Question on treating "NA" values in H2O

h2o_query.R

# Question on treating "NA" values.
# RS25072017

# PROBLEM STATEMENT: Remove the "?" values in the data set, and turn them into "n". ---------------------

require(h2o)

# Modify below, as needed.
h2o.init(startH2O = FALSE)


# 1. The R way. ---------------------

# Using the 1984 Congressional Voting Records from UCI.
url = "http://archive.ics.uci.edu/ml/machine-learning-databases/voting-records/house-votes-84.data"

# Load the data.
party.data = read.table(url, sep = ",")
colnames(party.data ) = c("party", paste("vote", 1:16, sep=""))

# I want to this to treat the "NA" values:
party.data[party.data  == "?"] = "n"

# No more "?" in the df:
head(party.data)

# 2. The H2O way. ---------------------
voting.data = h2o.importFile(path = url, 
                             col.names = c("party", paste0("vote", 1:16)), 
                             col.types = rep("string", 17))


# This doesn't work:
voting.data[voting.data == "?", ] = "n"

# This still has NA's!
head(voting.data)

# Why? Look at the difference in semantics:
## Pure R
party.data == "?"

## H20
voting.data == "?"
## It's not a boolean.