[Python] why x_test and x_train are equal [closed]

The code should split dataset 'x' into distinct training (x_train) and testing (x_test) subsets, but currently fails to do

code must split the x to x_train and x_test but my code don't work,why x_train and x_test are equal and same?

stop_words = stopwords.words("english")
neg = []
for file in os.listdir("dataset/neg"):
with open("dataset/neg/" + file) as f:
text = f.read()
tokens = word_tokenize(text)
translator = str.maketrans("", "", punctuation)
clean_tokens = []
for w in tokens:
word = w.translate(translator)
if word.lower() not in stop_words:
clean_tokens.append(word)
tokens = clean_tokens
neg.append(" ".join(tokens))

pos = []
for file in os.listdir("dataset/pos"):
with open("dataset/pos/" + file) as f:
text = f.read()
tokens = word_tokenize(text)
translator = str.maketrans("", "", punctuation)
clean_tokens = []
for w in tokens:
word = w.translate(translator)
if word.lower() not in stop_words:
clean_tokens.append(word)
tokens = clean_tokens
pos.append(" ".join(tokens))

x = np.concatenate([neg,pos])
y_neg =[]
for nege in range(0,700):
y_neg.append(0)

y_pos =[]
for pose in range(0,700):
y_neg.append(1)

y = np.concatenate([y_neg,y_pos])


x_train,y_train,x_test,y_test = train_test_split(x,y,test_size=0.2)

print(len(x_train))
print(len(x_test))

Continue reading...