telvis07

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

{
  "facets": {
    "terms": {
      "facet_filter": {
        "fquery": {
          "query": {
            "filtered": {
              "filter": {
                "bool": {
                  "must": [

telvis07

# 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 "
}'

telvis07

curl -XDELETE localhost:9200/test

curl -XPOST localhost:9200/test -d '
{
  "mappings": {
    "type1": {
      "properties": {
        "message": {
          "index": "analyzed",
          "type": "string"

telvis07

curl -XPOST localhost:9200/test -d '
{
  "mappings": {
    "type1": {
      "properties": {
        "message": {
          "index": "analyzed",
          "type": "string"
        },
        "depart": {