sklearn.inspection.permutation_importance 파라미터 정리

permutation_importance

sklearn.inspection. permutation_importance ( estimator , X , y , * , 점수 = 없음 , n_repeats = 5 , 
n_jobs = 없음 , random_state = 없음 , sample_weight = 없음 , max_samples = 1.0 )

from sklearn.inspection import permutation_importance

728x90

permutation_importance 파라미터

estimator = object

X = ndarray or DataFrame, shape (n_samples, n_features)

y = array-like or None, shape (n_samples, ) or (n_samples, n_classes)

scoring = str, callable, list, tuple, or dict, default=None

# 분류때 사용하는거 ex)f1_score, accuracy 등

n_repeats = int, default=5

n_jobs = int or None, default=None

random_state = int, RandomState instance, default=None

sample_weight = array-like of shape (n_samples,), default=None

max_samples = int or float, default=1.0

# 각 반복에서 기능 중요도를 계산하기 위해 X에서 추출할 샘플 수(교체 없음)

from sklearn.datasets import load_diabetes
from sklearn.ensemble import RandomForestRegressor
from sklearn.inspection import permutation_importance
from sklearn.model_selection import train_test_split

# load the diabetes dataset
diabetes = load_diabetes()

# split the data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(diabetes.data, diabetes.target, random_state=0)

# create a random forest regressor
rf = RandomForestRegressor(random_state=0)

# fit the model to the training data
rf.fit(X_train, y_train)

# calculate feature importance scores using permutation importance
result = permutation_importance(rf, X_test, y_test, n_repeats=10, random_state=0)

# print the feature importance scores
print(result.importances_mean)