AI 8일차 (2023-05-17) 인공지능 기초 _머신러닝 - XGBoost early stopping 및 metrics

XGBoost early stopping

ㄴ Early stopping : 모델의 훈련을 조기에 중단하는 기법 --> 모델이 더 이상 개선되지 않을 때 훈련을 종료하여 과적합을 방지하고 효율적인 모델을 얻을 수 있음

ㄴ XGBoost에서는 early_stopping_rounds 매개변수를 사용하여 early stopping을 구현할 수 있음

 

metrics

eval_metric 

회귀모델 : rmse, mae, rmsle...
이진분류 : error, auc, logloss...
다중분류 : merror, mlogloss...

 

 

실습

 

ml21_xgb_earlystopping_california.py

import numpy as np
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split, KFold
from sklearn.model_selection import cross_val_score, cross_val_predict
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.preprocessing import MaxAbsScaler, RobustScaler

import tensorflow as tf
tf.random.set_seed(77) #weight의 난수값 조절

#1. 데이터
datasets = fetch_california_housing()
x = datasets.data
y = datasets.target


x_train, x_test, y_train, y_test = train_test_split(
    x, y, train_size = 0.7,  random_state=100, shuffle= True 
)

# kfold
n_splits = 11    # 보통 홀수로 들어감
random_state = 42
kfold = KFold(n_splits=n_splits, shuffle=True, 
              random_state=random_state)

# Scaler 적용
# scaler = MinMaxScaler()
# scaler = StandardScaler()
# scaler = MaxAbsScaler()
scaler = RobustScaler()
scaler.fit(x_train)                 # train 은 fit, transform 모두 해줘야 함
x_train = scaler.transform(x_train) # train 은 fit, transform 모두 해줘야 함
x_test = scaler.transform(x_test)   # test 는 transform 만 하면 됨

# 2. 모델
from xgboost import XGBRegressor
model = XGBRegressor(random_state=123, n_estimators=1000,
                    learning_rate = 0.1, max_depth = 6, gamma= 1)

# 3. 훈련
model.fit(x_train, y_train, early_stopping_rounds=20,
          eval_set = [(x_train, y_train), (x_test, y_test)],
          eval_metric='rmse')  
          
          # eval_set : 검증
          # fit 메서드를 사용하여 모델을 훈련
          # early_stopping_rounds = 20 : 20번의 반복 동안 검증 데이터의 성능 향상이 없을 경우 훈련을 조기 종료
          # eval_set 매개변수에 훈련 세트와 테스트 세트를 지정하여 성능을 평가
          # eval_metric 매개변수를 사용하여 평가 지표를 설정
          
          # eval_metric 회귀모델 : rmse, mae, rmsle...
          #             이진분류 : error, auc, logloss...
          #             다중분류 : merror, mlogloss...
        

# 4. 평가, 예측
score = cross_val_score(model, 
                        x_train, y_train, 
                        cv=kfold)   # cv : corss validation
# print('cv acc : ', score)   # kfold 에 있는 n_splits 숫자만큼 나옴 
y_predict = cross_val_predict(model,
                              x_test, y_test,
                              cv=kfold)

r2 = r2_score(y_test, y_predict)
print('cv pred r2 : ', r2)
# cv pred r2 :  0.8184110207883767

ㄴ fetch_california_housing 데이터는 회귀이므로 eval_metric = 'rmse'

 

 

ml21_xgb_earlystopping_cancer.py

import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split, KFold
from sklearn.model_selection import cross_val_score, cross_val_predict
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.preprocessing import MaxAbsScaler, RobustScaler

import tensorflow as tf
tf.random.set_seed(77)  # weight 의 난수값 조정

# 1. 데이터
datasets = load_breast_cancer()  # 다중분류
x = datasets['data']
y = datasets.target

x_train, x_test, y_train,y_test = train_test_split(
    x, y, train_size=0.8, shuffle=True, random_state=42

)
# kfold
n_splits = 11    # 보통 홀수로 들어감
random_state = 42
kfold = KFold(n_splits=n_splits, shuffle=True, 
              random_state=random_state)


# Scaler
scaler = MinMaxScaler()
scaler.fit(x_train)           # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_train) # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_test) 



# 2. 모델
from xgboost import XGBClassifier
model = XGBClassifier()

# 3. 훈련
model.fit(x_train, y_train, early_stopping_rounds=100,
          eval_set = [(x_train, y_train), (x_test, y_test)],
          eval_metric='error')  # 이진분류 : error


