h2o domino

install.R

# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Install h2o
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

# The following two commands remove any previously installed H2O packages for R.
if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }

# Next, we download packages that H2O depends on.
if (! ("methods" %in% rownames(installed.packages()))) { install.packages("methods") }
if (! ("statmod" %in% rownames(installed.packages()))) { install.packages("statmod") }
if (! ("stats" %in% rownames(installed.packages()))) { install.packages("stats") }
if (! ("graphics" %in% rownames(installed.packages()))) { install.packages("graphics") }
if (! ("RCurl" %in% rownames(installed.packages()))) { install.packages("RCurl") }
if (! ("rjson" %in% rownames(installed.packages()))) { install.packages("rjson") }
if (! ("tools" %in% rownames(installed.packages()))) { install.packages("tools") }
if (! ("utils" %in% rownames(installed.packages()))) { install.packages("utils") }

# Now we download, install and initialize the H2O package for R.
install.packages("h2o", type="source", repos=(c("http://h2o-release.s3.amazonaws.com/h2o/rel-simons/4/R")))

model.R

source("install.R")

library(h2o)

h2oCluster <- h2o.init()

fit <- h2o.loadModel("/home/public/DLModel1", h2oCluster)

model.predict <- function(pclass, sex, age, sibsp, parch, fare) {
  data <- as.h2o(data.frame(Pclass=as.factor(pclass), 
                            Sex=sex, 
                            Age=age, 
                            SibSp = sibsp, 
                            Parch=parch, 
                            Fare=fare))
  result <- as.data.frame(h2o.predict(fit, data))
  result$p1 >= 0.5
}

#model.predict(1,"female", 38, 0, 0, 71.2833) # returns true
#model.predict(1,"male", 38, 0, 0, 71.2833) # returns false

train.R

source("install.R")

library(h2o)

# initialize connection to h2o cluster
h2oCluster <- h2o.init()

# upload data to cluster
df <- h2o.uploadFile("data/train.csv")
df$Pclass <- as.factor(df$Pclass)
df <- h2o.impute(df, "Age", method = "mean")

# split data into train/test
df.split <- h2o.splitFrame(data = df , ratios = 0.75)
df.train <- df.split[[1]]
df.test <- df.split[[2]]

# fit model
fit.glm <- h2o.glm(y = "Survived",
                   x = c("Pclass","Sex","Age","SibSp","Parch","Fare"),
                   training_frame = df.train, 
                   family = "binomial", link = "logit",
                   solver = "AUTO", lambda_search = FALSE)

pred <- h2o.predict(fit.glm,df.test)
perf <- h2o.performance(fit.glm, df.test, measure="precision")

plot(perf,type="roc", col="blue")

h2o.saveModel(fit.glm, dir=getwd(), name="DLModel1", force=T)