What I'm trying to do is map the CodeOT to each object in my payload such as :
null/0 get the value 1
1 to 5 get the value 2
and 6 to 9 get the value 3
I am lost in how to do it as I'm new to dataweave
example of payload :
{
"refSig" : "0110443372",
"indSap":2
},
{
"refSig" : "0000443942",
"indSap":0
},
{
"refSig" : "0117243942",
"indSap":null
}
the conversion table is provided and must be used as is, here's a part of it
{
"CodeSap": null,
"Libelle": "",
"CodeOT": 1
},
{
"CodeSap": 0,
"Libelle": "Elle a demandé un délai de paiement",
"CodeOT": 1
},
{
"CodeSap": 1,
"Libelle": "Elle a des factures SATD",
"CodeOT": 2
},
{
"CodeSap": 2,
"Libelle": "Elle a des factures remises à l’huissier",
"CodeOT": 2
}
I need to map the CodeOT from the conversion table to the indSap from the payload using CodeSap
I started doing this but it doesn't seem to lead me anywhere
%dw 2.0
output application/json
---
lignesOK : payload map (item, index) -> {
bf: item mapObject (value, key) -> {
(key): value,
codeOt: varTable map (it,val) ->{
(val):(it)
}
}
}
expected output for the example of the payload above is :
{
"refSig" : "0110443372",
"CodeOT":2
},
{
"refSig" : "0000443942",
"CodeOT":1
},
{
"refSig" : "0117243942",
"CodeOT":1
}
Assuming that the input and table are arrays and that entries in the table are unique per CodeSap the following script works, though the output is a bit different than expected because of the incomplete table provided:
%dw 2.0
output application/json
var varTable=[{
"CodeSap": null,
"Libelle": "",
"CodeOT": 1
},
{
"CodeSap": 0,
"Libelle": "Elle a demandé un délai de paiement",
"CodeOT": 1
},
{
"CodeSap": 1,
"Libelle": "Elle a des factures SATD",
"CodeOT": 2
},
{
"CodeSap": 2,
"Libelle": "Elle a des factures remises à l’huissier",
"CodeOT": 2
}]
---
payload map (item, index) -> {
refSig: item.refSig,
codeOt: (varTable filter (item.indSap == $.CodeSap))[0].CodeOT
}
Output:
[
{
"refSig": "0110443372",
"codeOt": null
},
{
"refSig": "0000443942",
"codeOt": 1
},
{
"refSig": "0117243942",
"codeOt": 1
}
]
Related
Input:
{
"count": 3,
"employees":
[
{
"name":"appy",
"age":34
},
{
"name":"happy",
"age":38
},
{
"name":"cruise",
"age":36
}
]
}
Output:
[
{
"first":"appy",
"age":34
},
{
"first":"happy",
"age":38
},
{
"first":"cruise",
"age":36
}
]
This is my input i am trying to add "first" in "name" how can i do any suggestions i am using Map function here.
"first" in "name" place i am trying to use map function
Just map the elements:
%dw 2.0
output application/json
---
payload.employees map {
first: $.name,
age: $.age
}
Output:
[
{
"first": "appy",
"age": 34
},
{
"first": "happy",
"age": 38
},
{
"first": "cruise",
"age": 36
}
]
In my mongodb collection documents are stored in the following format:
{ "_id" : ObjectId("62XXXXXX"), "res" : 12, ... }
{ "_id" : ObjectId("63XXXXXX"), "res" : 23, ... }
{ "_id" : ObjectId("64XXXXXX"), "res" : 78, ... }
...
I need to extract id's for the document for which the value of "res" is outlier (i.e. value < Q1 - 1.5 * IQR or value > Q3 + 1.5 * IQR (Q1, Q3 are percentiles)). I have done this using pandas functionality by retrieving all documents from the collection, which may become slow if the number of documents in collection become too big.
Is there a way to do this using mongodb aggregation pipeline (or just calculating percentiles)?
