L5打卡学习笔记
- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊
决策树模型
- 导入数据
- 模型训练
- 模型预测
- 个人总结
导入数据
import pandas as pd
import numpy as npurl = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
names = ['花萼-length', '花萼-width', '花瓣-length', '花瓣-width', 'class']dataset = pd.read_csv(url, names=names)
dataset
| 花萼-length | 花萼-width | 花瓣-length | 花瓣-width | class | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
| ... | ... | ... | ... | ... | ... |
| 145 | 6.7 | 3.0 | 5.2 | 2.3 | Iris-virginica |
| 146 | 6.3 | 2.5 | 5.0 | 1.9 | Iris-virginica |
| 147 | 6.5 | 3.0 | 5.2 | 2.0 | Iris-virginica |
| 148 | 6.2 | 3.4 | 5.4 | 2.3 | Iris-virginica |
| 149 | 5.9 | 3.0 | 5.1 | 1.8 | Iris-virginica |
150 rows × 5 columns
# 数据划分
X = dataset.iloc[ : ,[0,1,2,3]].values #可选择部分列作为分类标准
Y = dataset.iloc[ : , 4].values
X,Y
(array([[5.1, 3.5, 1.4, 0.2],[4.9, 3. , 1.4, 0.2],[4.7, 3.2, 1.3, 0.2],[4.6, 3.1, 1.5, 0.2],[5. , 3.6, 1.4, 0.2],[5.4, 3.9, 1.7, 0.4],[4.6, 3.4, 1.4, 0.3],[5. , 3.4, 1.5, 0.2],[4.4, 2.9, 1.4, 0.2],[4.9, 3.1, 1.5, 0.1],[5.4, 3.7, 1.5, 0.2],[4.8, 3.4, 1.6, 0.2],[4.8, 3. , 1.4, 0.1],[4.3, 3. , 1.1, 0.1],[5.8, 4. , 1.2, 0.2],[5.7, 4.4, 1.5, 0.4],[5.4, 3.9, 1.3, 0.4],[5.1, 3.5, 1.4, 0.3],[5.7, 3.8, 1.7, 0.3],[5.1, 3.8, 1.5, 0.3],[5.4, 3.4, 1.7, 0.2],[5.1, 3.7, 1.5, 0.4],[4.6, 3.6, 1. , 0.2],[5.1, 3.3, 1.7, 0.5],[4.8, 3.4, 1.9, 0.2],[5. , 3. , 1.6, 0.2],[5. , 3.4, 1.6, 0.4],[5.2, 3.5, 1.5, 0.2],[5.2, 3.4, 1.4, 0.2],[4.7, 3.2, 1.6, 0.2],[4.8, 3.1, 1.6, 0.2],[5.4, 3.4, 1.5, 0.4],[5.2, 4.1, 1.5, 0.1],[5.5, 4.2, 1.4, 0.2],[4.9, 3.1, 1.5, 0.1],[5. , 3.2, 1.2, 0.2],[5.5, 3.5, 1.3, 0.2],[4.9, 3.1, 1.5, 0.1],[4.4, 3. , 1.3, 0.2],[5.1, 3.4, 1.5, 0.2],[5. , 3.5, 1.3, 0.3],[4.5, 2.3, 1.3, 0.3],[4.4, 3.2, 1.3, 0.2],[5. , 3.5, 1.6, 0.6],[5.1, 3.8, 1.9, 0.4],[4.8, 3. , 1.4, 0.3],[5.1, 3.8, 1.6, 0.2],[4.6, 3.2, 1.4, 0.2],[5.3, 3.7, 1.5, 0.2],[5. , 3.3, 1.4, 0.2],[7. , 3.2, 4.7, 1.4],[6.4, 3.2, 4.5, 1.5],[6.9, 3.1, 4.9, 1.5],[5.5, 2.3, 4. , 1.3],[6.5, 2.8, 4.6, 1.5],[5.7, 2.8, 4.5, 1.3],[6.3, 3.3, 4.7, 1.6],[4.9, 2.4, 