随机森林特征重要性

代码：

import numpy as np
from sklearn.ensemble import RandomForestClassifier
 
data = np.random.random((100,10))
lanel = np.zeros((100))
lanel[25:50] = 1
lanel[50:75] = 2
lanel[75:] = 3
 
model = RandomForestClassifier(max_depth=None,n_estimators=1000,
                               criterion='gini',class_weight="balanced")
model.fit(data,lanel)
train_score = model.score(data,lanel)
print('train_score: ', train_score)
 
# 特征重要性
feature_impotant = model.feature_importances_
print(feature_impotant)
 

train_score:  1.0
0.9999999999999998
'
运行
运行

更直观的演示：

from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
 
iris = load_iris()
X, y = iris.data, iris.target
 
rfc = RandomForestClassifier(n_estimators=100, random_state=42)
rfc.fit(X, y)
 
importances = rfc.feature_importances_
 
indices = sorted(range(len(importances)), key=lambda i: importances[i], reverse=True)
 
print("Feature ranking:")
for f in range(X.shape[1]):
    print(f"{f+1}. {iris.feature_names[indices[f]]}: {importances[indices[f]]}")

Feature ranking:
1. petal length (cm): 0.4361295069034437
2. petal width (cm): 0.43606478004168353
3. sepal length (cm): 0.10612761987750428
4. sepal width (cm): 0.02167809317736852