f1_score값 관련

다시 해봐도 똑같네요. 랜덤포레스트로는 f1스코어가 잘 나오는 것 같은데, lgb로 해보면 f1스코어가 1.0으로 나와요 ㅠㅠ
# 시험환경 세팅
import pandas as pd
from sklearn import datasets
dataset = datasets.load_breast_cancer()
df = pd.DataFrame(dataset['data'], columns=dataset['feature_names'])
df['target'] = dataset['target']
df.to_csv("data2.csv", index=False)

from sklearn.model_selection import train_test_split
train, test = train_test_split(df, test_size=0.2, random_state=2022)
y_test = test.pop('target')
train.to_csv('train.csv', index=False)
test.to_csv('test.csv', index=False)

#####################################################################

# 출력을 원하실 경우 print() 함수 활용
# 예시) print(df.head())

# getcwd(), chdir() 등 작업 폴더 설정 불필요
# 파일 경로 상 내부 드라이브 경로(C: 등) 접근 불가

# 데이터 파일 읽기 예제
import pandas as pd
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
# 사용자 코딩

# 수치형 이상치 스케일링
# print(train.head())
train.select_dtypes(exclude=object).columns
cols = ['mean radius', 'mean texture', 'mean perimeter', 'mean area',
       'mean smoothness', 'mean compactness', 'mean concavity',
       'mean concave points', 'mean symmetry', 'mean fractal dimension',
       'radius error', 'texture error', 'perimeter error', 'area error',
       'smoothness error', 'compactness error', 'concavity error',
       'concave points error', 'symmetry error', 'fractal dimension error',
       'worst radius', 'worst texture', 'worst perimeter', 'worst area',
       'worst smoothness', 'worst compactness', 'worst concavity',
       'worst concave points', 'worst symmetry', 'worst fractal dimension']

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
train[cols] = scaler.fit_transform(train[cols])
test[cols] = scaler.transform(test[cols])
# print(train.head())

# 검증 데이터 분리
from sklearn.model_selection import train_test_split
X_tr, X_val, y_tr, y_val = train_test_split(train.drop('target', axis=1), train['target'], test_size=0.15, random_state=2023)
X_tr.shape, X_val.shape, y_tr.shape, y_val.shape

from sklearn.ensemble import RandomForestClassifier
import lightgbm as lgb
from sklearn.metrics import f1_score

# model = RandomForestClassifier(random_state=2023)
# model.fit(X_tr, y_tr)
# pred = model.predict(X_val)
# print(f1_score(y_val, pred))

# 0.9876543209876543

model = lgb.LGBMClassifier()
model.fit(X_tr, y_tr)
pred = model.predict(X_val)
print(f1_score(y_val, pred))
인프런 커뮤니티 질문&답변
