import pandas as pd 
from sklearn.ensemble import RandomForestClassifier


train = pd.read_csv('/kaggle/input/big-data-analytics-certification-kr-2024-2/train.csv')
test = pd.read_csv('/kaggle/input/big-data-analytics-certification-kr-2024-2/test.csv')

# print(len(train.columns))
# print(len(test.columns))

# print(train.info()) # 모두 수치형 자료
# print(test.info())

# print(train.isnull().sum()) # 둘 다 결측치 없음
# print(test.isnull().sum())



target = train.pop('Class')
train = train.drop(columns = 'id')
test_id = test.pop('id')
# print(train.shape, test.shape)

model = RandomForestClassifier(random_state = 2024)
model.fit(train, target)
pred = model.predict_proba(test)[:, 1]
# print(pred)

submission = pd.DataFrame({'id': test_id, 'Class' : pred})
submission.to_csv('submission.csv', index = False)
print(pd.read_csv('submission.csv'))