인프런 커뮤니티 질문&답변

import pandas as pd
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
y_test = pd.read_csv("y_test.csv")

from sklearn.preprocessing import LabelEncoder
cols = train.select_dtypes(include = 'object').columns
for col in cols: 
    le = LabelEncoder()
    train[col] = le.fit_transform(train[col])
    test[col] = le.transform(test[col])

train = train.drop('CLIENTNUM',axis=1)
test_id = test.pop('CLIENTNUM')

from sklearn.model_selection import train_test_split
X_tr,X_val,y_tr,y_val = train_test_split(train,
                                         train['Attrition_Flag'],
                                         test_size = 0.2,
                                         random_state = 2022)

from xgboost import XGBClassifier
from sklearn.metrics import roc_auc_score,accuracy_score,f1_score,precision_score, recall_score
model = XGBClassifier(random_state=2022)
model.fit(X_tr,y_tr)
pred = model.predict(X_val)
pred

print(accuracy_score(y_val,pred))
print(f1_score(y_val,pred))
print(precision_score(y_val,pred))
print(recall_score(y_val,pred))


pred = model.predict(X_val)
pred

pred = model.predict_proba(test)
pred    (여기 과정에서 오류가 생깁니다 ㅠ)

ValueError: Feature shape mismatch, expected: 20, got 19

이렇게 오류가 생기는데 뭐가 잘못된걸까요?ㅠㅠ