之前写过很久了,怕新更新的xgboost不再适用,重新调试了一下代码,可运行,但数据得换成自己的,xgboost,都应该知道它的威力了,这里不再多说,欢迎一起讨论!
# coding=utf-8
import pandas as pd
import xgboost as xgb
from sklearn import metrics
import matplotlib.pylab as plt
from sklearn.model_selection import train_test_split
# 训练模型并预测出结果
def train_model(train_xy, test_xy, random_seed):
test_ID = test_xy.ID
test_y = test_xy.Kind
test_xy = test_xy.drop(['ID'], axis=1) # 去掉ID
test_xy = test_xy.drop(['Kind'], axis=1) # 去掉类标
dtest = xgb.DMatrix(test_xy)
train_y = train_xy.Kind
train_xy = train_xy.drop(['ID'], axis=1)
# train_xy = train_xy.dro