인프런 커뮤니티 질문&답변

다음 코드를썼더니 점수가 검정 점수가 0.98나오는데 과적합인지 확인하고싶어서요 ㅠㅠ

train = pd.read_csv('/content/drive/MyDrive/퇴근후딴짓/archive/energy_train.csv')
test = pd.read_csv('/content/drive/MyDrive/퇴근후딴짓/archive/energy_test.csv')
X = train.iloc[:,:-1]
y = train.iloc[:,-1]

display(X.info() , X.head() , X.nunique())
cat_col = X.loc[:,X.nunique() <= 6].columns
num_col = X.loc[:,~(X.nunique() <= 6)].columns

X[cat_col] = X[cat_col].astype('category')
test[cat_col] = test[cat_col].astype('category')

X = pd.get_dummies(X,columns=cat_col)
test = pd.get_dummies(test,columns=cat_col)

#겹치는거 x
print(set(X.columns) - set(test.columns))
print( set(test.columns) - set(X.columns))

from sklearn.model_selection import train_test_split
X_tr,X_val,y_tr,y_val = train_test_split(X,y,test_size=0.2 , stratify = y, random_state=42)

from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(random_state=42)
rf.fit(X_tr,y_tr)
pred=rf.predict(X_val)

from sklearn.metrics import f1_score
f1_score(y_val,pred,average= 'macro')