dataset fixing

import pandas as pd
from sklearn.model_selection import train_test_split

# reading featuers of dataset
f=open('/content/spike_counts.txt', 'r')

lst0=[]
for i in f:
    lst1=[int(j) for j in i.split(' ')]
    lst0.append(lst1)

df0=pd.DataFrame(lst0)
print(df0.shape)

#reading labels of dataset
df1=pd.read_table('/content/location_areas.txt',header=None)
print(df1.shape)

#splitting the dataset into 80%-20% train-test segments
X_train,X_test,y_train,y_test=train_test_split(df0,df1,train_size=0.8,random_state=0)
print(X_train.shape)
print(X_test.shape)
print(y_train.shape)
print(y_test.shape)