python xgboost_机器学习集成学习之XGBoost（基于python实现）

# 引入基本工具库

import xgboost as xgb  # 引入工具库
# read in data
dtrain = xgb.DMatrix('demo/data/agaricus.txt.train')   # XGBoost的专属数据格式，但是也可以用dataframe或者ndarray
dtest = xgb.DMatrix('demo/data/agaricus.txt.test')  # # XGBoost的专属数据格式，但是也可以用dataframe或者ndarray
# specify parameters via map
param = {'max_depth':2, 'eta':1, 'objective':'binary:logistic' }    # 设置XGB的参数，使用字典形式传入
num_round = 2     # 使用线程数
bst = xgb.train(param, dtrain, num_round)   # 训练
# make prediction
preds = bst.predict(dtest)   # 预测

方式1：pip3 install xgboost
方式2：pip install xgboost

# 1.LibSVM文本格式文件
dtrain = xgb.DMatrix('train.svm.txt')
dtest = xgb.DMatrix('test.svm.buffer')
# 2.CSV文件(不能含类别文本变量，如果存在文本变量请做特征处理如one-hot)
dtrain = xgb.DMatrix('train.csv?format=csv&label_column=0')
dtest = xgb.DMatrix('test.csv?format=csv&label_column=0')
# 3.NumPy数组
data = np.random.rand(5, 10)  # 5 entities, each contains 10 features
label = np.random.randint(2, size=5)  # binary target
dtrain = xgb.DMatrix(data, label=label)
# 4.scipy.sparse数组
csr = scipy.sparse.csr_matrix((dat, (row, col)))
dtrain = xgb.DMatrix(csr)
# pandas数据框dataframe
data = pandas.DataFrame(np.arange(12).reshape((4,3)), columns=['a', 'b', 'c'])
label = pandas.DataFrame(np.random.randint(2, size=4))
dtrain = xgb.DMatrix(data, label=label)

# 1.保存DMatrix到XGBoost二进制文件中
dtrain = xgb.DMatrix('train.svm.txt')
dtrain.save_binary('train.buffer')
# 2. 缺少的值可以用DMatrix构造函数中的默认值替换：
dtrain = xgb.DMatrix(data, label=label, missing=-999.0)
# 3.可以在需要时设置权重：
w = np.random.rand(5, 1)
dtrain = xgb.DMatrix(data, label=label, missing=-999.0, weight=w)

# 加载并处理数据
df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',header=None)
df_wine.columns = ['Class label', 'Alcohol','Malic acid', 'Ash','Alcalinity of ash','Magnesium', 'Total phenols',
                   'Flavanoids', 'Nonflavanoid phenols','Proanthocyanins','Color intensity', 'Hue','OD280/OD315 of diluted wines','Proline'] 
df_wine = df_wine[df_wine['Class label'] != 1]  # drop 1 class      
y = df_wine['Class label'].values
X = df_wine[['Alcohol','OD280/OD315 of diluted wines']].values
from sklearn.model_selection import train_test_split  # 切分训练集与测试集
from sklearn.preprocessing import LabelEncoder   # 标签化分类变量
le = LabelEncoder()
y = le.fit_transform(y)
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=1,stratify=y)
dtrain = xgb.DMatrix(X_train, label=y_train)
dtest = xgb.DMatrix(X_test)
# 1.Booster 参数
params = {
    'booster': 'gbtree',
    'objective': 'multi:softmax',  # 多分类的问题
    'num_class': 10,               # 类别数，与 multisoftmax 并用
    'gamma': 0.1,                  # 用于控制是否后剪枝的参数,越大越保守，一般0.1、0.2这样子。
    'max_depth': 12,               # 构建树的深度，越大越容易过拟合
    'lambda': 2,                   # 控制模型复杂度的权重值的L2正则化项参数，参数越大，模型越不容易过拟合。
    'subsample': 0.7,              # 随机采样训练样本
    'colsample_bytree': 0.7,       # 生成树时进行的列采样
    'min_child_weight': 3,
    'silent': 1,                   # 设置成1则没有运行信息输出，最好是设置为0.
    'eta': 0.007,                  # 如同学习率
    'seed': 1000,
    'nthread': 4,                  # cpu 线程数
    'eval_metric':'auc'
}
plst = params.items()
# evallist = [(dtest, 'eval'), (dtrain, 'train')]   # 指定验证集

