ver 3 full train set

This commit is contained in:
Łukasz Jędyk 2021-05-12 22:46:20 +02:00
parent 9dfe8fe3b5
commit 78ae1c52a8
3 changed files with 34220 additions and 34225 deletions

File diff suppressed because it is too large Load Diff

View File

@ -10,17 +10,12 @@ train_set = pd.read_table('train/train.tsv.xz', error_bad_lines=False, header=No
dev_set = pd.read_table('dev-0/in.tsv', error_bad_lines=False, header=None, names=col_names[4:], quoting=csv.QUOTE_NONE,)
test_set = pd.read_table('test-A/in.tsv', error_bad_lines=False, header=None, names=col_names[4:], quoting=csv.QUOTE_NONE,)
train_set = train_set.head(10000)
X_train = train_set['content']
y_train = (train_set['start_date'] + train_set['end_date']) / 2
X_dev = dev_set['content']
X_test = test_set['content']
print(dev_set)
print(test_set)
print('Trenowanie modelu...')
model = make_pipeline(TfidfVectorizer(), LinearRegression())
model.fit(X_train, y_train)

File diff suppressed because it is too large Load Diff