머신러닝 - ex06_타이타닉_앙상블모델

### 전처리된 파일 불러오기

import pandas as pd
X_train = pd.read_csv('X_train.csv')
X_test = pd.read_csv('X_test.csv')
y_train = pd.read_csv('y_train.csv')

X_train.shape, X_test.shape, y_train.shape

### 앙상블 모델 사용하기
- 머신러닝에서 성능이 좋은 모델
- 여러 개의 DecisionTree를 사용하는 모델

#### RandomForest  모델

from sklearn.ensemble import RandomForestClassifier

forest = RandomForestClassifier(n_estimators=90, max_features=0.3, max_depth=5)

# 경고 무시하는 기능
import warnings
warnings.filterwarnings('ignore')

forest.fit(X_train, y_train)

# 학습한 모델로 예측
pre = forest.predict(X_test)
pre
# 평가 결과 서식 불러오기
gender_sub = pd.read_csv('./data/gender_submission.csv')
# 예측한 값 집어넣기
gender_sub['Survived'] = pre
# 예측값 내보내기
gender_sub.to_csv('RFsub.csv',index =False)

#### AdaBoost 모델

from sklearn.ensemble import AdaBoostClassifier

adaboost = AdaBoostClassifier(n_estimators=500)

adaboost.fit(X_train,y_train)

pre = adaboost.predict(X_test)
pre

#### GBM(Gradient Boosting Machine)


from sklearn.ensemble import GradientBoostingClassifier

gbm = GradientBoostingClassifier(n_estimators=500, learning_rate=0.1,max_depth=5)

gbm.fit(X_train,y_train)

pre =gbm.predict(X_test)
pre

#### XGBoost

!pip install xgboost

import xgboost as xgb

from xgboost.sklearn import XGBClassifier

XGBClassifier()

#### LGBM(Light GBM)

!pip install lightgbm

import lightgbm

from lightgbm.sklearn import LGBMClassifier

4. 머신러닝 수업 자료(앙상블)_h.pdf

1.51MB