1、xgboost安装
xgboost是eXtreme Gradient Boosting(极限提升树),由陈天奇提出,因性能强大,广泛应用数据挖掘中。下面介绍在python下安装xgboost包。
pip 安装
直接cmd命令行输入:
pip install xgboost
如果不行,可以尝试手动安装:
cp36代表python3.6。
下载一下安装包. 其实,numpy和scipy可以直接pip install, pip install numpy
和 pip install scipy
,主要下载xgboost安装包就行。
numpy-1.13.1+mkl-cp36-cp36m-win_amd64.whl(如果想手动安装numpy)
scipy-0.19.1-cp36-cp36m-win_amd64.whl(如果想手动安装scipy)
xgboost-0.6-cp36-cp36m-win_amd64.whl
在这里-xgboost下载,然后在cmd,在下载文件的路径,运行:
F:\下载软件>pip install numpy-1.13.1+mkl-cp36-cp36m-win_amd64.whl
>> pip install scipy-0.19.1-cp36-cp36m-win_amd64.whl
>> pip install xgboost-0.6+20171121-cp36-cp36m-win_amd64.whl
2、xgboost调试
xgboost可以分成两种实现:1、原生接口(train);2、scikitlearn实现(fit);
xgboost处理的问题分成两种:1、分类问题;2、回归问题
导入xgboost:
import xgboost as xgb
.
2.1 Demo1 基于XGBoost原生接口的分类
xgb.train
#xgboost 分类
from sklearn.datasets import load_iris
import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
# read in the iris data
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234565)
params = {
'booster': 'gbtree',
'objective': 'multi:softmax',
'num_class': 3,
'gamma': 0.1,
'max_depth': 6,
'lambda': 2,
'subsample': 0.7,
'colsample_bytree': 0.7,
'min_child_weight': 3,
'silent': 1,
'eta': 0.1,
'seed': 1000,
'nthread': 4,
}
plst = params.items()
dtrain = xgb.DMatrix(X_train, y_train)
num_rounds = 500
model = xgb.train(plst, dtrain, num_rounds)
# 对测试集进行预测
dtest = xgb.DMatrix(X_test)
ans = model.predict(dtest)
# 计算准确率
cnt1 = 0
cnt2 = 0
for i in range(len(y_test)):
if ans[i] == y_test[i]:
cnt1 += 1
else:
cnt2 += 1
print("Accuracy: %.2f %% " % (100 * cnt1 / (cnt1 + cnt2)))
# 显示重要特征
plot_importance(model)
plt.show()
运行结果:
2.2 Demo2-基于Scikit-learn接口的分类
xgb.fit
#5.3 基于Scikit-learn接口的分类
from sklearn.datasets import load_iris
import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
# read in the iris data
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
# 训练模型
model = xgb.XGBClassifier(max_depth=5, learning_rate=0.1, n_estimators=160, silent=True, objective='multi:softmax')
model.fit(X_train, y_train)
# 对测试集进行预测
ans = model.predict(X_test)
# 计算准确率
cnt1 = 0
cnt2 = 0
for i in range(len(y_test)):
if ans[i] == y_test[i]:
cnt1 += 1
else:
cnt2 += 1
print("Accuracy: %.2f %% " % (100 * cnt1 / (cnt1 + cnt2)))
# 显示重要特征
plot_importance(model)
plt.show()
以下两个demo是回归问题的实现:
2.3 demo3-基于Scikit-learn接口的回归
xgb.fit
#5.4 基于Scikit-learn接口的回归
import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
import csv
# 读取文件原始数据
X=[]
y=[]
csvFile = open(r"G:\训练小样本3_label.csv", "r")
reader = csv.reader(csvFile)
for item in reader:
item=[float(ii) for ii in item]
X.append(item)
# 把读取的数据转化成float格式
for i in range(len(X)):
y.append(X[i].pop())
# XGBoost训练过程
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
model = xgb.XGBRegressor(max_depth=5, learning_rate=0.1, n_estimators=160, silent=True,
objective='reg:gamma')
model.fit(X_train, y_train)
# 对测试集进行预测
ans = model.predict(X_test)
# 显示重要特征
plot_importance(model)
plt.show()
2.4基于XGBoost原生接口的回归
# 5.2 基于XGBoost原生接口的回归
import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
import csv
from xgboost import XGBClassifier
X=[]
y=[]
csvFile = open(r"G:\训练小样本4large_label.csv", "r")
reader = csv.reader(csvFile)
for item in reader:
item=[float(ii) for ii in item]
X.append(item)
# 把读取的数据转化成float格式
for i in range(len(X)):
y.append(X[i].pop())
# XGBoost训练过程
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
params = {
'booster': 'gbtree',
'objective': 'reg:gamma',
'gamma': 0.1,
'max_depth': 5,
'lambda': 3,
'subsample': 0.7,
'colsample_bytree': 0.7,
'min_child_weight': 3,
'silent': 1,
'eta': 0.1,
'seed': 1000,
'nthread': 4,
}
dtrain = xgb.DMatrix(X_train, y_train)
# num_rounds = 300
num_rounds = 126
plst = params.items()
model = xgb.train(plst, dtrain, num_rounds)
# 对测试集进行预测
dtest = xgb.DMatrix(X_test)
ans = model.predict(dtest)
# 显示重要特征
plot_importance(model)
plt.show()
3、其他使用
定义model,获得gbtree.
# xgboost usage
import pandas as pd
import numpy as np
import xgboost as xgb
from sklearn.cross_validation import train_test_split
from sklearn import cross_validation
from matplotlib import pyplot as plt
from xgboost import plot_importance
train_df = pd.read_csv(r'G:\训练小样本.csv')
x_list=['210X1','220X2','310X2','311X72','261X237']
X_train = train_df[x_list].values
y_train = train_df.Y.values
X_dtrain, X_deval, y_dtrain, y_deval = cross_validation.train_test_split(X_train, y_train, random_state=1026, test_size=0.3)
dtrain = xgb.DMatrix(X_dtrain, y_dtrain)
deval = xgb.DMatrix(X_deval, y_deval)
watchlist = [(deval, 'eval')]
params = {
'booster': 'gbtree',
'objective': 'reg:linear',
'subsample': 0.8,
'colsample_bytree': 0.85,
'eta': 0.05,
'max_depth': 7,
'seed': 2016,
'silent': 0,
'eval_metric': 'rmse'
}
df_test=[100,1.5,1.5,90,95]
clf = xgb.train(params, dtrain, 50, watchlist, early_stopping_rounds=50)
pred = clf.predict(xgb.DMatrix(df_test))
# 显示重要特征
plot_importance(clf)
plt.show()
最近开通了个公众号,主要分享python学习相关内容,推荐系统,风控等算法相关的内容,感兴趣的伙伴可以关注下。
公众号相关的学习资料会上传到QQ群596506387,欢迎关注。
参考: