spark.bisectingKmeans {SparkR}

R Documentation

Bisecting K-Means Clustering Model

Description

Fits a bisecting k-means clustering model against a SparkDataFrame. Users can call summary to print a summary of the fitted model, predict to make predictions on new data, and write.ml/read.ml to save/load fitted models.

Get fitted result from a bisecting k-means model. Note: A saved-loaded model does not support this method.

Usage

spark.bisectingKmeans(data, formula, ...)

## S4 method for signature 'SparkDataFrame,formula'
spark.bisectingKmeans(
  data,
  formula,
  k = 4,
  maxIter = 20,
  seed = NULL,
  minDivisibleClusterSize = 1
)

## S4 method for signature 'BisectingKMeansModel'
summary(object)

## S4 method for signature 'BisectingKMeansModel'
predict(object, newData)

## S4 method for signature 'BisectingKMeansModel'
fitted(object, method = c("centers", "classes"))

## S4 method for signature 'BisectingKMeansModel,character'
write.ml(object, path, overwrite = FALSE)

Arguments

data	a SparkDataFrame for training.
formula	a symbolic description of the model to be fitted. Currently only a few formula operators are supported, including '~', '.', ':', '+', '-', '*', and '^'. Note that the response variable of formula is empty in spark.bisectingKmeans.
...	additional argument(s) passed to the method.
k	the desired number of leaf clusters. Must be > 1. The actual number could be smaller if there are no divisible leaf clusters.
maxIter	maximum iteration number.
seed	the random seed.
minDivisibleClusterSize	The minimum number of points (if greater than or equal to 1.0) or the minimum proportion of points (if less than 1.0) of a divisible cluster. Note that it is an expert parameter. The default value should be good enough for most cases.
object	a fitted bisecting k-means model.
newData	a SparkDataFrame for testing.
method	type of fitted results, "centers" for cluster centers or "classes" for assigned classes.
path	the directory where the model is saved.
overwrite	overwrites or not if the output path already exists. Default is FALSE which means throw exception if the output path exists.

Value

spark.bisectingKmeans returns a fitted bisecting k-means model.

summary returns summary information of the fitted model, which is a list. The list includes the model's k (number of cluster centers), coefficients (model cluster centers), size (number of data points in each cluster), cluster (cluster centers of the transformed data; cluster is NULL if is.loaded is TRUE), and is.loaded (whether the model is loaded from a saved file).

predict returns the predicted values based on a bisecting k-means model.

fitted returns a SparkDataFrame containing fitted values.

Note

spark.bisectingKmeans since 2.2.0

summary(BisectingKMeansModel) since 2.2.0

predict(BisectingKMeansModel) since 2.2.0

fitted since 2.2.0

write.ml(BisectingKMeansModel, character) since 2.2.0

See Also

predict, read.ml, write.ml

Examples

## Not run: 
##D sparkR.session()
##D t <- as.data.frame(Titanic)
##D df <- createDataFrame(t)
##D model <- spark.bisectingKmeans(df, Class ~ Survived, k = 4)
##D summary(model)
##D 
##D # get fitted result from a bisecting k-means model
##D fitted.model <- fitted(model, "centers")
##D showDF(fitted.model)
##D 
##D # fitted values on training data
##D fitted <- predict(model, df)
##D head(select(fitted, "Class", "prediction"))
##D 
##D # save fitted model to input path
##D path <- "path/to/model"
##D write.ml(model, path)
##D 
##D # can also read back the saved model and print
##D savedModel <- read.ml(path)
##D summary(savedModel)
## End(Not run)

---