Unable to create nested json output (aggregated) from CSV input
Issue I am facing is I need aggregation of CSV inputs on ID, and it contains multiple nesting. I am able to perform single nesting, but on further nesting, I am not able to write correct syntax.
INPUT:
input {
generator {
id => "first"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,HCC,0.83,COMMUNITYID1'
count => 1
}
generator {
id => "second"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,LACE,12,COMMUNITYID1'
count => 1
}
generator {
id => "third"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,CCI,0.23,COMMUNITYID1'
count => 1
}
}
filter
{
csv {
columns => ['id', 'reference', 'occurrenceDateTime', 'code', 'probabilityDecimal', 'comment']
}
mutate {
rename => {
"reference" => "[subject][reference]"
"code" => "[prediction][outcome][coding][code]"
"probabilityDecimal" => "[prediction][probabilityDecimal]"
}
}
mutate {
add_field => {
"[resourceType]" => "RiskAssessment"
"[prediction][outcome][text]" => "Member HCC score based on CMS HCC V22 risk adjustment model"
"[status]" => "final"
}
}
mutate {
update => {
"[subject][reference]" => "Patient/%{[subject][reference]}"
"[comment]" => "CommunityId/%{[comment]}"
}
}
mutate {
remove_field => [ "@timestamp", "sequence", "@version", "message", "host", "type" ]
}
}
filter {
aggregate {
task_id => "%{id}"
code => "
map['resourceType'] = event.get('resourceType')
map['id'] = event.get('id')
map['status'] = event.get('status')
map['occurrenceDateTime'] = event.get('occurrenceDateTime')
map['comment'] = event.get('comment')
map['[reference]'] = event.get('[subject][reference]')
map['[prediction]'] ||=
map['[prediction]'] << {
'code' => event.get('[prediction][outcome][coding][code]'),
'text' => event.get('[prediction][outcome][text]'),
'probabilityDecimal'=> event.get('[prediction][probabilityDecimal]')
}
event.cancel()
"
push_previous_map_as_event => true
timeout => 3
}
mutate {
remove_field => [ "@timestamp", "tags", "@version"]
}
}
output{
elasticsearch {
template => "templates/riskFactor.json"
template_name => "riskFactor"
action => "index"
hosts => ["localhost:9201"]
index => ["deepak"]
}
stdout {
codec => json{}
}
}
OUTPUT:
{
"reference": "Patient/GSIH1",
"comment": "CommunityId/COMMUNITYID1",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"resourceType": "RiskAssessment",
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"probabilityDecimal": "0.83",
"code": "HCC",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "0.23",
"code": "CCI",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "12",
"code": "LACE",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
}
]
}
REQUIRED OUTPUT:
{
"resourceType": "RiskAssessment",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"subject": {
"reference": "Patient/GSIH1"
},
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"outcome": {
"coding": [
{
"code": "HCC"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
},
{
"outcome": {
"coding": [
{
"code": "CCI"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
}
],
"comment": "CommunityId/COMMUNITYID1"
}
elasticsearch logstash aggregate
add a comment |
Issue I am facing is I need aggregation of CSV inputs on ID, and it contains multiple nesting. I am able to perform single nesting, but on further nesting, I am not able to write correct syntax.
