#16学習とテストデータセットを分離する

Model Selection

ラーニングデータセット

データセットのテスト

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))

train_test_split()

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

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)

NumberPandaryだけでなくPandas Data Frame/Seriesもtrain test split()に分割できます。

import pandas as pd

iris_df = pd.DataFrame(iris_data.data, columns=iris_data.feature_names)
iris_df['target']=iris_data.target
iris_df.head()

ftr_df = iris_df.iloc[:, :-1]
tgt_df = iris_df.iloc[:, -1]
X_train, X_test, y_train, y_test = train_test_split(ftr_df, tgt_df, 
                                                    test_size=0.3, random_state=121)
                                                    
print(type(X_train), type(X_test), type(y_train), type(y_test))                                                    

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