인프런 커뮤니티 질문&답변

df = pd.concat([X_train,y_train['Reached.on.Time_Y.N']], axis=1)

n_train = df.select_dtypes(exclude = object).copy()
c_train = df.select_dtypes(include = object).copy()
n_test = df.select_dtypes(exclude = object).copy()
c_test = df.select_dtypes(include = object).copy()

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
cols = ['Customer_care_calls','Customer_rating', 'Cost_of_the_Product', 'Prior_purchases', 'Discount_offered', 'Weight_in_gms']
n_train[cols] = scaler.fit_transform(n_train[cols])
n_test[cols] = scaler.transform(n_test[cols])

c_train = pd.get_dummies(c_train)
c_test = pd.get_dummies(c_test)

train = pd.concat([n_train, c_train], axis =1)
test = pd.concat([n_test, c_test], axis =1)

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

from sklearn.model_selection import train_test_split
X_tr, X_val, y_tr, y_val = train_test_split(
                                              train.drop('Reached.on.Time_Y.N', axis =1),
                                              train['Reached.on.Time_Y.N'],
                                              test_size = 0.2,
                                              random_state = 2023)

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score

model = RandomForestClassifier(random_state = 2023)
model.fit(X_tr, y_tr)
pred = model.predict_proba(X_val)[:,1]
print(roc_auc_score(y_val, pred))

pred = model.predict_proba(test)[:,1]
submit = pd.DataFrame({
                        'ID': test_id,
                        'Reached.on.Time_Y.N': pred
})
submit.to_csv("0000.csv", index = False)

작업형2를 n_train, n_test, c_train, c_test로 나누어서 풀어보는 연습을 하고있는데요

위와 같이 코딩을 했는데 roc_auc_score는 잘 출력이 되지만 아래와 같은 워닝이 뜹니다. 이유를 알 수 있을까요?

0.7289745856473446

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-81-0b0c32327ea7> in <cell line: 38>()
     36 print(roc_auc_score(y_val, pred))
     37 
---> 38 pred = model.predict_proba(test)[:,1]
     39 submit = pd.DataFrame({
     40                         'ID': test_id,

3 frames

/usr/local/lib/python3.10/dist-packages/sklearn/base.py in _check_feature_names(self, X, reset)
    479                 )
    480 
--> 481             raise ValueError(message)
    482 
    483     def _validate_data(

ValueError: The feature names should match those that were passed during fit.
Feature names unseen at fit time:
- Reached.on.Time_Y.N