Retrieve the results to view the best predictor subsets.
h2o.result(model)Returns an H2OFrame object
if (FALSE) { # \dontrun{
library(h2o)
h2o.init()
# Import the prostate dataset:
prostate <- h2o.importFile(
"http://s3.amazonaws.com/h2o-public-test-data/smalldata/logreg/prostate.csv"
)
# Set the predictors & response:
predictors <- c("AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS")
response <- "GLEASON"
# Build & train the model:
allsubsetsModel <- h2o.modelSelection(x = predictors,
y = response,
training_frame = prostate,
seed = 12345,
max_predictor_number = 7,
mode = "allsubsets")
# Retrieve the results (H2OFrame containing best model_ids, best_r2_value, & predictor subsets):
results <- h2o.result(allsubsetsModel)
print(results)
# Retrieve the list of coefficients:
coeff <- h2o.coef(allsubsetsModel)
print(coeff)
# Retrieve the list of coefficients for a subset size of 3:
coeff3 <- h2o.coef(allsubsetsModel, 3)
print(coeff3)
# Retrieve the list of standardized coefficients:
coeff_norm <- h2o.coef_norm(allsubsetsModel)
print(coeff_norm)
# Retrieve the list of standardized coefficients for a subset size of 3:
coeff_norm3 <- h2o.coef_norm(allsubsetsModel)
print(coeff_norm3)
# Check the variables that were added during this process:
h2o.get_predictors_added_per_step(allsubsetsModel)
# To find out which variables get removed, build a new model with ``mode = "backward``
# using the above training information:
bwModel <- h2o.modelSelection(x = predictors,
y = response,
training_frame = prostate,
seed = 12345,
max_predictor_number = 7,
mode = "backward")
h2o.get_predictors_removed_per_step(bwModel)
# To build the fastest model with ModelSelection, use ``mode = "maxrsweep"``:
sweepModel <- h2o.modelSelection(x = predictors,
y = response,
training_frame = prostate,
mode = "maxrsweep",
build_glm_model = FALSE,
max_predictor_number = 3,
seed = 12345)
# Retrieve the results to view the best predictor subsets:
h2o.result(sweepModel)
} # }