如何在python中的多类分类问题上获取每个类的SHAP值

Question

我有以下数据框：

import pandas as pd
import random

import xgboost
import shap

foo = pd.DataFrame({'id':[1,2,3,4,5,6,7,8,9,10],
                   'var1':random.sample(range(1, 100), 10),
                   'var2':random.sample(range(1, 100), 10),
                   'var3':random.sample(range(1, 100), 10),
                   'class': ['a','a','a','a','a','b','b','c','c','c']})

我想为此运行分类算法以预测 3 classes

因此，我将数据集拆分为训练和测试，然后运行 ​​xgboost

cl_cols = foo.filter(regex='var').columns
X_train, X_test, y_train, y_test = train_test_split(foo[cl_cols],
                                                        foo[['class']],
                                                        test_size=0.33, random_state=42)


model = xgboost.XGBClassifier(objective="binary:logistic")
model.fit(X_train, y_train)

现在我想获得平均 SHAP 值每个班级

以下代码产生了我想要的，但它使用绝对SHAP 值以计算平均值，但我只需要平均值

shap_values = shap.TreeExplainer(model).shap_values(X_test)
shap.summary_plot(shap_values, X_test)

此外，该图将class 标记为 0、1、2。我怎么知道 0,1 & 2 对应于原始的哪个class？

因为这段代码：

shap.summary_plot(shap_values, X_test,
                 class_names= ['a', 'b', 'c'])

给

和这段代码

shap.summary_plot(shap_values, X_test,
                 class_names= ['b', 'c', 'a'])

给

所以我不再确定这个传说了。 有任何想法吗 ？

Answer 1

我有同样的问题，也许这个问题可以帮助：https://github.com/slundberg/shap/issues/764

我还没有测试过，但似乎顺序应该与调用model.predict_proba() 时的顺序相同。在上面的链接中，建议使用摘要图的class_names=model.classes_ 选项。

Answer 2

通过做一些研究并在this post 和@Alessandro Nesti 的回答的帮助下，这是我的解决方案：

foo = pd.DataFrame({'id':[1,2,3,4,5,6,7,8,9,10],
                   'var1':random.sample(range(1, 100), 10),
                   'var2':random.sample(range(1, 100), 10),
                   'var3':random.sample(range(1, 100), 10),
                   'class': ['a','a','a','a','a','b','b','c','c','c']})

cl_cols = foo.filter(regex='var').columns
X_train, X_test, y_train, y_test = train_test_split(foo[cl_cols],
                                                        foo[['class']],
                                                        test_size=0.33, random_state=42)


model = xgboost.XGBClassifier(objective="multi:softmax")
model.fit(X_train, y_train)

def get_ABS_SHAP(df_shap,df):
    #import matplotlib as plt
    # Make a copy of the input data
    shap_v = pd.DataFrame(df_shap)
    feature_list = df.columns
    shap_v.columns = feature_list
    df_v = df.copy().reset_index().drop('index',axis=1)
    
    # Determine the correlation in order to plot with different colors
    corr_list = list()
    for i in feature_list:
        b = np.corrcoef(shap_v[i],df_v[i])[1][0]
        corr_list.append(b)
    corr_df = pd.concat([pd.Series(feature_list),pd.Series(corr_list)],axis=1).fillna(0)
 
    # Make a data frame. Column 1 is the feature, and Column 2 is the correlation coefficient
    corr_df.columns  = ['Variable','Corr']
    corr_df['Sign'] = np.where(corr_df['Corr']>0,'red','blue')
    
    shap_abs = np.abs(shap_v)
    k=pd.DataFrame(shap_abs.mean()).reset_index()
    k.columns = ['Variable','SHAP_abs']
    k2 = k.merge(corr_df,left_on = 'Variable',right_on='Variable',how='inner')
    k2 = k2.sort_values(by='SHAP_abs',ascending = True)
    
    k2_f = k2[['Variable', 'SHAP_abs', 'Corr']]
    k2_f['SHAP_abs'] = k2_f['SHAP_abs'] * np.sign(k2_f['Corr'])
    k2_f.drop(columns='Corr', inplace=True)
    k2_f.rename(columns={'SHAP_abs': 'SHAP'}, inplace=True)
    
    return k2_f

foo_all = pd.DataFrame()

for k,v in list(enumerate(model.classes_)):

    foo = get_ABS_SHAP(shap_values[k], X_test)
    foo['class'] = v
    foo_all = pd.concat([foo_all,foo])

import plotly_express as px
px.bar(foo_all,x='SHAP', y='Variable', color='class')

这导致

Answer 3

SHAP 值作为列表返回。您可以通过它们的索引访问相关的 SHAP 绝对值。

对于 0 类的摘要图，代码为

shap.summary_plot(shap_values[0], X_test)

Answer 4

这是@quant的代码的更新代码：

import pandas as pd
import random

import numpy as np

import xgboost
import shap

from sklearn.model_selection import train_test_split

import plotly_express as px


foo = pd.DataFrame({'id':[1,2,3,4,5,6,7,8,9,10],
                   'var1':random.sample(range(1, 100), 10),
                   'var2':random.sample(range(1, 100), 10),
                   'var3':random.sample(range(1, 100), 10),
                   'class': ['a','a','a','a','a','b','b','c','c','c']})

foo['class'], _ = pd.factorize(foo['class'], sort = True)

cl_cols = foo.filter(regex='var').columns
X_train, X_test, y_train, y_test = train_test_split(foo[cl_cols],
                                                        foo[['class']],
                                                        test_size=0.33, random_state=42)

model = xgboost.XGBClassifier(objective="multi:softmax")
model.fit(X_train, y_train)

shap_values = shap.TreeExplainer(model).shap_values(X_test)







def get_ABS_SHAP(df_shap,df):
    #import matplotlib as plt
    # Make a copy of the input data
    shap_v = pd.DataFrame(df_shap)
    feature_list = df.columns
    shap_v.columns = feature_list
    df_v = df.copy().reset_index().drop('index',axis=1)
    
    # Determine the correlation in order to plot with different colors
    corr_list = list()
    for i in feature_list:
        b = np.corrcoef(shap_v[i],df_v[i])[1][0]
        corr_list.append(b)
    corr_df = pd.concat([pd.Series(feature_list),pd.Series(corr_list)],axis=1).fillna(0)
 
    # Make a data frame. Column 1 is the feature, and Column 2 is the correlation coefficient
    corr_df.columns  = ['Variable','Corr']
    corr_df['Sign'] = np.where(corr_df['Corr']>0,'red','blue')
    
    shap_abs = np.abs(shap_v)
    k=pd.DataFrame(shap_abs.mean()).reset_index()
    k.columns = ['Variable','SHAP_abs']
    k2 = k.merge(corr_df,left_on = 'Variable',right_on='Variable',how='inner')
    k2 = k2.sort_values(by='SHAP_abs',ascending = True)
    
    k2_f = k2[['Variable', 'SHAP_abs', 'Corr']]
    k2_f['SHAP_abs'] = k2_f['SHAP_abs'] * np.sign(k2_f['Corr'])
    k2_f.drop(columns='Corr', inplace=True)
    k2_f.rename(columns={'SHAP_abs': 'SHAP'}, inplace=True)
    
    return k2_f

foo_all = pd.DataFrame()

for k,v in list(enumerate(model.classes_)):

    foo = get_ABS_SHAP(shap_values[k], X_test)
    foo['class'] = v
    foo_all = pd.concat([foo_all,foo])

px.bar(foo_all,x='SHAP', y='Variable', color='class')