Compute element-wise string distances between two H2OFrames. Both frames need to have the same shape (N x M) and only contain string/factor columns. Return a matrix (H2OFrame) of shape N x M.
h2o.stringdist( x, y, method = c("lv", "lcs", "qgram", "jaccard", "jw", "soundex"), compare_empty = TRUE )
x | An H2OFrame |
---|---|
y | A comparison H2OFrame |
method | A string identifier indicating what string distance measure to use. Must be one of: "lv" - Levenshtein distance "lcs" - Longest common substring distance "qgram" - q-gram distance "jaccard" - Jaccard distance between q-gram profiles "jw" - Jaro, or Jaro-Winker distance "soundex" - Distance based on soundex encoding |
compare_empty | if set to FALSE, empty strings will be handled as NaNs |
if (FALSE) { h2o.init() x <- as.h2o(c("Martha", "Dwayne", "Dixon")) y <- as.character(as.h2o(c("Marhta", "Duane", "Dicksonx"))) h2o.stringdist(x, y, method = "jw") }