diff --git a/run.py b/run.py index e12d136..3c85d5c 100644 --- a/run.py +++ b/run.py @@ -3,11 +3,8 @@ from sklearn.naive_bayes import GaussianNB from sklearn.feature_extraction.text import TfidfVectorizer print("Wczytywanie zbioru treningowego") -#, error_bad_lines=False train = pd.read_csv("train/train.tsv", sep='\t', header=None) -# print(train) -# train = train.dropna() X_train = train[1] Y_train = train[0] print(len(X_train))