Getters for number of lemmas and number of all words
This commit is contained in:
parent
2167e4b6fe
commit
2773a8b9e9
6
wani.py
6
wani.py
|
@ -825,6 +825,7 @@ class WordMsdRenderer:
|
|||
self.all_words = []
|
||||
self.rendered_words = {}
|
||||
self.frequent_words = {}
|
||||
self.num_words = defaultdict(int)
|
||||
self.lemma_msd = {}
|
||||
self.lemma_features = lemma_features
|
||||
self.memoized_msd_merges = {}
|
||||
|
@ -832,6 +833,9 @@ class WordMsdRenderer:
|
|||
def add_words(self, words):
|
||||
self.all_words.extend(words)
|
||||
|
||||
def num_all_words(self):
|
||||
return len(self.all_words)
|
||||
|
||||
def generate_renders(self):
|
||||
data = defaultdict(lambda: defaultdict(list))
|
||||
for w in self.all_words:
|
||||
|
@ -843,6 +847,8 @@ class WordMsdRenderer:
|
|||
common_msd = "*" * 10
|
||||
|
||||
for msd, texts in ld.items():
|
||||
self.num_words[(lemma, msd[0])] += len(texts)
|
||||
|
||||
rep = max(set(texts), key=texts.count)
|
||||
self.rendered_words[lemma][msd] = (rep, len(texts))
|
||||
|
||||
|
|
Loading…
Reference in New Issue
Block a user