3.3, 1. ],[6.6, 2.9, 4.6, 1.3],[5.2, 2.7, 3.9, 1.4],[5. , 2. , 3.5, 1. ],[5.9, 3. , 4.2, 1.5],[6. , 2.2, 4. , 1. ],[6.1, 2.9, 4.7, 1.4],[5.6, 2.9, 3.6, 1.3],[6.7, 3.1, 4.4, 1.4],[5.6, 3. , 4.5, 1.5],[5.8, 2.7, 4.1, 1. ],[6.2, 2.2, 4.5, 1.5],[5.6, 2.5, 3.9, 1.1],[5.9, 3.2, 4.8, 1.8],[6.1, 2.8, 4. , 1.3],[6.3, 2.5, 4.9, 1.5],[6.1, 2.8, 4.7, 1.2],[6.4, 2.9, 4.3, 1.3],[6.6, 3. , 4.4, 1.4],[6.8, 2.8, 4.8, 1.4],[6.7, 3. , 5. , 1.7],[6. , 2.9, 4.5, 1.5],[5.7, 2.6, 3.5, 1. ],[5.5, 2.4, 3.8, 1.1],[5.5, 2.4, 3.7, 1. ],[5.8, 2.7, 3.9, 1.2],[6. , 2.7, 5.1, 1.6],[5.4, 3. , 4.5, 1.5],[6. , 3.4, 4.5, 1.6],[6.7, 3.1, 4.7, 1.5],[6.3, 2.3, 4.4, 1.3],[5.6, 3. , 4.1, 1.3],[5.5, 2.5, 4. , 1.3],[5.5, 2.6, 4.4, 1.2],[6.1, 3. , 4.6, 1.4],[5.8, 2.6, 4. , 1.2],[5. , 2.3, 3.3, 1. ],[5.6, 2.7, 4.2, 1.3],[5.7, 3. , 4.2, 1.2],[5.7, 2.9, 4.2, 1.3],[6.2, 2.9, 4.3, 1.3],[5.1, 2.5, 3. , 1.1],[5.7, 2.8, 4.1, 1.3],[6.3, 3.3, 6. , 2.5],[5.8, 2.7, 5.1, 1.9],[7.1, 3. , 5.9, 2.1],[6.3, 2.9, 5.6, 1.8],[6.5, 3. , 5.8, 2.2],[7.6, 3. , 6.6, 2.1],[4.9, 2.5, 4.5, 1.7],[7.3, 2.9, 6.3, 1.8],[6.7, 2.5, 5.8, 1.8],[7.2, 3.6, 6.1, 2.5],[6.5, 3.2, 5.1, 2. ],[6.4, 2.7, 5.3, 1.9],[6.8, 3. , 5.5, 2.1],[5.7, 2.5, 5. , 2. ],[5.8, 2.8, 5.1, 2.4],[6.4, 3.2, 5.3, 2.3],[6.5, 3. , 5.5, 1.8],[7.7, 3.8, 6.7, 2.2],[7.7, 2.6, 6.9, 2.3],[6. , 2.2, 5. , 1.5],[6.9, 3.2, 5.7, 2.3],[5.6, 2.8, 4.9, 2. ],[7.7, 2.8, 6.7, 2. ],[6.3, 2.7, 4.9, 1.8],[6.7, 3.3, 5.7, 2.1],[7.2, 3.2, 6. , 1.8],[6.2, 2.8, 4.8, 1.8],[6.1, 3. , 4.9, 1.8],[6.4, 2.8, 5.6, 2.1],[7.2, 3. , 5.8, 1.6],[7.4, 2.8, 6.1, 1.9],[7.9, 3.8, 6.4, 2. ],[6.4, 2.8, 5.6, 2.2],[6.3, 2.8, 5.1, 1.5],[6.1, 2.6, 5.6, 1.4],[7.7, 3. , 6.1, 2.3],[6.3, 3.4, 5.6, 2.4],[6.4, 3.1, 5.5, 1.8],[6. , 3. , 4.8, 1.8],[6.9, 3.1, 5.4, 2.1],[6.7, 3.1, 5.6, 2.4],[6.9, 3.1, 5.1, 2.3],[5.8, 2.7, 5.1, 1.9],[6.8, 3.2, 5.9, 2.3],[6.7, 3.3, 5.7, 2.5],[6.7, 3. , 5.2, 2.3],[6.3, 2.5, 5. , 1.9],[6.5, 3. , 5.2, 2. ],[6.2, 3.4, 5.4, 2.3],[5.9, 3. , 5.1, 1.8]]),array(['Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-setosa', 'Iris-setosa','Iris-setosa', 'Iris-setosa', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-versicolor', 'Iris-versicolor', 'Iris-versicolor','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica', 'Iris-virginica','Iris-virginica', 'Iris-virginica'], dtype=object))
