Cộng đồng Hỏi & Đáp của Inflearn

RandomForestClassifier만 적용하여 앙상블 학습하였을때

ROC_AUC_SCORE가 1.0이 나오는데,, 연습문제 동영상과 같이 0.84.... 가 나오지 않고 1.0이 나오는 이유가 뭘까요 혹시 과적합이라면 오답이라고 할 수 있을까요?

전체 소스 공유합니다.

import seaborn as sns
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.ensemble import RandomForestClassifier

df = sns.load_dataset('titanic')

# 결측치 제거
df['age'] = df['age'].fillna(df.age.mean())
df['deck'] = df.deck.fillna(method='bfill')
df['deck'] = df.deck.fillna(method='ffill')
df['embarked'] = df.embarked.fillna('S')
df['embark_town'] = df.embark_town.fillna('Southampton')

df.isna().sum()

from sklearn.preprocessing import LabelEncoder
obj = ['sex', 'embarked', 'class', 'who', 'adult_male', 'deck', 'embark_town', 'alone']

encoder = LabelEncoder()

for i in obj:
  df[i] = encoder.fit_transform(df[i])

category = ['pclass', 'sex', 'class', 'who', 'adult_male', 'alone']

for i in category:
  df[i] = df[i].astype('category')

df = pd.get_dummies(df)

scaler = MinMaxScaler()
lst = ['age', 'fare']
scaler.fit(df[lst])
df[lst] = scaler.fit_transform(df[lst])

y = df['survived']

X_train, X_test, y_train, y_test = train_test_split(df, y, test_size=0.3, stratify=y, random_state=23)

ml = RandomForestClassifier()

ml.fit(X_train, y_train)
pred = pd.DataFrame(ml.predict_proba(X_test))

from sklearn.metrics import accuracy_score, roc_auc_score

print(roc_auc_score(y_test, pred.iloc[:, 1]))