인프런 커뮤니티 질문&답변

import pandas as pd

train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
train

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

from sklearn.preprocessing import MinMaxScaler
cols = ['Customer_Age','Dependent_count', 'Months_on_book', 'Total_Relationship_Count',	'Months_Inactive_12_mon',	'Contacts_Count_12_mon',	'Credit_Limit',	'Total_Revolving_Bal',	'Avg_Open_To_Buy',	'Total_Amt_Chng_Q4_Q1',	'Total_Trans_Amt',	'Total_Trans_Ct',	'Total_Ct_Chng_Q4_Q1',	'Avg_Utilization_Ratio']

scaler = MinMaxScaler()
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('CLIENTNUM', axis =1)
test = 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 = 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(X_val)
print(pred)
# 정확도
print(accuracy_score(y_val, pred))

# 정밀도
print(precision_score(y_val, pred))

# 재현율 (민감도)
print(recall_score(y_val, pred))

# F1
print(f1_score(y_val , pred))

위와 같이 코드를 진행시

[0 1 0 ... 1 0 1]

1.0

1.0

1.0

1.0

이 나옵니다. pred 자체가 1차원으로만 나오고 정확도 정밀도 재현율 F1도 1.0으로만 나오는데 무엇이 잘못된건지 모르겠습니다ㅠㅠ