fit.FeatureSpec: Fits a feature specification.

Description Usage Arguments Value See Also Examples

View source: R/feature_spec.R

Description

This function will fit the specification. Depending on the steps added to the specification it will compute for example, the levels of categorical features, normalization constants, etc.

Usage

1
2
## S3 method for class 'FeatureSpec'
fit(object, dataset = NULL, ...)

Arguments

object

A feature specification created with feature_spec().

dataset

(Optional) A TensorFlow dataset. If NULL it will use the dataset provided when initilializing the feature_spec.

...

(unused)

Value

a fitted FeatureSpec object.

See Also

Other Feature Spec Functions: dataset_use_spec(), feature_spec(), step_bucketized_column(), step_categorical_column_with_hash_bucket(), step_categorical_column_with_identity(), step_categorical_column_with_vocabulary_file(), step_categorical_column_with_vocabulary_list(), step_crossed_column(), step_embedding_column(), step_indicator_column(), step_numeric_column(), step_remove_column(), step_shared_embeddings_column(), steps

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
## Not run: 
library(tfdatasets)
data(hearts)
hearts <- tensor_slices_dataset(hearts) %>% dataset_batch(32)

# use the formula interface
spec <- feature_spec(hearts, target ~ age) %>%
  step_numeric_column(age)

spec_fit <- fit(spec)
spec_fit

## End(Not run)

tfdatasets documentation built on Nov. 10, 2021, 1:07 a.m.