인프런 커뮤니티 질문&답변

#중급단계
#목표 : 범주형 카테고리 데이터 활용하기
import pandas as pd
train=pd.read_csv("train.csv")
test=pd.read_csv("test.csv")
#원핫?레이블인코딩?
#EDA
train.shape
#범주형데이터를 원핫인코딩해보기
train.describe(include="O")
test.describe(include="O")
train=pd.get_dummies(train)
test=pd.get_dummies(test)
target=train.pop('Segmentation')
test_ID = test.pop("ID")
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(max_depth=9, random_state=2022)
model.fit(train,target)
pred = model.predict(test)
pred