add type hints

src/TRUNAJOD/lexico_semantic_norms.py

@@ -13,6 +13,7 @@
 We provide two downloadable models of these variables, which come from
 :cite:`duchon2013espal` and :cite:`guasch2016spanish`.
 """
+from spacy.tokens import Doc
 from TRUNAJOD.lexicosemantic_norms_espal import LEXICOSEMANTIC_ESPAL
 from TRUNAJOD.lexicosemantic_norms_espal import LSNorm
 from TRUNAJOD.utils import lemmatize
@@ -28,7 +29,12 @@ class LexicoSemanticNorm(object):
     :cite:`guasch2016spanish`.
     """
 
-    def __init__(self, doc, lexico_semantic_norm_dict, lemmatizer=None):
+    def __init__(
+        self,
+        doc: Doc,
+        lexico_semantic_norm_dict: dict,
+        lemmatizer: dict = None,
+    ):
         """Initialize lexico semantic norm object.
 
         Calculate average over number of tokens given a text.
@@ -102,47 +108,47 @@ def __init__(self, doc, lexico_semantic_norm_dict, lemmatizer=None):
             self.__context_avilability /= count
             self.__familiarity /= count
 
-    def get_arousal(self):
+    def get_arousal(self) -> float:
         """Get arousal.
 
         :return: Average arousal.
         :rtype: float
         """
         return self.__arousal
 
-    def get_concreteness(self):
+    def get_concreteness(self) -> float:
         """Get concreteness.
 
         :return: Average concreteness.
         :rtype: float
         """
         return self.__concreteness
 
-    def get_context_availability(self):
+    def get_context_availability(self) -> float:
         """Get context_availability.
 
         :return: Average context_availability.
         :rtype: float
         """
         return self.__context_avilability
 
-    def get_familiarity(self):
+    def get_familiarity(self) -> float:
         """Get familiarity.
 
         :return: Average familiarity.
         :rtype: float
         """
         return self.__familiarity
 
-    def get_imageability(self):
+    def get_imageability(self) -> float:
         """Get imageability.
 
         :return: Average imageability.
         :rtype: float
         """
         return self.__imageability
 
-    def get_valence(self):
+    def get_valence(self) -> float:
         """Get valence.
 
         :return: Average valence.
@@ -151,7 +157,7 @@ def get_valence(self):
         return self.__valence
 
 
-def get_conc_imag_familiarity(doc):
+def get_conc_imag_familiarity(doc: Doc) -> [float, float, float]:
     """Get lexico-semantic variables.
 
     Computes three lexico-semantic variables: Concreteness, Imageability and

src/TRUNAJOD/semantic_measures.py

@@ -6,9 +6,10 @@
 semantic measurements require word vectors (word embeddings) obtained from
 CORPUS semantics.
 """
+from spacy.tokens import Doc
 
 
-def avg_w2v_semantic_similarity(docs, N):
+def avg_w2v_semantic_similarity(docs: Doc, N: int) -> float:
     """Compute average semantic similarity between adjacent sentences.
 
     This is using word2vec :cite:`mikolov2013word2vec` model based on SPACY
@@ -43,7 +44,7 @@ def avg_w2v_semantic_similarity(docs, N):
     return avg_sim / float(N - 1)
 
 
-def get_synsets(lemma, synset_dict):
+def get_synsets(lemma: str, synset_dict: dict) -> str:
     """Return synonym set given a word lemma.
 
     The function requires that the synset_dict is passed into it. In our case
@@ -61,7 +62,7 @@ def get_synsets(lemma, synset_dict):
     return synset_dict.get(lemma, {lemma})
 
 
-def overlap(lemma_list_group, synset_dict):
+def overlap(lemma_list_group: list, synset_dict: dict) -> float:
     """Compute average overlap in a text.
 
     Computes semantic synset overlap (synonyms), based on a lemma list group