xgboost实现蘑菇数据分类预测demo

数据集下载：

训练集；测试集。

import xgboost as xgb
import numpy as np
# 自己实现loss function,softmax函数
def log_reg(y_hat, y):
	p = 1.0 / (1.0 + np.exp(-y_hat))
	g = p - y.get_label()
	h = p * (1.0 - p)
	return g, h
# 自己实现错误率计算
def error_rate(y_hat, y):
	return 'error', float(sum(y.get_label() != (y_hat > 0.5))) / len(y_hat)

if __name__ == '__main__':
	# 读取数据
	data_train = xgb.DMatrix('agaricus_train.txt')
	data_test = xgb.DMatrix('agaricus_test.txt')
	print('data_train:\n', data_train)
	print(type(data_train))

	# 设定相关参数
	param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
	# param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'reg:logistic'}
	watchlist = [(data_test, 'eval'), (data_train, 'train')]
	n_round = 10
	bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist, obj=log_reg, feval=error_rate)

	# 计算错误率
	y_hat = bst.predict(data_test)
	y = data_test.get_label()
	print('y_hat:\n', y_hat)
	print('y:\n', y)

	error = sum(y != (y_hat > 0.5))
	error_rate = float(error) / len(y_hat)

	print('total samples:%d' % len(y_hat))
	print('the wrong numbers:%d' % error)
	print('error ratio:%.3f%%' % error_rate)

我们加入logistic回归作对比：

import xgboost as xgb
import numpy as np
import pandas as pd
import scipy.sparse
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

# 自己实现loss function,softmax函数
def log_reg(y_hat, y):
	p = 1.0 / (1.0 + np.exp(-y_hat))
	g = p - y.get_label()
	h = p * (1.0 - p)
	return g, h
# 自己实现错误率计算
def error_rate(y_hat, y):
	return 'error', float(sum(y.get_label() != (y_hat > 0.5))) / len(y_hat)

def read_data(path):
	y = []
	row = []
	col = []
	values = []
	r = 0       # 首行
	for d in open(path):
		d = d.strip().split()      # 以空格分开
		y.append(int(d[0]))
		d = d[1:]
		for c in d:
			key, value = c.split(':')
			row.append(r)
			col.append(int(key))
			values.append(float(value))
		r += 1
	x = scipy.sparse.csr_matrix((values, (row, col))).toarray()
	y = np.array(y)
	return x, y

if __name__ == '__main__':
	# 读取数据
	data_train = xgb.DMatrix('agaricus_train.txt')
	data_test = xgb.DMatrix('agaricus_test.txt')
	print('data_train:\n', data_train)
	print(type(data_train))

	# 设定相关参数
	param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
	# param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'reg:logistic'}
	watchlist = [(data_test, 'eval'), (data_train, 'train')]
	n_round = 10
	bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist, obj=log_reg, feval=error_rate)

	# 计算错误率
	y_hat = bst.predict(data_test)
	y = data_test.get_label()
	print('y_hat:\n', y_hat)
	print('y:\n', y)

	error = sum(y != (y_hat > 0.5))
	error_rate = float(error) / len(y_hat)
	print('total samples:%d' % len(y_hat))
	print('the wrong numbers:%d' % error)
	print('error ratio:%.3f%%' % error_rate)
	print('logistic accuracy ratio:%.3f%%' % (1 - error_rate))
	print('=========================================')
	
	# logistic regression
	x, y = read_data('agaricus_train.txt')

	x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=1)
	lr = LogisticRegression(penalty='l2')
	lr.fit(x_train, y_train.ravel())
	y_hat = lr.predict(x_test)
	acc = y_hat.ravel() == y_test.ravel()
	print('acc:\t', acc)
	print('XGBosst accuracy:\t', float(acc.sum()) / y_hat.size)