ID 삭제 필수 인가요?

投稿した質問数 2

0

데이터가

어떻게 나올지 몰라 판단 기준은 평가 지표 점수로 하는 것이 맞습니다

일반적으로는

의미 없는 데이터여서 삭제하지만 성능이 좋게 검증된다면 그대로 두시죠!!

0

코드는 대략 이렇게 썼습니다

0

# 데이터 불러오기
train = pd.read_csv("https://raw.githubusercontent.com/lovedlim/inf/refs/heads/main/p4/4_2/train.csv")
test = pd.read_csv("https://raw.githubusercontent.com/lovedlim/inf/refs/heads/main/p4/4_2/test.csv")

train.info()

# print(set(train['Gender']) == set(test['Gender']))
# print(set(train['Ever_Married']) == set(test['Ever_Married']))
# print(set(train['Graduated']) == set(test['Graduated']))
# print(set(train['Profession']) == set(test['Profession']))
# print(set(train['Spending_Score']) == set(test['Spending_Score']))
# print(set(train['Var_1']) == set(test['Var_1']))

target = train.pop("Segmentation")

# train = train.drop('ID', axis=1)
# test = test.drop('ID', axis=1)


print(train.shape)
print(test.shape)

train = pd.get_dummies(train)
test = pd.get_dummies(test)
print(train.shape)
print(test.shape)

from sklearn.model_selection import train_test_split
X_tr, X_val, y_tr, y_val = train_test_split(train, target, test_size=0.2, random_state=0)

from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(random_state=0)
rf.fit(X_tr, y_tr)
pred_rf = rf.predict(X_val)

import lightgbm as lgb
lg = lgb.LGBMClassifier(verbose=-1, random_state=0)
lg.fit(X_tr, y_tr)
pred_lg = lg.predict(X_val)

from sklearn.metrics import f1_score
f1_rf = f1_score(y_val, pred_rf, average='macro')
f1_lg = f1_score(y_val, pred_lg, average='macro')

print(f1_rf)
print(f1_lg)