If I understand how you want to retrieve outliers, here's one way you might be able to do it.
db.collection.aggregate([
{ // partition res into quartiles
"$bucketAuto": {
"groupBy": "$res",
"buckets": 4
}
},
{ // get the max of each quartile
"$group": {
"_id": "$_id.max"
}
},
{ // sort the quartile maxs
"$sort": {
"_id": 1
}
},
{ // put sorted quartile maxs into array
"$group": {
"_id": null,
"maxs": {"$push": "$_id"}
}
},
{ // assign Q1 and Q3
"$project": {
"_id": 0,
"q1": {"$arrayElemAt": ["$maxs", 0]},
"q3": {"$arrayElemAt": ["$maxs", 2]}
}
},
{ // set IQR
"$set": {
"iqr": {
"$subtract": ["$q3", "$q1"]
}
}
},
{ // assign upper/lower outlier thresholds
"$project": {
"outlierThresholdLower": {
"$subtract": [
"$q1",
{"$multiply": ["$iqr", 1.5]}
]
},
"outlierThresholdUpper": {
"$add": [
"$q3",
{"$multiply": ["$iqr", 1.5]}
]
}
}
},
{ // get outlier _id's
"$lookup": {
"from": "collection",
"as": "outliers",
"let": {
"oTL": "$outlierThresholdLower",
"oTU": "$outlierThresholdUpper"
},
"pipeline": [
{
"$match": {
"$expr": {
"$or": [
{"$lt": ["$res", "$$oTL"]},
{"$gt": ["$res", "$$oTU"]}
]
}
}
},
{
"$project": {
"_id": 1
}
}
]
}
}
])
Try it on mongoplayground.net.
One more option based on #rickhg12hs's answer, is to use $setWindowFields:
db.collection.aggregate([
{$setWindowFields: {
sortBy: {res: 1},
output: {
totalCount: {$count: {}},
index: {$sum: 1, window: {documents: ["unbounded", "current"]}}
}
}
},
{$match: {
$expr: {$lte: [
{$abs: {$subtract: [
{$mod: [
{$multiply: [
{$add: ["$index", {$round: {$divide: ["$totalCount", 4]}}]}, 2]},
"$totalCount"
]}, 0]}
}, 1]}
}},
{$group: {_id: null, res: {$push: "$res"}}},
{$project: {_id: 0, q1: {$first: "$res"}, q3: {$last: "$res"},
iqr: {"$subtract": [{$last: "$res"}, {$first: "$res"}]}
}},
{$project: {
outlierThresholdLower: {$subtract: ["$q1", {$multiply: ["$iqr", 1.5]}]},
outlierThresholdUpper: {$add: ["$q3", {$multiply: ["$iqr", 1.5]}]}
}
},
{$lookup: {
from: "collection",
as: "outliers",
let: {oTL: "$outlierThresholdLower", oTU: "$outlierThresholdUpper"},
pipeline: [
{$match: {$expr: {$or: [{$lt: ["$res", "$$oTL"]}, {$gt: ["$res", "$$oTU"]}]}}},
{$project: {_id: 1}}
]
}
}
])
See how it works on the playground example
I'm new to SQL and MongoDB. I'm trying to convert this:
SELECT accountType, ROUND(AVG(balance), 2) avgBalance
FROM customers
WHERE gender="female"
GROUP BY accountType
HAVING COUNT(*) < 140
ORDER BY avgBalance
LIMIT 1
to MongoDB but I can't get it to work. I don't quite understand how the order ($group, $match, $project, $round, $avg etc.) should be and how the "ROUND and AVG" are used together. This is how the answer should be like: { "accountType" : "account-type", "avgBalance" : NumberDecimal("9999.99") }
Here is what I have so far:
db.customers.aggregate( [ { $group: { _id: { accountType: "accountType", avgBalance: { $avg: { "balance" } } }, { $match: { count: { $lt: 140 } } }, { gender: "female" }, { $project: { "accountType": { $round: [ $agv: "balance", 2 ] } } }, { $limit: 1 } ] )
Direction is not bad, would be this one:
db.customers.aggregate([
// WHERE gender="female"
{ $match: { gender: "female" } },
// GROUP BY accountType, SELECT AVG(balance)
{
$group: {
_id: "$accountType",
avgBalance: { $avg: "$balance" },
count: {$sum: 1}
}
},
// HAVING COUNT(*) < 140
{ $match: { count: { $lt: 140 } } },
// SELECT ... AS ...
