인프런 커뮤니티 질문&답변

 라이브러리 및 데이터 불러오기
import pandas as pd

train = pd.read_csv('https://raw.githubusercontent.com/lovedlim/inf/refs/heads/main/p2/ch4/train.csv')
test = pd.read_csv('https://raw.githubusercontent.com/lovedlim/inf/refs/heads/main/p2/ch4/test.csv')

# test.isnull().sum() #결측치 처리 필요함 Item_Weight//// Outlet_Size
target=train.pop('Item_Outlet_Sales')


# 결측치 처리
train['Item_Weight'] = train['Item_Weight'].fillna(train['Item_Weight'].mean())
train['Outlet_Size'] = train['Outlet_Size'].fillna(train['Outlet_Size'].mode()[0])

test['Item_Weight'] = test['Item_Weight'].fillna(train['Item_Weight'].mean())
test['Outlet_Size'] = test['Outlet_Size'].fillna(train['Outlet_Size'].mode()[0])

# train=train.drop('Item_Identifier',axis=1)
# test=test.drop('Item_Identifier',axis=1)



#다르므로 데이터 합친 후 레이블인코딩 하고 다시 train test로 나누기
combined=pd.concat([train,test])


#->그다음 레이블인코딩해보자
cols=train.select_dtypes(include="O").columns
print(cols)
from sklearn. preprocessing import LabelEncoder
for col in cols:
  le=LabelEncoder()
  combined[col]=le.fit_transform(combined[col])

#->다시 데이터 train과 test로 나누자
train=combined.iloc[:len(train)].copy()
test=combined.iloc[len(train):].copy()


print(train.shape, test.shape)
#train데이터분할하기

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=100)

# #모델구축(1)
# from sklearn.ensemble import RandomForestRegressor
# model=RandomForestRegressor(random_state=200)
# model.fit(X_tr,y_tr)
# pred = model.predict(X_val)

#모델구축(2)
import lightgbm as lgb
model = lgb.LGBMRegressor(random_state=0, verbose=-1)
model.fit(X_tr, y_tr)
pred = model.predict(X_val)

#성능평가
from sklearn.metrics import root_mean_squared_error
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error

result=root_mean_squared_error(y_val,pred) 
print('RMSE:', result)

result = mean_squared_error(y_val, pred)
print('MSE:', result)

result = mean_absolute_error(y_val, pred)
print('MAE:', result)

result = r2_score(y_val, pred)
print('r2:', result)