More lines.

This commit is contained in:
Jan Nowak 2022-04-04 18:43:08 +02:00
parent 827021f1a3
commit 0f6815f63d
4 changed files with 28458 additions and 6 deletions

10519
dev-0/out.tsv Normal file

File diff suppressed because it is too large Load Diff

10519
dev-0/out_1000000.tsv Normal file

File diff suppressed because it is too large Load Diff

12
run.py
View File

@ -30,7 +30,7 @@ class WordPred:
for w1, w2, w3 in trigrams(tokens, pad_right=True, pad_left=True): for w1, w2, w3 in trigrams(tokens, pad_right=True, pad_left=True):
if w1 and w2 and w3: if w1 and w2 and w3:
self.model[(w2, w3)][w1] += 1 self.model[(w2, w3)][w1] += 1
if index == 1000000: if index == 1300000:
break break
for word_pair in self.model: for word_pair in self.model:
@ -46,7 +46,7 @@ class WordPred:
if len(tokens) < 4: if len(tokens) < 4:
prediction = 'the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1' prediction = 'the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1'
else: else:
prediction = word_gap_prediction.predict_probs(tokens[0], tokens[1]) prediction = wp.predict_probs(tokens[0], tokens[1])
outputf.write(prediction + '\n') outputf.write(prediction + '\n')
def predict_probs(self, word1, word2): def predict_probs(self, word1, word2):
@ -70,7 +70,7 @@ class WordPred:
return str_prediction return str_prediction
word_gap_prediction = WordPred() wp = WordPred()
word_gap_prediction.read_train_data('train/in.tsv.xz') wp.read_train_data('train/in.tsv.xz')
word_gap_prediction.generate_outputs('dev-0/in.tsv.xz', 'dev-0/out.tsv') wp.generate_outputs('dev-0/in.tsv.xz', 'dev-0/out.tsv')
# word_gap_prediction.generate_outputs('test-A/in.tsv.xz', 'test-A/out.tsv') wp.generate_outputs('test-A/in.tsv.xz', 'test-A/out.tsv')

7414
test-A/out.tsv Normal file

File diff suppressed because it is too large Load Diff