import pandas as pd
df=pd.read_csv('https://archive.ics.uci.edu/ml/'
'machine-learning-databases'
'/breast-cancer-wisconsin/wdbc.data', header=None)
from sklearn.preprocessing import LabelEncoder
X=df.loc[:,2:].values
y=df.loc[:, 1].values
le=LabelEncoder()
y=le.fit_transform(y)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=\
train_test_split(X, y, test_size=0.2, stratify=y, random_state=1)