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)

le.transform(['M', 'B'])

'''

array([1, 0])

'''

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=1)

from sklearn.preprocessing import StandardScaler

from sklearn.decomposition import PCA

from sklearn.linear_model import LogisticRegression

from sklearn.pipeline import Pipeline

pipe_lr = Pipeline([ ('scl', StandardScaler()), ('pca', PCA(n_components=2)) , ('clf', LogisticRegression(random_state=1))])

pipe_lr.fit(X_train, y_train)

print('Test Accuracy: %.3f' % pipe_lr.score(X_test, y_test))

#Test Accuracy: 0.947