INPUT:
input {
generator {
id => "first"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,HCC,0.83,COMMUNITYID1'
count => 1
}
generator {
id => "second"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,LACE,12,COMMUNITYID1'
count => 1
}
generator {
id => "third"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,CCI,0.23,COMMUNITYID1'
count => 1
}
}
filter
{
csv {
columns => ['id', 'reference', 'occurrenceDateTime', 'code', 'probabilityDecimal', 'comment']
}
mutate {
rename => {
"reference" => "[subject][reference]"
"code" => "[prediction][outcome][coding][code]"
"probabilityDecimal" => "[prediction][probabilityDecimal]"
}
}
mutate {
add_field => {
"[resourceType]" => "RiskAssessment"
"[prediction][outcome][text]" => "Member HCC score based on CMS HCC V22 risk adjustment model"
"[status]" => "final"
}
}
mutate {
update => {
"[subject][reference]" => "Patient/%{[subject][reference]}"
"[comment]" => "CommunityId/%{[comment]}"
}
}
mutate {
remove_field => [ "@timestamp", "sequence", "@version", "message", "host", "type" ]
}
}
filter {
aggregate {
task_id => "%{id}"
code => "
map['resourceType'] = event.get('resourceType')
map['id'] = event.get('id')
map['status'] = event.get('status')
map['occurrenceDateTime'] = event.get('occurrenceDateTime')
map['comment'] = event.get('comment')
map['[reference]'] = event.get('[subject][reference]')
map['[prediction]'] ||=
map['[prediction]'] << {
'code' => event.get('[prediction][outcome][coding][code]'),
'text' => event.get('[prediction][outcome][text]'),
'probabilityDecimal'=> event.get('[prediction][probabilityDecimal]')
}
event.cancel()
"
push_previous_map_as_event => true
timeout => 3
}
mutate {
remove_field => [ "@timestamp", "tags", "@version"]
}
}
output{
elasticsearch {
template => "templates/riskFactor.json"
template_name => "riskFactor"
action => "index"
hosts => ["localhost:9201"]
index => ["deepak"]
}
stdout {
codec => json{}
}
}
OUTPUT:
{
"reference": "Patient/GSIH1",
"comment": "CommunityId/COMMUNITYID1",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"resourceType": "RiskAssessment",
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"probabilityDecimal": "0.83",
"code": "HCC",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "0.23",
"code": "CCI",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "12",
"code": "LACE",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
}
]
}
REQUIRED OUTPUT:
{
"resourceType": "RiskAssessment",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"subject": {
"reference": "Patient/GSIH1"
},
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"outcome": {
"coding": [
{
"code": "HCC"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
},
{
"outcome": {
"coding": [
{
"code": "CCI"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
}
],
"comment": "CommunityId/COMMUNITYID1"
}
elasticsearch logstash aggregate
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14
add a comment |
Issue I am facing is I need aggregation of CSV inputs on ID, and it contains multiple nesting. I am able to perform single nesting, but on further nesting, I am not able to write correct syntax.
INPUT:
input {
generator {
id => "first"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,HCC,0.83,COMMUNITYID1'
count => 1
}
generator {
id => "second"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,LACE,12,COMMUNITYID1'
count => 1
}
generator {
id => "third"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,CCI,0.23,COMMUNITYID1'
count => 1
}
}
filter
{
csv {
columns => ['id', 'reference', 'occurrenceDateTime', 'code', 'probabilityDecimal', 'comment']
}
mutate {
rename => {
"reference" => "[subject][reference]"
"code" => "[prediction][outcome][coding][code]"
"probabilityDecimal" => "[prediction][probabilityDecimal]"
}
}
mutate {
add_field => {
"[resourceType]" => "RiskAssessment"
"[prediction][outcome][text]" => "Member HCC score based on CMS HCC V22 risk adjustment model"
"[status]" => "final"
}
}
mutate {
update => {
"[subject][reference]" => "Patient/%{[subject][reference]}"
"[comment]" => "CommunityId/%{[comment]}"
}
}
mutate {
remove_field => [ "@timestamp", "sequence", "@version", "message", "host", "type" ]
}
}
filter {
aggregate {
task_id => "%{id}"
code => "
map['resourceType'] = event.get('resourceType')
map['id'] = event.get('id')
map['status'] = event.get('status')
map['occurrenceDateTime'] = event.get('occurrenceDateTime')
map['comment'] = event.get('comment')
map['[reference]'] = event.get('[subject][reference]')
map['[prediction]'] ||=
map['[prediction]'] << {
'code' => event.get('[prediction][outcome][coding][code]'),
'text' => event.get('[prediction][outcome][text]'),
'probabilityDecimal'=> event.get('[prediction][probabilityDecimal]')
}
event.cancel()
"
push_previous_map_as_event => true
timeout => 3
}
mutate {
remove_field => [ "@timestamp", "tags", "@version"]
}
}
output{
elasticsearch {
template => "templates/riskFactor.json"
template_name => "riskFactor"
action => "index"
hosts => ["localhost:9201"]
index => ["deepak"]
}
stdout {
codec => json{}
}
}
OUTPUT:
{
"reference": "Patient/GSIH1",
"comment": "CommunityId/COMMUNITYID1",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"resourceType": "RiskAssessment",
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"probabilityDecimal": "0.83",
"code": "HCC",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "0.23",
"code": "CCI",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "12",
"code": "LACE",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
}
]
}
REQUIRED OUTPUT:
{
"resourceType": "RiskAssessment",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"subject": {
"reference": "Patient/GSIH1"
},
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"outcome": {
"coding": [
{
"code": "HCC"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
},
{
"outcome": {
"coding": [
{
"code": "CCI"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
}
],
"comment": "CommunityId/COMMUNITYID1"
}
elasticsearch logstash aggregate
Issue I am facing is I need aggregation of CSV inputs on ID, and it contains multiple nesting. I am able to perform single nesting, but on further nesting, I am not able to write correct syntax.
