s470611/challenging-america-word-gap-prediction
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

smoothing

Browse Source
This commit is contained in:
Bartosz Karwacki 2022-04-10 18:43:05 +02:00
parent d71b99be29
commit 2b253e5c4f
3 changed files with 1297 additions and 1298 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1462
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

9
run.py
View File

@ -41,15 +41,14 @@ class Model:
for w1 in self.model: for w1 in self.model:
total_count = float(sum(self.model[w1].values())) total_count = float(sum(self.model[w1].values()))
denominator = total_count + self.alpha * len(self.vocab)
for w2 in self.model[w1]: for w2 in self.model[w1]:
self.model[w1][w2] /= total_count nominator = self.model[w1][w2] + self.alpha
self.model[w1][w2] = (self.model[w1][w2] + self.alpha) / ( self.model[w1][w2] = nominator / denominator
total_count + self.alpha * len(self.vocab)
)
def _predict(self, word): def _predict(self, word):
predictions = dict(self.model[word]) predictions = dict(self.model[word])
most_common = dict(Counter(predictions).most_common(5)) most_common = dict(Counter(predictions).most_common(6))
total_prob = 0.0 total_prob = 0.0
str_prediction = "" str_prediction = ""

1124
test-A/out.tsv
View File

File diff suppressed because it is too large Load Diff