인프런 커뮤니티 질문&답변

작업 2유형 기출문제 4번을 풀이하는 중인데 f1_score 평가지표로 y_val predict 돌려보다가 에러가 떠서 질문 드립니다!

모델링까지는 문제없이 돌아갔었는데 혹시 아래 에러창이 어디서 에러가 났다는 뜻인지 여쭤봅니다!

# 라이브러리 불러오기
import pandas as pd

# 데이터 불러오기
train = pd.read_csv("./sample_data/train.csv")
test = pd.read_csv("./sample_data/test.csv")

#데이터 확인
#train.shape, test.shape ((6665, 11), (2154, 10))

#train.head()
#ID	Gender	Ever_Married	Age	Graduated	Profession	Work_Experience	Spending_Score	Family_Size	Var_1	Segmentation
#test.head()
#ID	Gender	Ever_Married	Age	Graduated	Profession	Work_Experience	Spending_Score	Family_Size	Var_1

#결측치 확인 없음, 없음
#train.isnull().sum()
#test.isnull().sum()

#object 확인
#train.info() Gender Ever_Married Graduated Profession Spending_Score Var_1
#test.info() 동일

#object 레이블 인코딩
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.head()
#test.head()
#train.info()
#test.info()

#ID값 삭제
train = train.drop('ID',axis=1)
#train.shape (6665, 10)
test_ID = test.pop('ID')
#test.shape (2154, 9)

#데이터 분리
from sklearn.model_selection import train_test_split
X_tr,X_val,y_tr,y_val = train_test_split(
                      train.drop('Segmentation',axis=1),
                      train['Segmentation'],
                      test_size=0.2,
                      random_state=2022
)

#train.head()
#test.head()
#X_tr.shape,X_val.shape,y_tr.shape,y_val.shape
#((5332, 9), (1333, 9), (5332,), (1333,))

#모델링
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(random_state=2022)
model.fit(X_tr,y_tr)
pred = model.predict(X_val)

#평가
from sklearn.metrics import f1_score
f1_score(y_val,pred)