빅분기 실습 3 - Model Selection 소개

## 2.4 Model Selection 소개
### 학습/테스트 데이터 셋 분리 – train_test_split()

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

iris = load_iris()
dt_clf = DecisionTreeClassifier()
train_data = iris.data
train_label = iris.target
dt_clf.fit(train_data, train_label)

# 학습 데이터 셋으로 예측 수행
pred = dt_clf.predict(train_data)
print('예측 정확도:',accuracy_score(train_label,pred))

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

dt_clf = DecisionTreeClassifier( )
iris_data = load_iris()

X_train, X_test, y_train, y_test = train_test_split(iris_data.data, iris_data.target, test_size=0.3, random_state=121)

dt_clf.fit(X_train, y_train)
pred = dt_clf.predict(X_test)
print('예측 정확도: {0:.4f}'.format(accuracy_score(y_test,pred)))

chapter3.3 Model Selection 모듈 소개.ipynb

0.02MB