h2o (version 2.8.1.1)

h2o.createFrame: Create an H2O Frame

Description

Create an H2O data frame from scratch, with optional randomization. Supports categoricals, integers, reals and missing values.

Usage

h2o.createFrame(object, key, rows, cols, seed, randomize, value, real_range, 
  categorical_fraction, factors, integer_fraction, integer_range, 
  missing_fraction, response_factors)

Arguments

object

An H2OClient object containing the IP address and port of the server running H2O.

key

The unique hex key assigned to the created frame.

rows

Number of rows

cols

Number of columns

seed

Random number seed

randomize

Whether frame should be randomized

value

Constant value (for randomize=false)

real_range

Range for real variables (-range ... range)

categorical_fraction

Fraction of categorical columns (for randomize=true)

factors

Factor levels for categorical variables

integer_fraction

Fraction of integer columns (for randomize=true)

integer_range

Range for integer variables (-range ... range)

missing_fraction

Fraction of missing values

response_factors

Number of factor levels of the first column (1=real, 2=binomial, N=multinomial)

Value

• Returns an H2O data frame.

Examples

library(h2o)
localH2O = h2o.init(beta = TRUE)
myframe = h2o.createFrame(localH2O, 'myframekey', rows = 1000, cols = 10, 
                          seed = -12301283, randomize = TRUE, value = 0, real_range = 2.0,
                          categorical_fraction = 0.2, factors = 100, 
                          integer_fraction = 0.2, integer_range = 100, missing_fraction = 0.1, 
                          response_factors = 2)
head(myframe)
summary(myframe)
h2o.shutdown(localH2O)