由于lgbm.predict_proba输出的结果维度和样本的数据集不一致，导致dataframe进行列赋值的时候报错，下面可以通过修改num_class来验证
# -*- coding: utf-8 -*-
"""
@Time : 2022/7/29 14:48
@Author: Breeze
@File : 多分类测试输出.py
"""
import sys
from lightgbm import LGBMClassifier
import numpy as np
import os
print(sys.version)
clf_multiclass = LGBMClassifier()
n_estimators = 100
lr = 0.01
max_depth = 3
l1 = 0.1
l2 = 0.1
subsample_for_bin = 32
min_child_sample = 32
num_class = 3
wd_namelist_model = LGBMClassifier(
objective='multiclass', # 'multilogloss
num_class=num_class, # 'regression' for LGBMRegressor, 'binary' or 'multiclass' for LGBMClassifier, 'lambdarank' for LGBMRanker.
n_estimators=n_estimators,
learning_rate=lr,
num_leaves=2**max_depth-1, # (0, 2^max_depth - 1]
colsample_bytree=0.6,
subsample=0.6,
max_depth=max_depth, # 10
reg_alpha=l1, # 0.04
reg_lambda=l2,
subsample_for_bin=subsample_for_bin,
subsample_freq=32, # 12
min_split_gain=0.01,
min_child_weight=0.01,
min_child_sample=min_child_sample,
silent=False,
verbose=1,
# importance_type='gain',
random_state=2022)
train_data = np.random.rand(50000, 100) # 500 entities, each contains 100 features
train_label = np.random.randint(num_class, size=50000) # 5 targets
val_data = np.random.rand(5000, 100)
val_label = np.random.randint(num_class, size=5000)
# wd_namelist_model.fit(train_data,train_label)
wd_namelist_model.fit(train_data, train_label
# , sample_weight=train_weight
, eval_set=[(train_data, train_label),(val_data, val_label)]
# , eval_sample_weight=[train_weight, val_weight]
# , eval_metric=['auc']
, eval_metric=['auc_mu'] # binary_logloss multi_logloss,cross_entropy
, verbose=10
, early_stopping_rounds=50)
# val_pred = wd_namelist_model.predict(val_data)
val_pred = wd_namelist_model.predict_proba(val_data)# [0,:]
print(val_pred.shape)
如果想要用多分类，来训练二分类目标变量，可以通过如下方法获取概率值
wd_namelist_model.predict_proba(val_data)[0,:len(val_data)]
