인프런 커뮤니티 질문&답변

안녕하세요 선생님..

이 문제에서

import pandas as pd

pd.set_option('display.max_column',None)

pd.set_option('display.float_format',"{:.10f}".format)

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

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

# print(train.shape, test.shape) # 3500,11 / 2482 ,10개

# print(train.isnull().sum()) # 환불금액 결측치 있음 2295

train = train.fillna(0)

test = train.fillna(0)

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

# print(train.head())

# print(train.info()) # 주 구매상품, 주 구매지점

# print(train.describe(include='object')) # 유니크가 42개, 24개라서 라벨인코더 가야할듯

# cols = train.select_dtypes(inclued='object').coulmns !!!!

# print(train.head())

cols = ['주구매상품', '주구매지점']

# print(train['주구매상품'].nunique())

# print(test['주구매상품'].nunique())

# print(train.describe(include='O'))

# print(test.describe(include='O'))

from sklearn.preprocessing import LabelEncoder

for col in cols :

le = LabelEncoder()

train[col] = le.fit_transform(train[col])

test[col] = le.transform(test[col])

# print(train.shape, test.shape)

# print(train.head())

target = train.pop('성별')

# print(target)

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)

# print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape) # 2800

from sklearn.metrics import roc_auc_score

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier()

rf.fit(X_tr,y_tr)

pred = rf.predict_proba(test) <---- 실행했는데

여기를 실행하면

ValueError: X has 11 features, but DecisionTreeClassifier is expecting 10 features as input.

가 발생합니다.. 대체 왜 그럴까요 ㅠㅠ??