{
$project: {
accountType: "$_id",
avgBalance: { $round: ["$avgBalance", 2] }
}
},
// ORDER BY avgBalance
{ $sort: { avgBalance: 1 } },
// LIMIT 1
{ $limit: 1 }
])
Realise this topic has been asked many times - but the advice hasn't helped me solve this problem.
The following query is trying to determine the presence of sales on a given weekday using ISODay. Because the query will be run at the start of the month, I need to know how many occurrences of the specific ISOday occur in the month.
var query = { eventType: 'Sale', site : 4, tank: 1, txnDate : { "$gt" : new Date('2018-08-01T00:00:00') } };
db.tankevent.aggregate([
{ $match: query },
{ $project : {
isoDay: { $isoDayOfWeek: "$txnDate" },
dayDate: { $dateToString: { format: "%d", date:"$txnDate" } }
}
},
{ $group:
{ _id : { isoday: "$isoDay", dday: "$dayDate" }, count: { "$sum" : 1 } }
},
{ $sort: { "_id.isoday": 1, "_id.dday": 1 } }
])
provides the following output
/* 1 */
{
"_id" : {
"isoday" : 1,
"dday" : "06"
},
"count" : 62.0
}
/* 2 */
{
"_id" : {
"isoday" : 1,
"dday" : "13"
},
"count" : 69.0
}
/* 3 */
{
"_id" : {
"isoday" : 1,
"dday" : "20"
},
"count" : 72.0
}
/* 4 */
{
"_id" : {
"isoday" : 2,
"dday" : "07"
},
"count" : 75.0
}
I am trying to have "count" represent the number of unique "dday" records - so using the output above, I want count to be "3" for isoDay = 1. At the moment count is reporting number of sales events that occurred for the group combination
All you need to do is have the grouping twice.
db.tankevent.aggregate([
{ $match: query },
{ $project : {
isoDay: { $isoDayOfWeek: "$txnDate" },
dayDate: { $dateToString: { format: "%d", date:"$txnDate" } }
}
},
{ $group:
{ _id : { isoday: "$isoDay", dday: "$dayDate" }, count: { "$sum" : 1 } }
},
{ $project : {
isoDay_Final: "$_id.isoday"
}
},
{ $group:
{ _id : "$isoDay_Final", count: { "$sum" : 1 } }
},
{ $sort: { "_id": 1 } }
])
I have a collection as below
{"country":"US","city":"NY"}
{"country":"US","city":"AL"}
{"country":"US","city":"MA"}
{"country":"US","city":"NY"}
{"country":"US","city":"MA"}
{"country":"IN","city":"DL"}
{"country":"IN","city":"KA"}
{"country":"IN","city":"DL"}
{"country":"IN","city":"DL"}
{"country":"IN","city":"KA"}
and expecting an output
{ "data": { "US": {"NY": 2,"AL": 1,"MA": 2 },
"IN": {"DL": 3,"KA": 2 }}
}
Below is the mongodb query I tried, i was able to get to get the count at country level, but not at the state level. please help me in correcting the below query to get data at state level.
db.country_dash.aggregate([
{"$group": {
"_id":"$country",
"state": {"$addToSet": "$state"}
}},
{"$project": {
"_id":0,
"country":"$_id",
"state": {"$size": "$state"}
} }
])
db.country_dash.aggregate(
// Pipeline
[
// Stage 1
{
$group: {
_id: {
city: '$city'
},
total: {
$sum: 1
},
country: {
$addToSet: '$country'
}
}
},
// Stage 2
{
$project: {
total: 1,
country: {
$arrayElemAt: ['$country', 0]
},
city: '$_id.city',
_id: 0
}
},
// Stage 3
{
$group: {
_id: '$country',
data: {
$addToSet: {
city: '$city',
total: '$total'
}
}
}
},
]
);