我如何处理多类决策树？答案

【问题标题】：how to i handle a multiclass decision tree?我如何处理多类决策树？
【发布时间】：2020-10-17 02:51:25
【问题描述】：

我是 python 和 ML 的新手，但我正在尝试使用 sklearn 来构建决策树。我有许多分类特征，我已将它们转换为数值变量。但是，我的目标功能是一个多类，我遇到了一个错误。我应该如何处理多类目标？

ValueError：目标是多类但平均值='二进制'。请选择另一个平均设置，[None, 'micro', 'macro', 'weighted'] 之一。

from sklearn.model_selection import train_test_split

#SPLIT DATA INTO TRAIN AND TEST SET
X_train, X_test, y_train, y_test = train_test_split(X, y, 
                                                    test_size =0.30, #by default is 75%-25%
                                                    #shuffle is set True by default,
                                                    stratify=y, #preserve target propotions 
                                                    random_state= 123) #fix random seed for replicability

print(X_train.shape, X_test.shape)


from sklearn.tree import DecisionTreeClassifier
model = DecisionTreeClassifier(criterion='gini', max_depth=3, min_samples_split=4, min_samples_leaf=2)

model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# criterion : "gini", "entropy"
# max_depth : The maximum depth of the tree.
# min_samples_split : The minimum number of samples required to split an internal node:
# min_samples_leaf : The minimum number of samples required to be at a leaf node. 

#DEFINE YOUR CLASSIFIER and THE PARAMETERS GRID
from sklearn.tree import DecisionTreeClassifier
import numpy as np

classifier = DecisionTreeClassifier()
parameters = {'criterion': ['entropy','gini'], 
              'max_depth': [3,4,5],
              'min_samples_split': [5,10],
              'min_samples_leaf': [2]}

from sklearn.model_selection import GridSearchCV
gs = GridSearchCV(classifier, parameters, cv=3, scoring = 'f1', verbose=50, n_jobs=-1, refit=True)

enter image description here

【问题讨论】：

标签： python machine-learning decision-tree sklearn-pandas gridsearchcv

【解决方案1】：

您应该手动指定分数函数：

from sklearn.metrics import f1_score, make_scorer

f1 = make_scorer(f1_score, average='weighted')

....

gs = GridSearchCV(classifier, parameters, cv=3, scoring=f1, verbose=50, n_jobs=-1, refit=True)

【讨论】：

感谢您的建议，我刚刚尝试了同样的错误。
我刚刚调整了我的代码示例。可以试试吗？

【解决方案2】：

非常感谢您的帮助。我想到了。它实际上在gs线上。在得分方面，我需要调整你提到的内容。所以我修改了评分 = f1_macro

gs = GridSearchCV(classifier, parameters, cv=3, scoring=f1_macro, verbose=50, n_jobs=-1, refit=True)

【讨论】：

不客气！如果将答案标记为解决方案，我将不胜感激。