I have multiple locations:
Document 1 -
"contact": [
{
"address": {
"geolocation": {
"lon": -73.5409,
"lat": 41.2512
}
}
}
]
Document 2 -
{ "contact": [
{
"address": {
"geolocation": {
"lon": -73.7055,
"lat": 40.6744
}
}
},
{
"address": [
{
"geolocation": {
"lon": -73.9325,
"lat": 40.7482
}
},
{
"geolocation": {
"lon": -87.9921,
"lat": 42.9959
}
},
{
"geolocation": {
"lon": -95.4563,
"lat": 29.8775
}
}
]
}
]
}
geo_distance finds both documents by closest location.
"geo_distance": {
"distance": "275mi",
"distance_type": "plane",
"contact.address.geolocation": {
"lat": 42,
"lon": -71
},
"unit": "mi"
}
}
But when I add script field to output lat, lon, and distance
"script_fields": {
"distance_value": {
"script": "doc.containsKey('contact.address.geolocation') ? doc['contact.address.geolocation'].value ? doc['contact.address.geolocation'].arcDistanceInMiles(42.2882,-71.0474) : null : null"
},
"geolocation": {
"script": "doc.containsKey('contact.address.geolocation') ? doc['contact.address.geolocation'].value : null"
}
}
it output random geolocation element from Document 2.
For document 1 it is 147 miles
But for document 2 it is 1601 miles because it takes different location than in geo_distance filter.
How can I print same value as in geo_distance? I want to show distance to my point.
I've tried this script:
"script_fields": {
"distance_value": {
"script": "if (doc.containsKey('contact.address.geolocation')==false) return null; min = 40000; for(e in doc['contact.address.geolocation']){ c=0; if(e!=null) c = e.arcDistanceInMiles(42.2882,-71.0474); if(c<min) min=c;}; return min;"
}
}
It gives error
No signature of method: org.elasticsearch.common.geo.GeoPoint.arcDistanceInMiles() is applicable for argument types: (java.lang.Double, java.lang.Double)
Also I don't think it will iterate over all gelocation fields.
I found only one way to output same distance as in the filter - add "sort" element:
"sort": [
"_score",
{
"_geo_distance": {
"contact.address.geolocation": [
-71,
42
],
"order": "asc",
"unit": "mi"
}
}
]
Related
I have ES documents similar to this, I have a location array with a type field.
{
"type": "A/B/C",
"locations1": [
{
"lat": 19.0179332,
"lon": 72.868069
},
{
"lat": 18.4421771,
"lon": 73.8585108
}
]
}
Type value determines the distance applicable for that location.
Let's say, the allowed distance of query for type A is 10km, for type B is 100km, for type C is 1000km.
Given location L, I want to find all documents which satisfy the distance criteria for that document for the given location and the final result should be sorted by distance.
I am not able to figure out how to use dynamic radius for this. Is it possible or I need to change my document structure similar to this?
EDIT:
I was also thinking of destructing the document locations like this
"locationsTypeA": [
{
"lat": 19.0179332,
"lon": 72.868069
},
{
"lat": 18.4421771,
"lon": 73.8585108
}
],
"locationsTypeB": [
{
"lat": 19.0179332,
"lon": 72.868069
},
{
"lat": 18.4421771,
"lon": 73.8585108
}
],
"locationsTypeC": [
{
"lat": 19.0179332,
"lon": 72.868069
},
{
"lat": 18.4421771,
"lon": 73.8585108
}
]
}
And then I can use the query
"query": {
"bool": {
"should": [
{
"geo_distance": {
"distance": "10km",
"locationsTypeA": {
"lat": 12.5,
"lon": 18.2
}
}
},
{
"geo_distance": {
"distance": "100km",
"locationsTypeB": {
"lat": 12.5,
"lon": 18.2
}
}
},
{
"geo_distance": {
"distance": "1000km",
"locationsTypeC": {
"lat": 12.5,
"lon": 18.2
}
}
}
]
}
}
}
Using the 1st doc structure and the mapping looking like:
PUT geoindex
{
"mappings": {
"properties": {
"locations": {
"type": "geo_point"
}
}
}
}
Let's take a random point between Pune and Mumbai to be the origin relative to which we'll perform a scripted geo query using the arcDistance function:
GET geoindex/_search
{
"query": {
"bool": {
"must": [
{
"script": {
"script": {
"source": """
def type = doc['type.keyword'].value;
def dynamic_distance;
if (type == "A") {
dynamic_distance = 10e3;
} else if (type == "B") {
dynamic_distance = 100e3;
} else if (type == "C") {
dynamic_distance = 1000e3;
}
def distance_in_m = doc['locations'].arcDistance(
params.origin.lat,
params.origin.lon
);
return distance_in_m < dynamic_distance
""",
"params": {
"origin": {
"lat": 18.81531,
"lon": 73.49029
}
}
}
}
}
]
}
},
"sort": [
{
"_geo_distance": {
"locations": {
"lat": 18.81531,
"lon": 73.49029
},
"order": "asc"
}
}
]
}
I did the similar but less complex approach
Here's the code:
{
query: {
bool: {
must: [
{
match: {
companyName: {
query: req.text
}
}
},
{
script: {
script: {
params: {
lat: parseFloat(req.lat),
lon: parseFloat(req.lon)
},
source: "doc['location'].arcDistance(params.lat, params.lon) / 1000 < doc['searchRadius'].value",
lang: "painless"
}
}
}
]
}
},
sort: [
{
_geo_distance: {
location: {
lat: parseFloat(req.lat),
lon: parseFloat(req.lon)
},
order: "asc",
unit:"km"
}
}
],
I am trying to understand how elastic search supports Geo Spatial search internally.