INPUT:
input {
generator {
id => "first"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,HCC,0.83,COMMUNITYID1'
count => 1
}
generator {
id => "second"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,LACE,12,COMMUNITYID1'
count => 1
}
generator {
id => "third"
type => 'csv'
message => '829cd0e0-8d24-4f25-92e1-724e6bd811e0,GSIH1,2017-10-10 00:00:00.000,CCI,0.23,COMMUNITYID1'
count => 1
}
}
filter
{
csv {
columns => ['id', 'reference', 'occurrenceDateTime', 'code', 'probabilityDecimal', 'comment']
}
mutate {
rename => {
"reference" => "[subject][reference]"
"code" => "[prediction][outcome][coding][code]"
"probabilityDecimal" => "[prediction][probabilityDecimal]"
}
}
mutate {
add_field => {
"[resourceType]" => "RiskAssessment"
"[prediction][outcome][text]" => "Member HCC score based on CMS HCC V22 risk adjustment model"
"[status]" => "final"
}
}
mutate {
update => {
"[subject][reference]" => "Patient/%{[subject][reference]}"
"[comment]" => "CommunityId/%{[comment]}"
}
}
mutate {
remove_field => [ "@timestamp", "sequence", "@version", "message", "host", "type" ]
}
}
filter {
aggregate {
task_id => "%{id}"
code => "
map['resourceType'] = event.get('resourceType')
map['id'] = event.get('id')
map['status'] = event.get('status')
map['occurrenceDateTime'] = event.get('occurrenceDateTime')
map['comment'] = event.get('comment')
map['[reference]'] = event.get('[subject][reference]')
map['[prediction]'] ||=
map['[prediction]'] << {
'code' => event.get('[prediction][outcome][coding][code]'),
'text' => event.get('[prediction][outcome][text]'),
'probabilityDecimal'=> event.get('[prediction][probabilityDecimal]')
}
event.cancel()
"
push_previous_map_as_event => true
timeout => 3
}
mutate {
remove_field => [ "@timestamp", "tags", "@version"]
}
}
output{
elasticsearch {
template => "templates/riskFactor.json"
template_name => "riskFactor"
action => "index"
hosts => ["localhost:9201"]
index => ["deepak"]
}
stdout {
codec => json{}
}
}
OUTPUT:
{
"reference": "Patient/GSIH1",
"comment": "CommunityId/COMMUNITYID1",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"resourceType": "RiskAssessment",
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"probabilityDecimal": "0.83",
"code": "HCC",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "0.23",
"code": "CCI",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
{
"probabilityDecimal": "12",
"code": "LACE",
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
}
]
}
REQUIRED OUTPUT:
{
"resourceType": "RiskAssessment",
"id": "829cd0e0-8d24-4f25-92e1-724e6bd811e0",
"status": "final",
"subject": {
"reference": "Patient/GSIH1"
},
"occurrenceDateTime": "2017-10-10 00:00:00.000",
"prediction": [
{
"outcome": {
"coding": [
{
"code": "HCC"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
},
{
"outcome": {
"coding": [
{
"code": "CCI"
}
],
"text": "Member HCC score based on CMS HCC V22 risk adjustment model"
},
"probabilityDecimal": 0.83
}
],
"comment": "CommunityId/COMMUNITYID1"
}
elasticsearch logstash aggregate
elasticsearch logstash aggregate
edited Jan 25 at 11:27


James Z
11.2k71936
11.2k71936
asked Jan 2 at 10:12


Deepak SinghalDeepak Singhal
84
84
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14
add a comment |
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54004471%2funable-to-create-nested-json-output-aggregated-from-csv-input%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54004471%2funable-to-create-nested-json-output-aggregated-from-csv-input%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
- Can you possibly provide only the essential JSON? It is entirely too much to read.
– AlvinfromDiaspar
Jan 2 at 12:12
Also, what is "PFA"? Can't you spell it out instead of using shortcuts like this?
– AlvinfromDiaspar
Jan 2 at 12:13
I have inserted complete json input to provide a better understanding, and I have used PFA (Please find attached) hoping that its popular enough abbreviations to get my query clear. Any updates on the answer ? @AlvinfromDiaspar
– Deepak Singhal
Jan 3 at 6:14