sport-text-classification-b.../bayes2.py
2021-05-12 20:18:46 +02:00

24 lines
546 B
Python

import pandas as pd
import numpy as np
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)
X_train = []
y_train = []
with gzip.open('train/train.tsv.gz', 'r') as f:
for l in f:
line = l.decode('UTF-8').replace("\n", "").split("\t")
y_train.append(line[0])
X_train.append(line[1:])
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)