telvis07
/ ngram_prune.R
Last active Jul 1, 2016
NLP - prune ngrams by finding the minimum number of ngrams that cover X percent of the word instances
View ngram_prune.R
| prune_ngram_df_by_cover_percentage <- function(df, percentage) { | |
| # assumes df contains columns (word, freq) | |
| # assumes df is sorted by freq in descending order | |
| # prune ngrams by finding the minimum number of ngrams that cover X percent of the word instances | |
| sums <- cumsum(df$freq) | |
| cover <- which(sums >= sum(df$freq) * percentage)[1] | |
| print(sprintf("%s of %s (%s%%) cover %s%% of word instances", | |
| cover, | |
| nrow(df), | |
| cover/nrow(df)*100, |
telvis07
/ kibana-filtered-query.json
Last active Aug 29, 2015
View kibana-filtered-query.json
| { | |
| "facets": { | |
| "terms": { | |
| "facet_filter": { | |
| "fquery": { | |
| "query": { | |
| "filtered": { | |
| "filter": { | |
| "bool": { | |
| "must": [ |
telvis07
/ terms-filter-lookup.sh
Created Apr 26, 2013
Working example for https://github.com/elasticsearch/elasticsearch/issues/2674
View terms-filter-lookup.sh
| # index the information for user with id 2, specifically, its friends | |
| curl -XPUT localhost:9200/users/user/2 -d '{ | |
| "friends" : ["1", "3"] | |
| }' | |
| # index a tweet, from user with id 2 | |
| curl -XPUT localhost:9200/tweets/tweet/1 -d '{ | |
| "user" : "1", | |
| "tweet" : "hi i am user 1 " | |
| }' |
View multi_field_nested_test.sh
| curl -XDELETE localhost:9200/test | |
| curl -XPOST localhost:9200/test -d ' | |
| { | |
| "mappings": { | |
| "type1": { | |
| "properties": { | |
| "message": { | |
| "index": "analyzed", | |
| "type": "string" |
telvis07
/ elasticsearch_multi_field_geo_point.sh
Created Dec 6, 2012
multi-field with geo_point in a nested document
View elasticsearch_multi_field_geo_point.sh
| curl -XPOST localhost:9200/test -d ' | |
| { | |
| "mappings": { | |
| "type1": { | |
| "properties": { | |
| "message": { | |
| "index": "analyzed", | |
| "type": "string" | |
| }, | |
| "depart": { |