from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LinearRegression

with open('train/train.tsv', 'r', encoding='utf8') as f:
    train_data = f.readlines()

with open('train/meta.tsv', 'r', encoding='utf8') as f:
    expected_years = f.readlines()

for i, expected in enumerate(expected_years):
    expected_years[i] = expected.split('\t')[5]
#
vectorizer = TfidfVectorizer(token_pattern=r"\b[a-zA-Z]+\b|[0-9]{4}[\.]?[a-z]{0,3}[\.]?")
train = vectorizer.fit_transform(train_data)
model = LinearRegression()
model.fit(train, expected_years)

with open('dev-0/in.tsv', 'r', encoding='utf8') as f:
    dev_0 = f.readlines()

# prediction on test1 data
dev_0 = vectorizer.transform(dev_0)
predicted_dev_0 = model.predict(dev_0)

with open('dev-0/out.tsv', 'wt') as f:
    for p in predicted_dev_0:
        f.write(str(p) + '\n')

with open('dev-1/in.tsv', 'r', encoding='utf8') as f:
    dev_1 = f.readlines()

# prediction on test2 data
dev_1 = vectorizer.transform(dev_1)
predicted_dev_1 = model.predict(dev_1)

with open('dev-1/out.tsv', 'wt') as f:
    for p in predicted_dev_1:
        f.write(str(p) + '\n')

with open('test-A/in.tsv', 'r', encoding='utf8') as f:
    test_A = f.readlines()

test_A = vectorizer.transform(test_A)
predicted_test_A = model.predict(test_A)

with open('test-A/out.tsv', 'wt') as f:
    for p in predicted_test_A:
        f.write(str(p) + '\n')

print("finished")