작업형2 성별예측 문제

https://dataq.goorm.io/exam/116674/체험하기/quiz/4

여기서 하는 성별예측 문제에서

import pandas as pd

train = pd.read_csv("data/customer_train.csv")

test = pd.read_csv("data/customer_test.csv")

# print(train.shape, test.shape)

# print(train.info())

# print(train.isnull().sum())

# print(test.isnull().sum())

#결측치 처리 (환불금액)

train['환불금액'] = train['환불금액'].fillna(0)

test['환불금액'] = test['환불금액'].fillna(0)

# print(test.isnull().sum())

# print(train['성별'].value_counts())

#인코딩

target = train.pop('성별')

train = pd.get_dummies(train)

test = pd.get_dummies(test)

#검증 데이터 분리

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)

# print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape)

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(random_state=0)

rf.fit(X_tr, y_tr)

pred = rf.predict_proba(X_val)

# print(pred)

from sklearn.metrics import roc_auc_score

roc = roc_auc_score(y_val, pred[:,1])

#예측 및 파일생성

pred = rf.predict_proba(test)

submit = pd.DataFrame({

"pred":pred[:,1]

})

submit.to_csv("result.csv", index=False)

# print(pd.read_csv("result.csv"))

이렇게 코딩을 했는데 예측 및 파일 생성에서

pred = rf.predict_proba(test) 여기 부분이 오류가 뜨는데 왜 그런가요 ㅠㅠ

> Makefile:6: recipe for target 'py3_run' failed

make: *** [py3_run] Error 1

Traceback (most recent call last):

File "/goorm/Main.out", line 43, in <module>

pred = rf.predict_proba(test)

File "/usr/local/lib/python3.9/dist-packages/sklearn/ensemble/_forest.py", line 674, in predict_proba

X = self._validate_X_predict(X)

File "/usr/local/lib/python3.9/dist-packages/sklearn/ensemble/_forest.py", line 422, in validateX_predict

return self.estimators_[0]._validate_X_predict(X, check_input=True)

File "/usr/local/lib/python3.9/dist-packages/sklearn/tree/_classes.py", line 407, in validateX_predict

X = self._validate_data(X, dtype=DTYPE, accept_sparse="csr",

File "/usr/local/lib/python3.9/dist-packages/sklearn/base.py", line 437, in validatedata

self._check_n_features(X, reset=reset)

File "/usr/local/lib/python3.9/dist-packages/sklearn/base.py", line 365, in checkn_features

raise ValueError(

ValueError: X has 73 features, but DecisionTreeClassifier is expecting 74 features as input.

이렇게 뜹니다,,