
"$project": {
"_id": 0,
"dates": { "$setUnion": ["$dates", "$dates"] },
"numbers": 1,
"goals": 1,
"durations": 1
}
}
{ "$unwind": {
"path": "$dates",
"includeArrayIndex": "idx"
} },
{
"$project": {
"_id": 0,
"dates": 1,
"dateIndex": "$idx",
"numbers": { "$arrayElemAt": ["$numbers", "$idx"] },
"goals": { "$arrayElemAt": ["$goals", "$idx"] },
"durations": { "$arrayElemAt": ["$durations", "$idx"] }
}
}
])

Mongodb aggregate every two hours

I have an aggregate query of the following form
db.mycollection.aggregate([
{
"$match":
{
"Time": { $gte: ISODate("2016-01-30T00:00:00.000+0000") }
}
},
{
"$group":
{
"_id":
{
"day": { "$dayOfYear": "$Time" },
"hour": { "$hour": "$Time" }
},
"Dishes": { "$addToSet": "$Dish" }
}
},
{
"$group":
{
"_id": "$_id.hour",
"Food":
{
"$push":
{
"Day": "$_id.day",
"NumberOfDishes": { "$size":"$Dishes" }
}
}
}
},
{
"$project":
{
"Hour": "$_id",
"Food": "$Food",
"_id" : 0
}
},
{
"$sort": { "Hour": 1 }
}
]);
Instead of doing this as above in one hour durations e.g. 0-1,1-2,2-3,3-4,4-5,...,23-24, I want to be able to do this in two hour durations. e.g. 0-2,2-4,4-6,...,22-24. Is there a way to do that?
Hint: use arithmetic aggregation operators in $project
Lets say, H=floor(hour/2), where hour is actual hour from document date. Then you can get H by applying $floor and $divide operators to this date
"H": { $floor: { $divide: [ { "$hour": "$Time" }, 2 ] } }
Here H corresponds to the pair of hours (Hours=[0,2) => H=0, Hours=[2,4) => H=1, Hours=[22,24) => H=11, etc.) and you can pass it to the $group stage with
$group: { "_id": { "day": { $dayOfYear: "$Time" }, "H": "$H" } }
Then you can output the pair of hours for specific H with
"Hours": [ { $multiply: [ "$H", 2 ] }, { $sum: [ { $multiply: [ "$H", 2 ] }, 2 ] } ]
Given collection of documents
{ "Time" : ISODate("2016-01-30T01:00:00Z"), "Dish" : "dish1" }
{ "Time" : ISODate("2016-01-30T02:00:00Z"), "Dish" : "dish2" }
{ "Time" : ISODate("2016-01-30T03:00:00Z"), "Dish" : "dish3" }
{ "Time" : ISODate("2016-01-30T04:00:00Z"), "Dish" : "dish4" }
{ "Time" : ISODate("2016-01-30T05:00:00Z"), "Dish" : "dish5" }
{ "Time" : ISODate("2016-01-30T06:00:00Z"), "Dish" : "dish6" }
{ "Time" : ISODate("2016-01-30T07:00:00Z"), "Dish" : "dish7" }
{ "Time" : ISODate("2016-01-30T08:00:00Z"), "Dish" : "dish8" }
{ "Time" : ISODate("2016-01-30T09:00:00Z"), "Dish" : "dish9" }
and using the next aggregate on it
db.mycollection.aggregate([
{
"$match":
{
"Time": { $gte: ISODate("2016-01-30T00:00:00.000+0000") }
}
},
{
"$project":
{
"Dish": 1,
"Time": 1,
"H": { $floor: { $divide: [ { $hour: "$Time" }, 2 ] } }
}
},
{
"$group":
{
"_id":
{
"day": { $dayOfYear: "$Time" },
"H": "$H"
},
"Dishes": { $addToSet: "$Dish" }
}
},
{
"$group":
{
"_id": "$_id.H",
"Food":
{
"$push":
{
"Day": "$_id.day",
"NumberOfDishes": { $size: "$Dishes" }
}
}
}
},
{
"$sort": { "_id": 1 }
},
{
"$project":
{
"Hours": [ { $multiply: [ "$_id", 2 ] }, { $sum: [ { $multiply: [ "$_id", 2 ] }, 2 ] } ],
"Food": "$Food",
"_id": 0
}
}
]);
provides the result
{ "Food" : [ { "Day" : 30, "NumberOfDishes" : 1 } ], "Hours" : [ 0, 2 ] }
{ "Food" : [ { "Day" : 30, "NumberOfDishes" : 2 } ], "Hours" : [ 2, 4 ] }
{ "Food" : [ { "Day" : 30, "NumberOfDishes" : 2 } ], "Hours" : [ 4, 6 ] }
{ "Food" : [ { "Day" : 30, "NumberOfDishes" : 2 } ], "Hours" : [ 6, 8 ] }
{ "Food" : [ { "Day" : 30, "NumberOfDishes" : 2 } ], "Hours" : [ 8, 10 ] }

