小伙伴们大家好~o(￣▽￣)ブ，首先声明一下，我的开发环境是Jupyter lab，所用的库和版本大家参考：
Python 3.7.1（你的版本至少要3.4以上
Scikit-learn 0.20.0 （你的版本至少要0.20
Graphviz 0.8.4 (没有画不出决策树哦，安装代码conda install python-graphviz
Numpy 1.15.3, Pandas 0.23.4, Matplotlib 3.0.1, SciPy 1.1.0
用SKlearn 建立一棵决策树
这里采用的数据集是SKlearn中的红酒数据集。
1 导入需要的算法库和模块
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n11" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">from sklearn import tree #导入tree模块
from sklearn.datasets import load_wine #导入红酒数据集
from sklearn.model_selection import train_test_split #导入训练集和测试集切分包</pre>
2 探索数据
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="python " contenteditable="true" cid="n13" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">wine = load_wine()
wine.data
wine.data.shape
wine.target
wine.target.shape</pre>
运行的结果是这样子的：
data就是该数据集的特征矩阵，从运行结果可以看出，该红酒数据集一共有178条记录，13个特征。
特征矩阵中有178条记录，相对应的标签Y就有178个数据。
如果wine是一张表，应该长这样：
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n20" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">import pandas as pd
pd.concat([pd.DataFrame(wine.data),pd.DataFrame(wine.target)],axis=1)</pre>
这是数据集特征列名和标签分类
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="python" contenteditable="true" cid="n23" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">wine.feature_names
wine.target_names</pre>
3 分训练集和测试集
这里选取30%作为测试集。切分好之后，训练集有124条数据，测试集有54条数据。
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n28" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
Xtrain.shape
Xtest.shape</pre>
4 建立模型
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n32" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">clf = tree.DecisionTreeClassifier(criterion="entropy") #初始化树模型
clf = clf.fit(Xtrain, Ytrain) #实例化训练集
score = clf.score(Xtest, Ytest) #返回预测的准确度
?
score</pre>
5 画出一棵树吧
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n36" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">feature_name = ['酒精','苹果酸','灰','灰的碱性','镁','总酚','类黄酮','非黄烷类酚类','花青素','颜色强度','色调','od280/od315稀释葡萄酒','脯氨酸']
?
import graphviz
dot_data = tree.export_graphviz(clf
,out_file=None
,feature_names= feature_name
,class_names=["琴酒","雪莉","贝尔摩德"]
,filled=True
,rounded=True
)
graph = graphviz.Source(dot_data)
graph</pre>
6 探索决策树
<pre spellcheck="false" class="md-fences md-end-block ty-contain-cm modeLoaded" lang="Python" contenteditable="true" cid="n40" mdtype="fences" style="box-sizing: border-box; overflow: visible; font-family: var(--monospace); font-size: 0.9em; display: block; break-inside: avoid; text-align: left; white-space: normal; background-image: inherit; background-position: inherit; background-size: inherit; background-repeat: inherit; background-attachment: inherit; background-origin: inherit; background-clip: inherit; background-color: rgb(248, 248, 248); position: relative !important; border: 1px solid rgb(231, 234, 237); border-radius: 3px; padding: 8px 4px 6px; margin-bottom: 15px; margin-top: 15px; width: inherit; color: rgb(51, 51, 51); font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">#特征重要性
clf.feature_importances_
?
[*zip(feature_name,clf.feature_importances_)]</pre>
到现在为止，我们已经学会建立一棵完整的决策树了。有兴趣的话，动手建立一棵属于自己的决策树吧~