Make Predictions from an "FFMRanker" Object

Make Predictions from an "FFMRanker" Object

# S3 method for FFMRanker
predict(
  model,
  data,
  key,
  features = NULL,
  handle.missing = NULL,
  thread.ratio = NULL
)

Arguments

model	R6Class object A "FFMRanker" object for prediction.
data	DataFrame DataFrame containting data of user-item interaction and global side features for prediction.
key	character Name of the ID column.
features	list of characters, optional Name of feature columns in data. If not provided, it defaults all non-ID columns of data.
handle.missing	c("remove", "replace"), optional Specifies how to handle missing features of data: "remove" remove missing rows "replace" replace missing rows with 0
thread.ratio	double, optional Controls the proportion of available threads that can be used by this function. The value range is from 0 to 1, where 0 indicates a single thread, and 1 indicates all available threads. Values between 0 and 1 will use up to that percentage of available threads.Values outside this range are ignored. Defaults to 0.

Format

S3 methods

Value

DataFrame
Prediction made by the model, structured as follows:

• ID: id

• SCORE: Predict value

• CONFIDENCE: the confidence of a category

Examples

> data$Collect()
  ID USER  MOVIE TIMESTAMP
1  1    A Movie0         3
2  2    A Movie4         1
3  3    B Movie3         2
4  4    B   <NA>         5
5  5    C Movie2         2
6  6    F Movie4         3
7  7    D Movie2         2
8  8    D Movie4         1
9  9    E Movie7         4

Call the function:

> ranking.result <- predict.FFMRanker(model = FFMrank,
                                      data = data.pred.df.fit,
                                      thread.ratio = 1)

Output:

> ranking.result$Collect()
  ID    SCORE CONFIDENCE
1  1     high  0.2942058
2  2   medium  0.2098934
3  3  too low  0.3166094
4  4     high  0.2196706
5  5 too high  0.2225450
6  6     high  0.3856211
7  7  too low  0.4076951
8  8  too low  0.2952001
9  9     high  0.2826328

See also

hanaml.FFMRanker