文章目录
1.XGBoost简介
2.Kaggle简介
Kaggle是一个数据分析的竞赛平台,网址为:https://www.kaggle.com/
3.数据预处理-清洗
特征:重要性高,缺失率低
策略:通过计算进行补充;通过经验或业务知识估计
特征:重要性高,缺失率高
策略:尝试从其他渠道取书补全;使用其他字段通过数字获取;去除字段,并在字段中标明
特征:重要性低,缺失率低
策略:不做处理或简单填充
特征:重要性低,缺失率高
策略:去除该字段
4.案例部分
1)判断蘑菇是否有毒-二分类
# 判断蘑菇是否有毒-二分类
import xgboost as xgb
# 1、xgBoost的基本使用
# 2、binary:logistic/logitraw
if __name__ == "__main__":
# 读取数据,使用XGBoost中的数据结构DMatrix;XGBoost可以加载libsvm格式的文本数据,格式为稀疏特征
data_train = xgb.DMatrix('agaricus_train.txt')
data_test = xgb.DMatrix('agaricus_test.txt')
print(data_train) # <xgboost.core.DMatrix object at 0x000001C5C38ACBA8>
print(type(data_train)) # <class 'xgboost.core.DMatrix'>
# 设置参数
# 'max_depth': 3表示每一棵树的最大深度是3
# 'eta': 1表示衰减因子为1,即为原始模型,没有防止过拟合
# 'silent': 1输出生成树的过程,表示输出值不要输出过多的信息;=0时,可以输出过多信息
# 'objective': 'binary:logistic'这个问题本质上是二分类问题,故可以使用logistic回归
param = {
'max_depth': 3, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}
# param = {'max_depth': 3, 'eta': 0.3, 'silent': 1, 'objective': 'reg:logistic'}
watchlist = [(data_test, 'eval'), (data_train, 'train')]
# 迭代7轮,得到7棵树
n_round = 7
# 相当于之前的fit
# 参数设置
# param是一个字典,里面包含着训练中的参数关键字和对应的值
# data_train是训练数据
# num_boost_round 是指提升迭代的个数
# evals是一个列表,用于对训练过程中进行评估列表中的元素,形式是evals = [(dtrain,’train’),(dval,’val’)]
# 它使得我们可以在训练过程中观察验证集的效果
# obj表示自定义损失函数
# feval表示自定义评估函数-错误率
bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist)
# 计算错误率
y_hat = bst.predict(data_test)
y = data_test.get_label()
print(y_hat)
print(y)
error = sum(y != (y_hat > 0.5))
error_rate = float(error) / len(y_hat)
print('样本总数:\t', len(y_hat))
print('错误数目:\t%4d' % error)
print('错误率:\t%.5f%%' % (100*error_rate))
[0] eval-error:0.01614 train-error:0.01443
[1] eval-error:0.00000 train-error:0.00123
[2] eval-error:0.00000 train-error:0.00000
[3] eval-error:0.00000 train-error:0.00000
[4] eval-error:0.00000 train-error:0.00000
[5] eval-error:0.00000 train-error:0.00000
[6] eval-error:0.00000 train-error:0.00000
[0.0013066 0.9952118 0.0013066 ... 0.99917597 0.00155224 0.998858 ]
[0. 1. 0. ... 1. 0. 1.]
样本总数: 1611
错误数目: 0
错误率: 0.00000%
2)判断蘑菇是否有毒-手动读取数据
import numpy as np
import scipy.sparse
# 判断蘑菇是否有毒---手动读取数据
import xgboost as xgb
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
# 手动读取数据
def read_data(path):
y = [] # 标签值
row = [] # 存储相应的行
col = [] # 存储相应的列
values = [] # 存储相应的值,row,col,values的值一一对应
r = 0 # 首行
for d in open(path):
# 以空格分开
d = d.strip().split()
# 第0列给y
y.append(int(d[0]))
# 第一列后面的数都给d
d = d[1:]
# 遍历每一个d
for c in d:
# 以':'进行拆分,前面的是key,后面的是value
key, value = c.split(':')
# 对应的第几行放入 row中
row.append(r)
# 列中加入相应的key
col.append(int(key))
# 添加相应的值
values.append(float(value))
# 一行处理完r加1
r += 1
# 创建稀疏矩阵,(row,col)的位置赋值成相应的值
x = scipy.sparse.csr_matrix((values, (row, col))).toarray()
y = np.array(y)
return x, y
if __name__ == '__main__':
x, y = read_data('agaricus_train.txt')
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.6)
# Logistic回归
lr = LogisticRegression(penalty='l2')
lr.fit(x_train, y_train.ravel())
y_hat = lr.predict(x_test)
print('Logistic回归正确率:', accuracy_score(y_test, y_hat))
# XGBoost
data_train = xgb.DMatrix(x_train, label=y_train)
data_test = xgb.DMatrix(x_test, label=y_test)
watch_list = [(data_test, 'eval'), (data_train, 'train')]
param = {
'max_depth': 3, 'eta': 1, 'silent': 0, 'objective': 'multi:softmax', 'num_class': 3}
bst = xgb.train(param, data_train, num_boost_round=4, evals=watch_list)
y_hat = bst.predict(data_test)
print('XGBoost正确率:', accuracy_score(y_test, y_hat))
Logistic回归正确率: 1.0
[0] eval-merror:0.03569 train-merror:0.04070
[1] eval-merror:0.00729 train-merror:0.00998
[2] eval-merror:0.00077 train-merror:0.00051
[3] eval-merror:0.00077 train-merror:0.00051
XGBoost正确率: 0.9992325402916347
3)鸢尾花数据集-多分类
# 鸢尾花数据分类-多分类
import numpy as np
import pandas as pd
import xgboost as xgb
from sklearn.model_selection import train_test_split # cross_validation
from sklearn.linear_model import LogisticRegressionCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
def iris_type(s):
it = {
'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
return it[s]
if __name__ == "__main__":
path = u'iris.data' # 数据文件路径
# data = np.loadtxt(path, dtype=float, delimiter=',', converters={4: iris_type})
data = pd.read_csv(path, header=None)
# print(data)
# 特征值与目标值
x, y = data[range(4)], data[4]
# y本质上是字符串,转变成类别数据后,再转换成编码012
y = pd.Categorical(y).codes
# print(y)
# 数据集的分割-训练集与测试集
x_train, x_test, y_train, y_test = train_test_split(x,