def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**SparseFeaturizer.get_default_config(),
"analyzer": "word",
"min_ngram": 1,
"max_ngram": 1,
}
def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**SparseFeaturizer.get_default_config(),
FEATURES: [
["low", "title", "upper"],
["BOS", "EOS", "low", "upper", "title", "digit"],
["low", "title", "upper"],
],
}
def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**SparseFeaturizer.get_default_config(),
# text will be processed with case sensitive as default
"case_sensitive": True,
# use lookup tables to generate features
"use_lookup_tables": True,
# use regexes to generate features
"use_regexes": True,
# use match word boundaries for lookup table
"use_word_boundaries": True,
}
def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**SparseFeaturizer.get_default_config(),
# whether to use a shared vocab
"use_shared_vocab":
False,
# the parameters are taken from
# sklearn's CountVectorizer
# whether to use word or character n-grams
# 'char_wb' creates character n-grams inside word boundaries
# n-grams at the edges of words are padded with space.
"analyzer":
"word", # use 'char' or 'char_wb' for character
# remove accents during the preprocessing step
"strip_accents":
None, # {'ascii', 'unicode', None}
# list of stop words
"stop_words":
None, # string {'english'}, list, or None (default)
# min document frequency of a word to add to vocabulary
# float - the parameter represents a proportion of documents
# integer - absolute counts
"min_df":
1, # float in range [0.0, 1.0] or int
# max document frequency of a word to add to vocabulary
# float - the parameter represents a proportion of documents
# integer - absolute counts
"max_df":
1.0, # float in range [0.0, 1.0] or int
# set range of ngrams to be extracted
"min_ngram":
1, # int
"max_ngram":
1, # int
# limit vocabulary size
"max_features":
None, # int or None
# if convert all characters to lowercase
"lowercase":
True, # bool
# handling Out-Of-Vocabulary (OOV) words
# will be converted to lowercase if lowercase is True
"OOV_token":
None, # string or None
"OOV_words": [], # string or list of strings
# indicates whether the featurizer should use the lemma of a word for
# counting (if available) or not
"use_lemma":
True,
}