def __init__(
self,
tokenizer: algorithm(Document(), List(Sentence())),
feature_extractor: algorithm(Sentence(), Flags()),
):
self.tokenizer = tokenizer
self.feature_extractor = feature_extractor
def __init__(
self,
tokenizer: algorithm(Sentence(), List(Word())),
feature_extractor: algorithm(Word(), Flags()),
include_text: Boolean(),
):
self.tokenizer = tokenizer
self.feature_extractor = feature_extractor
self.include_text = include_text
def run(self, input: Sentence()) -> Flags():
tokens = self.tokenizer.run(input)
flags = [self.feature_extractor(w) for w in tokens]
if self.include_text:
return {
f"{w}|{f}": v for w, flag in zip(tokens, flags) for f, v in flag.items()
}
else:
return {f: v for flag in flags for f, v in flag.items()}
def run(self, input: Sentence()) -> Tuple(List(Word()), List(Flags())):
tokenized = self.nlp(input)
tokens = []
flags = []
for token in tokenized:
token_flags = {}
if self.extract_lemma:
token_flags["lemma"] = token.lemma_
if self.extract_pos_tag:
token_flags["pos"] = token.pos_
for kv in token.tag_.split("|"):
kv = kv.split("=")
if len(kv) == 2:
token_flags["tag_" + kv[0]] = kv[1]
else:
token_flags["tag_" + kv[0]] = True
if self.extract_dep:
token_flags["dep"] = token.dep_
if self.extract_entity:
token_flags["ent_type"] = token.ent_type_
token_flags["ent_kb_id"] = token.ent_kb_id_
if self.extract_details:
token_flags["is_alpha"] = token.is_alpha
token_flags["is_ascii"] = token.is_ascii
token_flags["is_digit"] = token.is_digit
token_flags["is_lower"] = token.is_lower
token_flags["is_upper"] = token.is_upper
token_flags["is_title"] = token.is_title
token_flags["is_punct"] = token.is_punct
token_flags["is_left_punct"] = token.is_left_punct
token_flags["is_right_punct"] = token.is_right_punct
token_flags["is_space"] = token.is_space
token_flags["is_bracket"] = token.is_bracket
token_flags["is_quote"] = token.is_quote
token_flags["is_currency"] = token.is_currency
token_flags["like_url"] = token.like_url
token_flags["like_num"] = token.like_num
token_flags["like_email"] = token.like_email
token_flags["is_oov"] = token.is_oov
token_flags["is_stop"] = token.is_stop
if self.extract_sentiment:
token_flags["sentiment"] = token.sentiment
tokens.append(token.text)
flags.append(token_flags)
return tokens, flags
def __init__(
self,
lowercase: Boolean(),
stopwords_remove: Boolean(),
binary: Boolean(),
inner_tokenizer: algorithm(Sentence(), List(Word())),
inner_stemmer: algorithm(Word(), Stem()),
inner_stopwords: algorithm(List(Word()), List(Word())),
):
self.stopwords_remove = stopwords_remove
self.inner_tokenizer = inner_tokenizer
self.inner_stemmer = inner_stemmer
self.inner_stopwords = inner_stopwords
SklearnTransformer.__init__(self)
_CountVectorizer.__init__(self, lowercase=lowercase, binary=binary)
# The next line will print all the algorithms that AutoGOAL found
# in the `contrib` library, i.e., anything that could be potentially used
# to solve an AutoML problem.
for cls in find_classes():
print("Using: %s" % cls.__name__)
# ## Experimentation
# Instantiate the classifier.
# Note that the input and output types here are defined to match the problem statement,
# i.e., text classification.
classifier = AutoML(
search_algorithm=PESearch,
input=List(Sentence()),
output=CategoricalVector(),
search_iterations=args.iterations,
score_metric=f1_score,
search_kwargs=dict(
pop_size=args.popsize,
search_timeout=args.global_timeout,
evaluation_timeout=args.timeout,
memory_limit=args.memory * 1024**3,
),
)
# This custom logger is used for debugging purposes, to be able later to recover
# the best pipelines and all the errors encountered in the experimentation process.
def run(self, input: Sentence()) -> List(Word()):
pass
import logging
logging.basicConfig(level=logging.DEBUG)
@nice_repr
class A:
def run(self, input: Sentence()) -> List(Word()):
pass
@nice_repr
class B:
def run(self, input: List(Word())) -> List(Vector()):
pass
@nice_repr
class C:
def run(self, input: List(Vector())) -> Matrix():
pass
builder = build_pipelines(input=Tuple(Sentence(), Vector()),
output=Matrix(),
registry=[A, B, C])
pipeline = builder.sample()
print(pipeline)
print(pipeline.run([[[True], [False, True]]]))
def run(
self, input: Tuple(Sentence(), List(Tuple(Entity(), Entity(), Category())))
) -> Tuple(List(Vector()), CategoricalVector()):
pass
def __init__(self,
tokenizer: algorithm(Sentence(), List(Word())),
token_feature_extractor: algorithm(Word(), Flags()),
# token_sentence_encoder: algorithm(Word(), )
):
pass
def run(
self, input: Tuple(Sentence(), List(Entity()))
) -> Tuple(List(Word()), List(Postag())):
pass
def __init__(self, tokenizer: algorithm(Sentence(), List(Word()))):
self.tokenizer = tokenizer
def run(self, input: List(Sentence())) -> MatrixContinuousSparse():
return SklearnTransformer.run(self, input)
def run(self, input:List(Sentence())) -> Document():
pass
def run(self, input:List(Word())) -> Sentence():
pass