【Scikit-learn】糖尿病患者のデータセットでRidgeモデルで特徴量の全組み合わせを検討［Python］

＜セル１＞

from sklearn.datasets import load_diabetes
import pandas as pd

diabetes = load_diabetes()

df = pd.DataFrame(diabetes.data, columns=diabetes.feature_names)

df["target"] = diabetes.target

df

実行結果

import itertools
from sklearn.model_selection import train_test_split
from sklearn.svm import SVR
from sklearn.metrics import r2_score
import numpy as np

import itertools
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Ridge
from sklearn.metrics import r2_score
import numpy as np

model_svr = SVR()

model_rd = Ridge()

＜セル２＞

import itertools
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Ridge
from sklearn.metrics import r2_score
import numpy as np

trial=10

score_list = []; combination_list = []

for i in range(1, len(diabetes.feature_names)+1):
    print(i)
    for comb in itertools.combinations(diabetes.feature_names, i):
#         print(comb)
        
        x = df.loc[:, comb]
        y = df.loc[:, "target"]
        
#         print(x)
        
        pred_rd_score = []
        
        for t in range(trial):
        
            x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, train_size=0.8)
            model_rd = Ridge()
            model_rd.fit(x_train, y_train)
            pred_rd = model_rd.predict(x_test)
            pred_rd_score.append(r2_score(y_test, pred_rd))
            
        pred_rd_ave = np.average(np.array(pred_rd_score))
        
#         print(pred_rd_ave)
        
        if len(score_list) < 10:
            score_list.append(pred_rd_ave)
            combination_list.append(comb)
        elif len(score_list) == 10:
            if np.min(score_list) < pred_rd_ave:
                del combination_list[np.argmin(score_list)]
                del score_list[np.argmin(score_list)]
                combination_list.append(comb)
                score_list.append(pred_rd_ave)
                
for comb, score in zip(combination_list, score_list):
    print(comb, score)

実行結果
('sex', 'bmi', 'bp', 's3', 's4', 's5') 0.439693010132639
('bmi', 'bp', 's1', 's3', 's5', 's6') 0.42800410791192245
('age', 'bmi', 'bp', 's3', 's4', 's5', 's6') 0.4260323203866879
('sex', 'bmi', 'bp', 's1', 's2', 's3', 's5') 0.43784734895660027
('sex', 'bmi', 'bp', 's1', 's3', 's4', 's5') 0.4291064870545248
('sex', 'bmi', 'bp', 's1', 's3', 's5', 's6') 0.43488580704318186
('bmi', 'bp', 's1', 's2', 's3', 's5', 's6') 0.4280862604485365
('age', 'sex', 'bmi', 'bp', 's2', 's3', 's5', 's6') 0.4349084526454246
('age', 'sex', 'bmi', 'bp', 's1', 's2', 's4', 's5', 's6') 0.4264502561900601
('age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6') 0.43040534713759004