인프런 커뮤니티 질문&답변

• 학습 관련 질문을 남겨주세요. 상세히 작성하면 더 좋아요!

• 질문과 관련된 영상 위치를 알려주면 더 빠르게 답변할 수 있어요

• 먼저 유사한 질문이 있었는지 검색해보세요

코랩에서는 제대로 돌아가는 코드를 시험환경에 넣었더니 실행시간 1분이 넘어 세션이 종료됩니다ㅠ

잘못된 부분이 있는지, 혹시 시험시간에도 이런 상황이 생긴다면 해결방안 있을까요?

import pandas as pd

train = pd.read_csv("https://raw.githubusercontent.com/lovedlim/inf/main/p2/heart/2files/train.csv")
test =  pd.read_csv("https://raw.githubusercontent.com/lovedlim/inf/main/p2/heart/2files/test.csv")
# train = pd.read_csv("train.csv")
# test =  pd.read_csv("test.csv")
#train.shape, test.shape #((242, 15), (61, 14))
#train.isnull().sum() #결측치 없음
y_train = train['output']
train = train.drop(['id', 'output'], axis=1)
test_id = test.pop('id')
#train.shape, test.shape #((242, 13), (61, 13))
n_cols = train.select_dtypes(exclude='O').columns
c_cols = train.select_dtypes(include='O').columns
n_train = train.select_dtypes(exclude='O').copy()
c_train = train.select_dtypes(include='O').copy()
n_test = test.select_dtypes(exclude='O').copy()
c_test = test.select_dtypes(include='O').copy()

#스케일러
from sklearn.preprocessing import StandardScaler
Scaler = StandardScaler()
n_train[n_cols] = Scaler.fit_transform(n_train[n_cols])
n_test[n_cols] = Scaler.transform(n_test[n_cols])
#인코딩
from sklearn.preprocessing import LabelEncoder
LE = LabelEncoder()
for col in c_cols:
  c_train[col] = LE.fit_transform(c_train[col])
  c_test[col] = LE.transform(c_test[col])
#합치고 검증데이터 분리
X_train = pd.concat([n_train,c_train], axis=1)
X_test = pd.concat([n_test,c_test], axis=1)
#X_train.shape, X_test.shape #((242, 13), (61, 13))

from sklearn.model_selection import train_test_split
x_tr, x_val, y_tr, y_val = train_test_split(X_train, y_train, test_size=0.15, random_state=2024)
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()
model.fit(x_tr,y_tr)
y_val_pred = model.predict_proba(x_val)

from sklearn.metrics import roc_auc_score
score = roc_auc_score(y_val,y_val_pred[:,1])
#print(score) #0.9092261904761905
pred = model.predict_proba(X_test)

df = pd.DataFrame({
    'id': test_id,
    'output': pred[:,1]
})

df.to_csv('010100.csv', index=False)