aloth

select
    guid
    , regexp_split_to_table(lower(post_content), '\s+') as word
    , count(1) as word_count
from
    alexblog_posts
group by
    guid, word

aloth

CASE LEFT([Word], 1)
    WHEN "#" THEN "Hash Tag"
    WHEN "@" THEN "User Reference"
    ELSE "Regular Content"
END

aloth

SCRIPT_STR('
  library(sentiment)
  get_emotion(.arg1, algorithm = "bayes")
'
, ATTR([Tweet Text]))

aloth

SCRIPT_STR('
  library(sentiment)
  get_polarity(.arg1, algorithm = "bayes")
'
, ATTR([Tweet Text]))

aloth

install.packages("devtools")
library(devtools)
install_github("aloth/sentiment/sentiment")

aloth

install.packages("Rcpp")
install.packages("http://alexloth.com/utils/sentiment/current/sentiment.zip",repos=NULL)

aloth

SCRIPT_REAL('
  import numpy as np
  return np.corrcoef(_arg1,_arg2)[0,1]
',
SUM([Sales]), SUM([Profit]))

aloth

SCRIPT_INT('
  kmeans(data.frame(.arg1,.arg2,.arg3),' + STR([Cluster Amount]) + ')$cluster;
',
SUM([Sales]), SUM([Profit]), SUM([Quantity]))

aloth

SCRIPT_STR('
  newurl <- .arg1
  url <- ""
  while(url != newurl){
    data <- system(toString(paste0("curl -I ", newurl)), intern=T)
    if(sum(grepl("location: ", tolower(data))) == 0){
      url <- newurl
    }else{
      data <- subset(data, tolower(substring(data, 1, 9))=="location:")
      stringurl <- substring(data[1], 11, nchar(data[1])-1)

aloth

REGEXP_EXTRACT(
  [Post Message],
  '((?:http|https)://(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-]))'
)