# 2.训练
num_round = 10
bst = xgb.train( plst, dtrain, num_round)
#bst = xgb.train( plst, dtrain, num_round, evallist )

# 3.保存模型
bst.save_model('0001.model')
# dump model
bst.dump_model('dump.raw.txt')
# dump model with feature map
#bst.dump_model('dump.raw.txt', 'featmap.txt')

# 4.加载保存的模型：
bst = xgb.Booster({'nthread': 4})  # init model
bst.load_model('0001.model')  # load data

# 5.也可以设置早停机制（需要设置验证集）
train(..., evals=evals, early_stopping_rounds=10)

# 6.预测
ypred = bst.predict(dtest)

# 1.绘制重要性
xgb.plot_importance(bst)
# 2.绘制输出树
#xgb.plot_tree(bst, num_trees=2)
# 3.使用xgboost.to_graphviz()将目标树转换为graphviz
#xgb.to_graphviz(bst, num_trees=2)

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
from sklearn.metrics import accuracy_score   # 准确率
# 加载样本数据集
iris = load_iris()
X,y = iris.data,iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234565) # 数据集分割
 
# 算法参数
params = {
    'booster': 'gbtree',
    'objective': 'multi:softmax',
    'num_class': 3,
    'gamma': 0.1,
    'max_depth': 6,
    'lambda': 2,
    'subsample': 0.7,
    'colsample_bytree': 0.75,
    'min_child_weight': 3,
    'silent': 0,
    'eta': 0.1,
    'seed': 1,
    'nthread': 4,
}
 
plst = params.items()
 
dtrain = xgb.DMatrix(X_train, y_train) # 生成数据集格式
num_rounds = 500
model = xgb.train(plst, dtrain, num_rounds) # xgboost模型训练
 
# 对测试集进行预测
dtest = xgb.DMatrix(X_test)
y_pred = model.predict(dtest)
 
# 计算准确率
accuracy = accuracy_score(y_test,y_pred)
print("accuarcy: %.2f%%" % (accuracy*100.0))
 
# 显示重要特征
plot_importance(model)
plt.show()

import xgboost as xgb
from xgboost import plot_importance
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error
 
# 加载数据集
boston = load_boston()
X,y = boston.data,boston.target
 
# 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:squarederror',
    '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
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()

import xgboost as xgb
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import roc_auc_score
 
iris = load_iris()
X,y = iris.data,iris.target
col = iris.target_names 
train_x, valid_x, train_y, valid_y = train_test_split(X, y, test_size=0.3, random_state=1)   # 分训练集和验证集
parameters = {
              'max_depth': [5, 10, 15, 20, 25],
              'learning_rate': [0.01, 0.02, 0.05, 0.1, 0.15],
              'n_estimators': [500, 1000, 2000, 3000, 5000],
              'min_child_weight': [0, 2, 5, 10, 20],
              'max_delta_step': [0, 0.2, 0.6, 1, 2],
              'subsample': [0.6, 0.7, 0.8, 0.85, 0.95],
              'colsample_bytree': [0.5, 0.6, 0.7, 0.8, 0.9],
              'reg_alpha': [0, 0.25, 0.5, 0.75, 1],
              'reg_lambda': [0.2, 0.4, 0.6, 0.8, 1],
              'scale_pos_weight': [0.2, 0.4, 0.6, 0.8, 1]
 
}
 
xlf = xgb.XGBClassifier(max_depth=10,
            learning_rate=0.01,
            n_estimators=2000,
            silent=True,
            objective='multi:softmax',
            num_class=3 ,          
            nthread=-1,
            gamma=0,
            min_child_weight=1,
            max_delta_step=0,
            subsample=0.85,
            colsample_bytree=0.7,
            colsample_bylevel=1,
            reg_alpha=0,
            reg_lambda=1,
            scale_pos_weight=1,
            seed=0,
            missing=None)
 
gs = GridSearchCV(xlf, param_grid=parameters, scoring='accuracy', cv=3)
gs.fit(train_x, train_y)
 
print("Best score: %0.3f" % gs.best_score_)
print("Best parameters set: %s" % gs.best_params_ )