s440054/challenging-america-word-gap-prediction
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

test 2

Browse Source
This commit is contained in:
s440054 2022-04-05 00:12:13 +02:00
parent a0a24dd6b5
commit a459bfbb6f
3 changed files with 16029 additions and 16029 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18842
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

6
run.py
View File

@ -11,10 +11,10 @@ def main():
train_words = get_csv("train/expected.tsv") train_words = get_csv("train/expected.tsv")
train_data = data[[7, 6]] train_data = data[[6, 7]]
train_data = pd.concat([train_data, train_words], axis=1) train_data = pd.concat([train_data, train_words], axis=1)
train_data[760] = train_data[7] + train_data[0] + train_data[6] train_data[607] = train_data[6] + train_data[0] + train_data[7]
model = defaultdict(lambda: defaultdict(lambda: 0)) model = defaultdict(lambda: defaultdict(lambda: 0))
@ -26,7 +26,7 @@ def main():
def train_model(data, model): def train_model(data, model):
for _, row in data.iterrows(): for _, row in data.iterrows():
words = nltk.word_tokenize(clean_text(row[760])) words = nltk.word_tokenize(clean_text(row[607]))
for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True): for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True):
if w1 and w2: if w1 and w2:
model[w2][w1] += 1 model[w2][w1] += 1

13210
test-A/out.tsv
View File

File diff suppressed because it is too large Load Diff