其他
决策树、随机森林可视化
The following article is from pythonic生物人 Author pythonic生物人
图怎么看：每一种颜色代表一个class，link的宽度表示从一个节点流向另一个节点的items数量。
安装
依赖pygraphviz，
pip install pybaobabdt
pip install pygraphviz
可视化决策树
import pybaobabdt
import pandas as pd
from scipy.io import arff
from sklearn.tree import DecisionTreeClassifier #导入决策树算法
data = arff.loadarff('winequality-red.arff')
df = pd.DataFrame(data[0])
y = list(df['class'])
features = list(df.columns)
features.remove('class')
X = df.loc[:, features]
clf = DecisionTreeClassifier().fit(X, y)
ax = pybaobabdt.drawTree(clf, size=10, dpi=300, features=features) #可视化主函数pybaobabdt.drawTree
可视化决策树-设置树深度
通过maxdepth限制需要渲染的树深度，对large trees特别友好，
ax = pybaobabdt.drawTree(
clf,
size=10,
dpi=100,
maxdepth=6, #设置渲染的树的最大深度
features=features)
可视化决策树-突出class
通过colormap凸显感兴趣的class，
from matplotlib.colors import ListedColormap
ax = pybaobabdt.drawTree(
clf,
size=10,
dpi=600,
colormap=ListedColormap(["#01a2d9", "gray", "#d5695d",
"gray"]), #通过颜色突出展示class 5和6 变量
features=features)
可视化随机森林
import pybaobabdt
import pandas as pd
from scipy.io import arff
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier #导入随机森林算法
data = arff.loadarff('vehicle.arff')
df = pd.DataFrame(data[0])
y = list(df['class'])
features = list(df.columns)
features.remove('class')
X = df.loc[:, features]
clf = RandomForestClassifier(n_estimators=20, n_jobs=-1, random_state=0)
clf.fit(X, y)
size = (15, 15)
plt.rcParams['figure.figsize'] = size
fig = plt.figure(figsize=size, dpi=300)
for idx, tree in enumerate(clf.estimators_):
ax1 = fig.add_subplot(5, 4, idx + 1)
pybaobabdt.drawTree(tree,
model=clf,
size=15,
dpi=300,
maxdepth=8,
features=features,
ax=ax1)
参考：https://pypi.org/project/pybaobabdt/>