ch6-Kfold-CrossValidation.py

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.cross_validation 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)


import numpy as np
from sklearn.cross_validation import StratifiedKFold
kfold = StratifiedKFold(y=y_train, n_folds=10, random_state=1)
scores = []
for k, (train, test) in enumerate(kfold):
    pipe_lr.fit(X_train[train], y_train[train])
    score = pipe_lr.score(X_train[test], y_train[test])
    scores.append(score)
    print('Fold: %s, Class dist.: %s, Acc: %.3f' % (k+1, np.bincount(y_train[train]), score))

print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))