1. DataFrame의 data로 학습
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import pandas as pd
iris = load_iris()
iris_data = iris.data
iris_label = iris.target
iris_df = pd.DataFrame(data = iris_data, columns = iris.feature_names)
iris_df['label'] = iris_label
X_train, X_test, y_train, y_test = train_test_split(iris_data, iris_label,
test_size = 0.2, random_state = 11)
clf = DecisionTreeClassifier(random_state = 11)
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
predaccur = accuracy_score(y_test, pred)
print("iris example Data를 DTC를 통해 예측 해본 결과, 정확도는 {0:.4f}".format(predaccur))
2. Data set의 data로 학습
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
iris = load_iris()
dt_clf = DecisionTreeClassifier()
train_data = iris.data
train_label = iris.target
dt_clf.fit(train_data, train_label)
pred = dt_clf.predict(train_data)
print("모든 데이터를 통한 예측 정확도 : {}".format(accuracy_score(train_label, pred)))
X_train, X_test, y_train, y_test = train_test_split(train_data, train_label
,test_size = 0.3, random_state = 121)
dt_clf.fit(X_train, y_train)
pred = dt_clf.predict(X_test)
print("train_test_split 사용 후 예측 정확도 : {0:.4f}".format(accuracy_score(y_test, pred)))