num_words now proper dict
This commit is contained in:
parent
865351b3f6
commit
ca0d6f0f55
7
wani.py
7
wani.py
|
@ -869,7 +869,7 @@ class WordMsdRenderer:
|
|||
self.all_words = []
|
||||
self.rendered_words = {}
|
||||
self.frequent_words = {}
|
||||
self.num_words = defaultdict(int)
|
||||
self.num_words = {}
|
||||
self.lemma_msd = {}
|
||||
self.lemma_features = lemma_features
|
||||
self.memoized_msd_merges = {}
|
||||
|
@ -881,6 +881,7 @@ class WordMsdRenderer:
|
|||
return len(self.all_words)
|
||||
|
||||
def generate_renders(self):
|
||||
num_words = defaultdict(int)
|
||||
data = defaultdict(lambda: defaultdict(list))
|
||||
for w in self.all_words:
|
||||
data[w.lemma][w.msd].append(w.text)
|
||||
|
@ -892,7 +893,7 @@ class WordMsdRenderer:
|
|||
|
||||
for msd, texts in ld.items():
|
||||
# TODO: this should be out of generate_renders...
|
||||
self.num_words[(lemma, msd[0])] += len(texts)
|
||||
num_words[(lemma, msd[0])] += len(texts)
|
||||
|
||||
rep = max(set(texts), key=texts.count)
|
||||
self.rendered_words[lemma][msd] = (rep, len(texts))
|
||||
|
@ -915,6 +916,8 @@ class WordMsdRenderer:
|
|||
self.lemma_msd[lemma] = "".join(
|
||||
l1 if l1 != "-" else l2 for l1, l2 in zip(lf[cmsd[0]], cmsd)
|
||||
)
|
||||
|
||||
self.num_words = dict(num_words)
|
||||
|
||||
def merge_msd(self, common_msd, new_msd):
|
||||
key = (common_msd, new_msd)
|
||||
|
|
Loading…
Reference in New Issue
Block a user