摘要

通過巢狀交叉驗證選擇演算法（外部迴圈通過k-折等進行引數優化，內部迴圈使用交叉驗證），我們可以對特定資料集進行模型選擇

程式碼

# 6.4.2: 巢狀交叉驗證選擇演算法，用於在不同的機器學習演算法中進行選擇

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import
 
 GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import LabelEncoder

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.pipeline import Pipeline


# 匯入資料
df = pd.read_csv('./Data/UCI/wdbc.data.txt'
 
)

# Slicing
X, y = df.iloc[:, 2:].values, df.iloc[:, 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)


# 構造模型
pipe_svc = Pipeline([('scl', StandardScaler()),
                     ('clf', SVC(random_state=1
 
))])
param_range = [10**c for c in range(-4, 4)]
# param_range = np.linspace(0.0001, 1, 10)
param_grid = [
    {'clf__C': param_range, 'clf__kernel': ['linear']}, # 對於線性SVM只需要調優正則化引數C
    {'clf__C': param_range, 'clf__gamma': param_range, 'clf__kernel': ['rbf']}   #  對於核SVM則需要同時調優C和gamma值
]

gs = GridSearchCV(estimator=pipe_svc,
                  param_grid=param_grid,
                  scoring='accuracy',
                  cv=10,
                  n_jobs=-1)
# gs.fit(X_train, y_train)
# clf = gs.best_estimator_
scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))


gs = GridSearchCV(estimator=DecisionTreeClassifier(random_state=0),
                  param_grid=[{'max_depth':[1,2,3,4,5,6,7,None]}],
                  scoring='accuracy',
                  cv=5)
scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))