In [1]:
# load Breast Cancer Wisconsin dataset
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
df = pd.read_csv('https://raw.githubusercontent.com/rasbt/python-machine-learning-book/master/code/datasets/wdbc/wdbc.data', header=None)
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=1)
In [2]:
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
# construct pipeline for SVC
pipe_svc = Pipeline([('scl', StandardScaler()),
('clf', SVC(random_state=1))])
# specify the range of parameter
param_range = [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0]
# specify the parameter we'd want to tune as a list of dictionaries
param_grid = [{'clf__C': param_range,
'clf__kernel': ['linear']},
{'clf__C': param_range,
'clf__gamma': param_range,
'clf__kernel': ['rbf']}]
# initialize GridSearchCV object
gs = GridSearchCV(estimator=pipe_svc,
param_grid=param_grid,
scoring='accuracy',
cv=10,
n_jobs=-1)
# use the training data to perform the grid search
gs = gs.fit(X_train, y_train)
# print the score and parameters of the best model
print(gs.best_score_)
print(gs.best_params_)
In [3]:
# use the test data to estimate the performance of the best selected model
clf = gs.best_estimator_
clf.fit(X_train, y_train)
print('Test accuracy: %.3f' % clf.score(X_test, y_test))
In [6]:
# nested cv
import numpy as np
from sklearn.model_selection import cross_val_score
scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))