# 4. 평가, 예측
score = cross_val_score(model, 
                        x_train, y_train, 
                        cv=kfold)   # cv : corss validation
# print('cv acc : ', score)   # kfold 에 있는 n_splits 숫자만큼 나옴 
y_predict = cross_val_predict(model,
                              x_test, y_test,
                              cv=kfold)
# print('cv pred : ', y_predict)
# cv pred :  [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 1 0 2 2 2 2 2 0 0] # 0.8% 를 제외한 나머지 0.2 %
acc = accuracy_score(y_test, y_predict)
print('cv pred acc : ', acc)

# cv pred acc :  0.9473684210526315

ㄴ cload_breast_cancer 데이터는 이진분류이므로 eval_metric = 'error' 사용

 

 

ml21_xgb_earlystopping_iris.py

import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split, KFold
from sklearn.model_selection import cross_val_score, cross_val_predict
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.preprocessing import MaxAbsScaler, RobustScaler

import tensorflow as tf
tf.random.set_seed(77)  # weight 의 난수값 조정

# 1. 데이터
datasets = load_iris()  # 다중분류
x = datasets['data']
y = datasets.target

x_train, x_test, y_train,y_test = train_test_split(
    x, y, train_size=0.8, shuffle=True, random_state=42

)
# kfold
n_splits = 11    # 보통 홀수로 들어감
random_state = 42
kfold = KFold(n_splits=n_splits, shuffle=True, 
              random_state=random_state)


# Scaler
scaler = MinMaxScaler()
scaler.fit(x_train)           # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_train) # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_test) 



# 2. 모델
from xgboost import XGBClassifier
model = XGBClassifier()

# 3. 훈련
model.fit(x_train, y_train, early_stopping_rounds=100,
          eval_set = [(x_train, y_train), (x_test, y_test)],
          eval_metric='merror')  # 다중분류 : merror


# 4. 평가, 예측
score = cross_val_score(model, 
                        x_train, y_train, 
                        cv=kfold)   # cv : corss validation
# print('cv acc : ', score)   # kfold 에 있는 n_splits 숫자만큼 나옴 
y_predict = cross_val_predict(model,
                              x_test, y_test,
                              cv=kfold)
# print('cv pred : ', y_predict)
# cv pred :  [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 1 0 2 2 2 2 2 0 0] # 0.8% 를 제외한 나머지 0.2 %
acc = accuracy_score(y_test, y_predict)
print('cv pred acc : ', acc)

# cv pred acc :  0.8666666666666667

ㄴ load_iris 데이터는 다중분류이므로 eval_metric = 'merror' 사용

 

 

ml21_xgb_earlystopping_wine.py

import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split, KFold
from sklearn.model_selection import cross_val_score, cross_val_predict
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.preprocessing import MaxAbsScaler, RobustScaler

import tensorflow as tf
tf.random.set_seed(77)  # weight 의 난수값 조정

# 1. 데이터
datasets = load_wine()  # 다중분류
x = datasets['data']
y = datasets.target

x_train, x_test, y_train,y_test = train_test_split(
    x, y, train_size=0.8, shuffle=True, random_state=42

)
# kfold
n_splits = 11    # 보통 홀수로 들어감
random_state = 42
kfold = KFold(n_splits=n_splits, shuffle=True, 
              random_state=random_state)


# Scaler
scaler = MinMaxScaler()
scaler.fit(x_train)                 # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_train) # train 은 fit, transform 모두 해줘야 함
x = scaler.transform(x_test) 



# 2. 모델
from xgboost import XGBClassifier
model = XGBClassifier()

# 3. 훈련
model.fit(x_train, y_train, early_stopping_rounds=100,
          eval_set = [(x_train, y_train), (x_test, y_test)],
          eval_metric='merror')  # 다중분류 : merror


# 4. 평가, 예측
score = cross_val_score(model, 
                        x_train, y_train, 
                        cv=kfold)   # cv : corss validation
# print('cv acc : ', score)   # kfold 에 있는 n_splits 숫자만큼 나옴 
y_predict = cross_val_predict(model,
                              x_test, y_test,
                              cv=kfold)
# print('cv pred : ', y_predict)
# cv pred :  [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 1 0 2 2 2 2 2 0 0] # 0.8% 를 제외한 나머지 0.2 %
acc = accuracy_score(y_test, y_predict)
print('cv pred acc : ', acc)


# cv pred acc :  0.8611111111111112

ㄴ load_wine 데이터는 다중분류이므로 eval_metricn = 'merror' 사용