01.pipelines.py

import pandas as pd

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data'
df = pd.read_csv(url, header=None)

from sklearn.preprocessing import LabelEncoder

X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)

# Check the mappings:
print('Mappings: [B, M] -> ', le.transform(['B', 'M']))

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)

from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

pipe_lr = make_pipeline(StandardScaler(),
                        PCA(n_components=2),
                        LogisticRegression(random_state=1, solver='lbfgs'))
pipe_lr.fit(X_train, y_train)
print(f'Train accuracy: {pipe_lr.score(X_train, y_train)}')
print(f'Test  accuracy: {pipe_lr.score(X_test, y_test)}')