模型训练
- DecisionTreeClassifier实际上是基于 CART 算法实现的，默认使用基尼不纯度作为分裂准则。
- 基尼指数是用于衡量样本集合中类别的不纯度（或混合程度）的指标。其取值范围在 0 到 1 之间：0 表示完全纯净，即数据集中所有样本都属于同一类别。1 表示完全不纯，即数据集样本均匀分布在所有类别中
from sklearn import tree
from sklearn.datasets import load_irisclf = tree.DecisionTreeClassifier() # sk-learn的决策树模型
clf = clf.fit(X, Y) # 用数据训练树模型构建()
r = tree.export_text(clf)
模型预测
text_x = X[[0,1,2,3,4,5], :]
pred_target_prob = clf.predict_proba(text_x) # 预测类别概率
pred_target = clf.predict(text_x) # 预测类别
# 打印结果
print("\n===模型======")
print(r)
print("\n===测试数据：=====")
print(text_x)
print("\n===预测所属类别概率：=====")
print(pred_target_prob)
print("\n===预测所属类别：======")
print(pred_target)
===模型======
|--- feature_2 <= 2.45
| |--- class: Iris-setosa
|--- feature_2 > 2.45
| |--- feature_3 <= 1.75
| | |--- feature_2 <= 4.95
| | | |--- feature_3 <= 1.65
| | | | |--- class: Iris-versicolor
| | | |--- feature_3 > 1.65
| | | | |--- class: Iris-virginica
| | |--- feature_2 > 4.95
| | | |--- feature_3 <= 1.55
| | | | |--- class: Iris-virginica
| | | |--- feature_3 > 1.55
| | | | |--- feature_0 <= 6.95
| | | | | |--- class: Iris-versicolor
| | | | |--- feature_0 > 6.95
| | | | | |--- class: Iris-virginica
| |--- feature_3 > 1.75
| | |--- feature_2 <= 4.85
| | | |--- feature_0 <= 5.95
| | | | |--- class: Iris-versicolor
| | | |--- feature_0 > 5.95
| | | | |--- class: Iris-virginica
| | |--- feature_2 > 4.85
| | | |--- class: Iris-virginica===测试数据：=====
[[5.1 3.5 1.4 0.2][4.9 3. 1.4 0.2][4.7 3.2 1.3 0.2][4.6 3.1 1.5 0.2][5. 3.6 1.4 0.2][5.4 3.9 1.7 0.4]]===预测所属类别概率：=====
[[1. 0. 0.][1. 0. 0.][1. 0. 0.][1. 0. 0.][1. 0. 0.][1. 0. 0.]]===预测所属类别：======
['Iris-setosa' 'Iris-setosa' 'Iris-setosa' 'Iris-setosa' 'Iris-setosa''Iris-setosa']
个人总结
- 本质上就是把输入向量的几个特征值做分类后按照影响因子排序后，作为逐层分类标准，影响因子大的排前面，例如花萼-length的影响最大的化 那么第一次就按这个参数分类，以此类推