For the basic search, it uses the inverted index; but how does it combine with the additional search criteria like searching for a particular text within a certain radius.
I would like to understand the internals of how the index would be stored and queried to support these queries
Text & geo queries are executed separately of one another. Let's take a concrete example:
PUT restaurants
{
"mappings": {
"properties": {
"location": {
"type": "geo_point"
},
"menu": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword"
}
}
}
}
}
}
POST restaurants/_doc
{
"name": "rest1",
"location": {
"lat": 40.739812,
"lon": -74.006201
},
"menu": [
"european",
"french",
"pizza"
]
}
POST restaurants/_doc
{
"name": "rest2",
"location": {
"lat": 40.7403963,
"lon": -73.9950026
},
"menu": [
"pizza",
"kebab"
]
}
You'd then match a text field and apply a geo_distance filter:
GET restaurants/_search
{
"query": {
"bool": {
"must": [
{
"match": {
"menu": "pizza"
}
},
{
"geo_distance": {
"distance": "0.5mi",
"location": {
"lat": 40.7388,
"lon": -73.9982
}
}
},
{
"function_score": {
"query": {
"match_all": {}
},
"boost_mode": "avg",
"functions": [
{
"gauss": {
"location": {
"origin": {
"lat": 40.7388,
"lon": -73.9982
},
"scale": "0.5mi"
}
}
}
]
}
}
]
}
}
}
Since the geo_distance query only assigns a boolean value (--> score=1; only checking if the location is within a given radius), you may want to apply a gaussian function_score to boost the locations that are closer to a given origin.
Finally, these scores are overridable by using a _geo_distance sort where you'd order by the proximity (while of course keeping the match query intact):
...
"query: {...},
"sort": [
{
"_geo_distance": {
"location": {
"lat": 40.7388,
"lon": -73.9982
},
"order": "asc"
}
}
]
}
I have data in this format generated from a random walk (to simulate people walking around). It is set up in this manner { location : { lat: someLat, lon: someLong }, id: uniqueId, date:date }. I am trying to write a query given a users unique ID, find how many other unique IDs came within X distance of the given ID between a certain time range. Any hints on how to accomplish this?
My idea is to have a top level filter aggregration, with a nested geo-query of some sort. I think the geo-distance query is the way to go, but I am not sure how to include it into the below query to get all of unique IDs that come within X distance of the ID I am filtering on. The query below is where I am starting from, I am filtering all documents from now - 1 day to now, where the documents user Id is the provided value. How would I check all other documents for their distances against documents that match this query?
{
"aggs" : {
"range": {
"date_range": {
"field": "date",
"format": "MM-yyyy",
"ranges": [
{ "to": "now" },
{ "from": "now-1d" }
]
}
},
"locations" : {
"filter" : {
"term": { "id.keyword": "7a50ab18-886b-42a2-80ad-3d45112e3cfd" }
}
}
}
}
Your hunch is correct. All of this can be done using range & geo_distance filtering and _geo_distance sorting. You wanna filter on the query-level, not in the aggs though:
GET walking/_search
{
"size": 0,
"query": {
"bool": {
"must": [
{
"range": {
"date": {
"gte": "now-1d"
}
}
}
],
"filter": [
{
"geo_distance": {
"distance": "20m",
"location": {
"lat": 48.20150179951008,
"lon": 16.39111876487732
}
}
}
]
}
},
"aggs": {
"rings_around_loc": {
"geo_distance": {
"field": "location",
"origin": {
"lat": 48.20150179951008,
"lon": 16.39111876487732
},
"unit": "m",
"keyed": true,
"ranges": [
{
"to": 10
},
{
"from": 10,
"to": 50
},
{
"from": 50
}
]
}
},
"locations": {
"value_count": {
"field": "id.keyword"
}
}
},
"sort": [
{
"_geo_distance": {
"location": {
"lat": 48.20150179951008,
"lon": 16.39111876487732
},
"order": "asc",
"unit": "m",
"mode": "min",
"distance_type": "arc",
"ignore_unmapped": true
}
}
]
}
Not sure what you need the range buckets for so I left them out.
