def test_lemmatize():
"""Test lemmatization method."""
assert utils.lemmatize({"corriendo": "correr"}, "corriendo") == "correr"
def test_lemmatize():
"""Test lemmatization method."""
assert utils.lemmatize({'corriendo': 'correr'}, 'corriendo') \
== 'correr'
def __init__(self, doc, lexico_semantic_norm_dict, lemmatizer=None):
"""Initialize lexico semantic norm object.
Calculate average over number of tokens given a text.
:param doc: Text to be processed
:type doc: Spacy Doc
:param lexico_semantic_norm_dict: Lexico semantic norms for words
:type lexico_semantic_norm_dict: dict
:param lemmatizer: Lemmatizer, defaults to None
:type lemmatizer: dict, optional
"""
valence = 0
arousal = 0
concreteness = 0
imageability = 0
context_availability = 0
familiarity = 0
count = 0.0
for token in doc:
word = token.text.lower()
word_lemma = word
if lemmatizer:
word_lemma = lemmatize(lemmatizer, word)
if word in lexico_semantic_norm_dict:
valence += lexico_semantic_norm_dict[word].get("valence")
arousal += lexico_semantic_norm_dict[word].get("arousal")
concreteness += lexico_semantic_norm_dict[word].get(
"concreteness")
imageability += lexico_semantic_norm_dict[word].get(
"imageability")
context_availability += lexico_semantic_norm_dict[word].get(
"context_availability")
familiarity += lexico_semantic_norm_dict[word].get(
"familiarity")
count += 1
elif word_lemma in lexico_semantic_norm_dict:
word = word_lemma
valence += lexico_semantic_norm_dict[word].get("valence")
arousal += lexico_semantic_norm_dict[word].get("arousal")
concreteness += lexico_semantic_norm_dict[word].get(
"concreteness")
imageability += lexico_semantic_norm_dict[word].get(
"imageability")
context_availability += lexico_semantic_norm_dict[word].get(
"context_availability")
familiarity += lexico_semantic_norm_dict[word].get(
"familiarity")
count += 1.0
self.__valence = valence
self.__arousal = arousal
self.__concreteness = concreteness
self.__imageability = imageability
self.__context_avilability = context_availability
self.__familiarity = familiarity
if count > 0:
self.__valence /= count
self.__arousal /= count
self.__concreteness /= count
self.__imageability /= count
self.__context_avilability /= count
self.__familiarity /= count
def __init__(self, doc: Doc, lemmatizer: Optional[Dict[str, str]] = None):
"""Initialize emotions class.
Average over number of tokens.
:param doc: Texto a ser procesado
:type doc: Spacy Doc
:param lemmatizer: Lematizador a utilizar, defaults to None
:type lemmatizer: Python dict, optional
"""
alegria = 0
enojo = 0
miedo = 0
repulsion = 0
sorpresa = 0
tristeza = 0
count = 0.0
for token in doc:
word = token.text.lower()
word_lemma = word
if lemmatizer:
word_lemma = lemmatize(lemmatizer, word)
if word in SPANISH_EMOTION_LEXICON:
pfa, emotion = SPANISH_EMOTION_LEXICON[word]
if emotion == "Alegría":
alegria += pfa
elif emotion == "Enojo":
enojo += pfa
elif emotion == "Miedo":
miedo += pfa
elif emotion == "Repulsión":
repulsion += pfa
elif emotion == "Sorpresa":
sorpresa += pfa
else:
tristeza += pfa
count += 1
elif word_lemma in SPANISH_EMOTION_LEXICON:
word = word_lemma
pfa, emotion = SPANISH_EMOTION_LEXICON[word]
if emotion == "Alegría":
alegria += pfa
elif emotion == "Enojo":
enojo += pfa
elif emotion == "Miedo":
miedo += pfa
elif emotion == "Repulsión":
repulsion += pfa
elif emotion == "Sorpresa":
sorpresa += pfa
else:
tristeza += pfa
count += 1.0
self.__alegria = alegria
self.__enojo = enojo
self.__miedo = miedo
self.__repulsion = repulsion
self.__sorpresa = sorpresa
self.__tristeza = tristeza
if count > 0:
self.__alegria /= count
self.__enojo /= count
self.__miedo /= count
self.__repulsion /= count
self.__sorpresa /= count
self.__tristeza /= count