$push and $sum with the aggregation framework on sub-documents

I've a data as follows:
{
"_id" : ObjectId("55d4410544c96d6f6578f893"),
"executionProject" : "Project1",
"suiteList" : [
{
"suiteName": "Suite1",
"suiteStatus" : "PASS",
},
{
"suiteName": "Suite2",
"suiteStatus" : "FAIL",
},
{
"suiteName": "Suite3",
"suiteStatus" : "PASS",
}
],
"runEndTime" : ISODate("2015-08-19T08:40:47.049Z")
}
{
"_id" : ObjectId("55d4410544c96d6f6578f894"),
"executionProject" : "Project1",
"suiteList" : [
{
"suiteName": "Suite1",
"suiteStatus" : "PASS",
},
{
"suiteName": "Suite2",
"suiteStatus" : "FAIL",
},
{
"suiteName": "Suite3",
"suiteStatus" : "FAIL",
}
],
"runEndTime" : ISODate("2015-08-19T08:50:47.049Z")
}
And I was trying to get the result like this:
{
"executionProject": "Project1",
"data": [
{
"date": "2015-08-19 08:40:47",
"suitePass": 2,
"suiteFail": 1
},
{
"date": "2015-08-19 08:50:47",
"suitePass": 1,
"suiteFail": 2
}
]
}
Here I'm trying to group by executionProject and push the runEndTime and the pass and fail counts of suites to the result.
I tried this, but giving me wrong way of projection:
db.testruns.aggregate([
{
$project: {
executionProject: "$executionProject",
runEndTime: "$runEndTime",
suiteList: "$suiteList"
}
},
{
$unwind: "$suiteList"
},
{
$group: {
_id: "$executionProject",
runEndTime: {
$addToSet: "$runEndTime"
},
suite_pass: {
$sum: {
$cond: {
"if": {
$eq: ["$suiteList.suiteStatus", "PASS"]
},
"then": 1,
"else": 0
}
}
}
}
},
{
$group: {
_id: "$_id",
runEndTime: { $push: {runTime: "$runEndTime", suite_pass: "$suite_pass"} }
}
},
{
$project: {
executionProject: "$_id",
runEndTime: "$runEndTime",
_id: 0
}
}
]);
First you need to group by the document to get the suite totals, then you add to the array as you group on the project. Also don't forget to "sort" if you want things in order:
[
{ "$unwind": "$suiteList" },
{ "$group": {
"_id": "$_id",
"executionProject": { "$first": "$executionProject" },
"suite-pass": {
"$sum": {
"$cond": [
{ "$eq": [ "$suiteList.suiteStatus", "PASS" ] },
1,
0
]
}
},
"suite-fail": {
"$sum": {
"$cond": [
{ "$eq": [ "$suiteList.suiteStatus", "FAIL" ] },
1,
0
]
}
},
"date": { "$first": "$runEndTime" }
}},
{ "$sort": { "executionProject": 1, "date": 1 } },
{ "$group": {
"_id": "$executionProject",
"data": {
"$push": {
"suite-pass": "$suite-pass",
"suite-fail": "$suite-fail",
"date": "$date"
}
}
}}
]
Produces:
{
"_id" : "Project1",
"data" : [
{
"suite-pass" : 2,
"suite-fail" : 1,
"date" : ISODate("2015-08-19T08:40:47.049Z")
},
{
"suite-pass" : 1,
"suite-fail" : 2,
"date" : ISODate("2015-08-19T08:50:47.049Z")
}
]
}