如何解决 ValueError: Target is multiclass but average='binary' in XGBoost Classifier

Question

# Importing required libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import metrics 
import warnings
warnings.filterwarnings('ignore')

# Loading data into dataframe
data = pd.read_csv("phishing.csv")
data.head()

# Dropping index column
data = data.drop(['Index'],axis = 1)

# Splitting the dataset into dependent and independent variables
X = data.drop(["class"],axis =1)
y = data["class"]

# Splitting the dataset into train and test sets: 80-20 split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 101)

# Creating holders to store the model performance results
ML_Model = []
accuracy = []
f1_score = []
recall = []
precision = []

# Function to call for storing the results
def storeResults(model, a,b,c,d):
  ML_Model.append(model)
  accuracy.append(round(a, 3))
  f1_score.append(round(b, 3))
  recall.append(round(c, 3))
  precision.append(round(d, 3))

# XGBoost Classifier Model
from xgboost import XGBClassifier

# Instantiate the model
xgb = XGBClassifier()

# Fit the model 
xgb.fit(X_train,y_train)

# Predicting the target value from the model for the samples
y_train_xgb = xgb.predict(X_train)
y_test_xgb = xgb.predict(X_test)

# Computing the accuracy, f1_score, recall, precision of the model performance
acc_train_xgb = metrics.accuracy_score(y_train,y_train_xgb)
acc_test_xgb = metrics.accuracy_score(y_test,y_test_xgb)
print("XGBoost Classifier : Accuracy on training Data: {:.3f}".format(acc_train_xgb))
print("XGBoost Classifier : Accuracy on test Data: {:.3f}".format(acc_test_xgb))
print()

f1_score_train_xgb = metrics.f1_score(y_train,y_train_xgb)
f1_score_test_xgb = metrics.f1_score(y_test,y_test_xgb)
print("XGBoost Classifier : f1_score on training Data: {:.3f}".format(f1_score_train_xgb))
print("XGBoost Classifier : f1_score on test Data: {:.3f}".format(f1_score_test_xgb))
print()

recall_score_train_xgb = metrics.recall_score(y_train,y_train_xgb)
recall_score_test_xgb = metrics.recall_score(y_test,y_test_xgb)
print("XGBoost Classifier : Recall on training Data: {:.3f}".format(recall_score_train_xgb))
print("XGBoost Classifier : Recall on test Data: {:.3f}".format(recall_score_train_xgb))
print()

precision_score_train_xgb = metrics.precision_score(y_train,y_train_xgb)
precision_score_test_xgb = metrics.precision_score(y_test,y_test_xgb)
print("XGBoost Classifier : precision on training Data: {:.3f}".format(precision_score_train_xgb))
print("XGBoost Classifier : precision on test Data: {:.3f}".format(precision_score_train_xgb))`

输出：

XGBoost Classifier : Accuracy on training Data: 0.986
XGBoost Classifier : Accuracy on test Data: 0.548

错误：

ValueError: Target is multiclass but average='binary'. Please choose another average setting, one of [None, 'micro', 'macro', 'weighted'].

如何解决这个错误得到最终的输出？

Answer 1

#computing the accuracy, f1_score, Recall, precision of the model performance

acc_train_xgb = metrics.accuracy_score(y_train,y_train_xgb)
acc_test_xgb = metrics.accuracy_score(y_test,y_test_xgb)
print("XGBoost Classifier : Accuracy on training Data: {:.3f}".format(acc_train_xgb))
print("XGBoost Classifier : Accuracy on test Data: {:.3f}".format(acc_test_xgb))
print()

f1_score_train_xgb = metrics.f1_score(y_train,y_train_xgb,average='micro')
f1_score_test_xgb = metrics.f1_score(y_test,y_test_xgb,average='micro')
print("XGBoost Classifier : f1_score on training Data: {:.3f}".format(f1_score_train_xgb))
print("XGBoost Classifier : f1_score on test Data: {:.3f}".format(f1_score_test_xgb))
print()

recall_score_train_xgb = metrics.recall_score(y_train,y_train_xgb)
recall_score_test_xgb = metrics.recall_score(y_test,y_test_xgb,average='micro')
print("XGBoost Classifier : Recall on training Data: {:.3f}".format(recall_score_train_xgb))
print("XGBoost Classifier : Recall on test Data: {:.3f}".format(recall_score_train_xgb))
print()

precision_score_train_xgb = metrics.precision_score(y_train,y_train_xgb)
precision_score_test_xgb = metrics.precision_score(y_test,y_test_xgb,average='micro')
print("XGBoost Classifier : precision on training Data: {:.3f}".format(precision_score_train_xgb))
print("XGBoost Classifier : precision on test Data: {:.3f}".format(precision_score_train_xgb))