机器学习常用模板—（XGB）

XGB分为原生接口和Sklearn接口，下面是基于Sklearn的接口

基于Sklearn接口

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()

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

# 读取文件原始数据
data = []
labels = []
labels2 = []
with open("lppz5.csv", encoding='UTF-8') as fileObject:
    for line in fileObject:
        line_split = line.split(',')
        data.append(line_split[10:])
        labels.append(line_split[8])

X = []
for row in data:
    row = [float(x) for x in row]
    X.append(row)

y = [float(x) for x in labels]

# 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()

注：转自与知乎 作者：章华燕