빅데이터 분석기사 실기 예제 - 작업형 2유형(4)

당뇨병 여부 판단

# EDA 
# print(X_train.head())
# print(X_test.head())
# print(y_test.head()) # id, Outcome
# print(X_train.info())
# print(X_train.describe())
# print(y_train['Outcome'].value_counts()) # 0:403, 1:211

# 결측치 확인
# print(X_train.isnull().sum()) X
# print(X_test.isnull().sum()) X

# 필요없는 컬럼 제거
# print(X_train.shape, X_test.shape)
X_train = X_train.drop('id', axis = 1)
test_id = X_test.pop('id')
# print(X_train.shape, X_test.shape, y_train.shape)

# 모델 학습 및 예측
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(random_state = 2023)
model.fit(X_train, y_train['Outcome'])
pred = model.predict(X_test)
# print(pred)

pd.DataFrame({
    'idx' : test_id,
    'Outcome' : pred
}).to_csv('0000.csv', index = False)

print(pd.read_csv('0000.csv'))