def get_encoders(self):
return (
Unique('a', twin=True),
Unique('b', twin=True),
Token('c', twin=True, sequence_length=3),
Unique('user_id'),
Pass('price')
)
def get_encoders(self):
return (
# An encoder to tokenize product names into max 15 tokens that
# occur in the corpus at least 10 times in the corpus. We also
# want the estimator to spend 5x as many resources on name vs
# department since there are so many more words in english
# than their are grocery store departments.
Token('product_name',
sequence_length=15,
minimum_occurrences=10,
embed_scale=5),
# An encoder to translate department names into unique
# identifiers that occur at least 50 times
Unique('department', minimum_occurrences=50))
def get_encoders(self):
return (Unique('a'), Unique('b'), Token('words'))
def get_encoders(self):
return (OneHot('a', minimum_occurrences=1001,
compressed=True), OneHot('b'), Token('words'))