Full steps to replicate:
PUT walking
{
"mappings": {
"properties": {
"date": {
"type": "date"
},
"id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword"
}
}
},
"location": {
"type": "geo_point"
}
}
}
}
And then POST _bulk this random walk data
I'm using Elasticsearch 5.1 with geohash_grid query as below:
{
"query": {
...
"geo_bounding_box":...
},
"aggs": {
"lochash": {
"geohash_grid": {
"field": "currentShopGeo",
"precision": 5
}
}
}
}
And here is the results of elasticsearch:
{
....,
"aggregations": {
"lochash": {
"buckets": [
{
"key": "w3gvv",
"doc_count": 1 // only 1 doc_count
}
]
}
}
}
Then, I used "w3gvv" to decode geohash and have a bounding box as below following "w3gvv".
{
"top_left": {
"lat": 10.8984375,
"lon": 106.7431640625
},
"bottom_right": {
"lat": 10.8544921875,
"lon": 106.787109375
}
}
However, when I use the returned bounding box above to search for the document inside, it appears that Elasticsearch returns 13 items more. Anyone have any idea why it is so weird?
Got a solution,
We could use geo_bounds to know the exact boundary of the clusters that are returned by Elasticsearch as below:
"aggs": {
"lochash": {
"geohash_grid": {
"field": "currentShopGeo",
"precision": 5
},
"aggs": {
"cell": {
"geo_bounds": {
"field": "currentShopGeo"
}
}
}
}
}
The result should be:
{
"key": "w3gvv",
"doc_count": 1,
"cell": {
"bounds": {
"top_left": {
"lat": 10.860191588290036,
"lon": 106.75263083539903
},
"bottom_right": {
"lat": 10.860191588290036,
"lon": 106.75263083539903
}
}
}
}
It appears that the results shows exactly where the item is.
What I try to achieve is an aggregation of geo_bounds. However, in the test database we got some strange values where the location might be negative (this isn't per say strange) which doesn't make sense in this case.
For some queries, this might result in a bounding box which covers another country which we are not expecting.
I would like to filter the geo_bounds aggregation where either longitude or latitude must be larger than 0.
I know that there is a filter for aggregations, as specified on https://www.elastic.co/guide/en/elasticsearch/reference/1.6/search-aggregations-bucket-filter-aggregation.html but I am really not sure how to range check the longitude or latitude.
In our index model we got a structure where we have a location object which contains lon and lat.
As negative values is valid for location, they're treated as valid by ES. So, 2 options here: validate data during indexing (way better IMO, but seems that its too late in your case) or filtering out points with negative location values in query.
The problem with on-the-fly filtering is that ES can actually filter geo-points with 4 filters only. And this filters are not that cheap in terms of performance. You can use geo_bounding_box for your need, like this:
Index:
PUT so/_mapping/t1
{
"t1": {
"properties": {
"pin": {
"properties": {
"location": {
"type": "geo_point"
}
}
}
}
}
}
POST so/t1
{
"pin": {
"location": {
"lat": 10.1,
"lon": 9.9
}
}
}
POST so/t1
{
"pin": {
"location": {
"lat": 20.1,
"lon": 99.9
}
}
}
POST so/t1
{
"pin": {
"location": {
"lat": -10.1,
"lon": -9.9
}
}
}
Query:
GET so/t1/_search?search_type=count
{
"aggs": {
"plain": {
"geo_bounds": {
"field": "pin.location"
}
},
"positive": {
"filter": {
"geo_bounding_box": {
"pin.location": {
"top_left": {
"lat": 90,
"lon": 0
},
"bottom_right": {
"lat": 0,
"lon": 180
}
}
}
},
"aggs": {
"bounds": {
"geo_bounds": {
"field": "pin.location"
}
}
}
}
}
}
Result:
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 3,
"max_score": 0,
"hits": []
},
"aggregations": {
"positive": {
"doc_count": 2,
"bounds": {
"bounds": {
"top_left": {
"lat": 20.1,
"lon": 9.9
},
"bottom_right": {
"lat": 10.1,
"lon": 99.9
}
}
}
},
"plain": {
"bounds": {
"top_left": {
"lat": 20.1,
"lon": -9.9
},
"bottom_right": {
"lat": -10.1,
"lon": 99.9
}
}
}
}
}