인프런 커뮤니티 질문&답변

# 출력을 원하실 경우 print() 함수 활용
# 예시) print(df.head())

# getcwd(), chdir() 등 작업 폴더 설정 불필요
# 파일 경로 상 내부 드라이브 경로(C: 등) 접근 불가

# 데이터 파일 읽기 예제
import pandas as pd
X_test = pd.read_csv("data/X_test.csv")
X_train = pd.read_csv("data/X_train.csv")
y_train = pd.read_csv("data/y_train.csv")

# 사용자 코딩

# 답안 제출 참고
# 아래 코드 예측변수와 수험번호를 개인별로 변경하여 활용
# pd.DataFrame({'cust_id': X_test.cust_id, 'gender': pred}).to_csv('003000000.csv', index=False)

# print(X_test.shape, X_train.shape, y_train.shape)

# print(X_test.isnull().sum())
# print(X_test['환불금액'].describe())

# print(X_train.isnull().sum())
# print(y_train.isnull().sum())
# print(X_test.shape, X_train.shape, y_train.shape)
# print(X_train.isnull().sum())
X_test['환불금액'] = X_test['환불금액'].fillna(0)
X_train['환불금액'] = X_train['환불금액'].fillna(0)
# print(X_train.isnull().sum())
# print(X_test.shape, X_train.shape)
# print(X_test.describe(include ='object'))
# print(X_train.describe(include ='object'))
# print(X_test.shape, X_train.shape)
# con_data = X_train.concat(X_test.)
print(X_test.shape, X_train.shape)
cust_ID= X_test.pop('cust_id')
X_train = X_train.drop('cust_id',axis =1)
y_cust_ID = y_train.pop('cust_id')
print(X_test.shape, X_train.shape)
print(y_train.head())

X_com = pd.concat([X_test, X_train],axis=0)
X_com = pd.get_dummies(X_com)
print(X_com.shape)
X_test = X_com.iloc[0:2482,:]
X_train = X_com.iloc[2482:5982,:]
print(X_test.shape, X_train.shape,y_train.shape)

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 =0.1,random_state =0)
print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape)

import lightgbm as lgm
model = lgm.LGBMClassifier()
model.fit(X_tr, y_tr)
pred = model.predict_proba(X_val)

마지막에서 오류가 발생했습니다.

DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().

return f(*args, **kwargs)

 # from sklearn.ensemble import RandomForestClassifier

# rf = RandomForestClassifier()

# rf.fit(X_tr, y_tr)

# pred = rf.predict_proba(X_val)

랜덤 포레스트로 돌려도 같은 오류가 발생합니다

어떤걸 잘못한건가요?