python機器學習之decisiontreeclassifier

#決策樹算法的原理是一系列if_else的邏輯迭代。適用於對數據進行分類和回歸，優點是對於數據的本身要求不高，直觀容易理解，缺點是容易過擬合和泛化能力不強。對於回歸而言，不能外推。

from sklearn.tree import DecisionTreeClassifier

import matplotlib.pyplot as plt

import pandas as pd

import numpy as np

from sklearn.datasets import load_breast_cancer

from sklearn.model_selection import train_test_split

cancer=load_breast_cancer()

x_train,x_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer,random_state=42)

tree=DecisionTreeClassifier()

tree.fit(x_train,y_train)

tree.score(x_train,y_train)

tree.score(x_test,y_test)

#結果顯示過擬合，預剪枝max_depth

tree04=DecisionTreeClassifier(max_depth=4,random_state=0)

tree04.fit(x_train,y_train)

tree04.score(x_train,y_train)

tree04.score(x_test,y_test)

#針對決策樹缺點的集成