작성자 없음
작성자 정보가 삭제된 글입니다.
해결된 질문
작성
·
107
0
import pandas as pd
pd.set_option('display.max_columns',None)
train = pd.read_csv("data/customer_train.csv")
test = pd.read_csv("data/customer_test.csv")
train['환불금액'] = train['환불금액'].fillna(0)
test['환불금액'] = test['환불금액'].fillna(0)
#cols=['주구매상품','주구매지점']#0.6117
cols=['회원ID','총구매액','최대구매액','환불금액','방문일수','방문당구매건수','주말방문비율','구매주기']
target=train.pop('성별')
#from sklearn.preprocessing import LabelEncoder
#le=LabelEncoder()
#for col in cols:
# train[col]=le.fit_transform(train[col])
# test[col]=le.transform(test[col])
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)
from sklearn.ensemble import RandomForestClassifier
model=RandomForestClassifier()
model.fit(x_tr,y_tr)
pred=model.predict_proba(x_val)
#print(pred)
from sklearn.metrics import roc_auc_score
print(roc_auc_score(y_val, pred[:,1]))
pred = model.predict_proba(test)
submit = pd.DataFrame({
'pred': pred[:,1]
})
submit.to_csv('result.csv', index=False)
print(pd.read_csv('result.csv'))
답변 2
0
obeject가 있어서 에러가 발생했어요
수치형 값만 선택하려고 한 것인가요?
인코딩 방법은 아래와 같습니다.
cols=['주구매상품','주구매지점']
target=train.pop('성별')
from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
for col in cols:
train[col]=le.fit_transform(train[col])
test[col]=le.transform(test[col])
0
import pandas as pd
pd.set_option('display.max_columns',None)
train = pd.read_csv("data/customer_train.csv")
test = pd.read_csv("data/customer_test.csv")
train['환불금액'] = train['환불금액'].fillna(0)
test['환불금액'] = test['환불금액'].fillna(0)
#cols=['주구매상품','주구매지점']#0.6117
cols=['회원ID','총구매액','최대구매액','환불금액','방문일수','방문당구매건수','주말방문비율','구매주기']
target=train.pop('성별')
#from sklearn.preprocessing import LabelEncoder
#le=LabelEncoder()
#for col in cols:
# train[col]=le.fit_transform(train[col])
# test[col]=le.transform(test[col])
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)
from sklearn.ensemble import RandomForestClassifier
model=RandomForestClassifier()
model.fit(x_tr,y_tr)
pred=model.predict_proba(x_val)
#print(pred)
from sklearn.metrics import roc_auc_score
print(roc_auc_score(y_val, pred[:,1]))
pred = model.predict_proba(test)
submit = pd.DataFrame({
'pred': pred[:,1]
})
submit.to_csv('result.csv', index=False)
print(pd.read_csv('result.csv'))
본문 코드가 깨져서 댓글로 다시 올립니다!