2021-05-12 19:58:28 +02:00
|
|
|
import pandas as pd
|
2021-05-12 20:18:46 +02:00
|
|
|
import numpy as np
|
2021-05-12 19:58:28 +02:00
|
|
|
import gzip
|
|
|
|
|
|
|
|
|
|
dev = pd.read_table('dev-0/in.tsv', error_bad_lines=False, header=None)
|
|
|
|
|
test = pd.read_table('test-A/in.tsv', error_bad_lines=False, header=None)
|
|
|
|
|
|
2021-05-12 20:18:46 +02:00
|
|
|
X_train = []
|
|
|
|
|
y_train = []
|
2021-05-12 19:58:28 +02:00
|
|
|
|
|
|
|
|
with gzip.open('train/train.tsv.gz', 'r') as f:
|
|
|
|
|
for l in f:
|
|
|
|
|
line = l.decode('UTF-8').replace("\n", "").split("\t")
|
2021-05-12 20:18:46 +02:00
|
|
|
y_train.append(line[0])
|
|
|
|
|
X_train.append(line[1:])
|
2021-05-12 19:58:28 +02:00
|
|
|
|
2021-05-12 20:18:46 +02:00
|
|
|
X_train = np.asanyarray(X_train)
|
|
|
|
|
y_train = np.asanyarray(y_train)
|
|
|
|
|
|
|
|
|
|
X_dev = dev[0].values
|
|
|
|
|
X_test = test[0].values
|
|
|
|
|
|
|
|
|
|
print(X_dev)
|
