메뉴
Optimize and maintain XGBoost machine learning models for football predictions. Use when tuning hyperparameters, implementing feature engineering, analyzing model performance, or deploying ML models to production.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Comprehensive API testing including unit tests, integration tests, performance testing, and automated test pipelines. Use when testing REST endpoints, validating API responses, load testing, or setting up test automation.
Manage code quality for Football Prediction project using Make commands. Use when running quality checks, formatting code, running tests, or preparing for commits. Supports black, flake8, mypy, bandit, pytest, and coverage tools.
Collect football data from external APIs including FotMob L2 data, odds information, and real-time match statistics. Use when gathering match data, collecting historical statistics, or updating prediction datasets.
Design and optimize data pipelines for football prediction system. Use when building ETL processes, data transformations, or optimizing data flow between PostgreSQL, Redis, and external APIs.
Manage PostgreSQL database operations including migrations, query optimization, connection pooling, and data backup/restore. Use when handling database tasks, optimizing queries, or managing database connections.
Manage application deployment including Docker containers, production environments, and service orchestration. Use when deploying to production, managing Docker services, or handling deployment rollbacks.
| name | machine-learning-engineering |
| description | Optimize and maintain XGBoost machine learning models for football predictions. Use when tuning hyperparameters, implementing feature engineering, analyzing model performance, or deploying ML models to production. |
专业的机器学习工程技能模块，专注于模型优化、特征工程和模型部署的最佳实践。
# 模型快速优化示例
from xgboost import XGBClassifier
from sklearn.model_selection import cross_val_score
# 基础优化配置
params = {
'max_depth': 6,
'learning_rate': 0.1,
'n_estimators': 100,
'subsample': 0.8,
'colsample_bytree': 0.8
}
model = XGBClassifier(**params)
scores = cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy')
# 高级超参数优化
import optuna
from sklearn.metrics import accuracy_score
def objective(trial):
params = {
'max_depth': trial.suggest_int('max_depth', 3, 10),
'learning_rate': trial.suggest_loguniform('learning_rate', 0.01, 0.3),
'n_estimators': trial.suggest_int('n_estimators', 50, 500),
'subsample': trial.suggest_uniform('subsample', 0.6, 1.0),
'colsample_bytree': trial.suggest_uniform('colsample_bytree', 0.6, 1.0),
'min_child_weight': trial.suggest_int('min_child_weight', 1, 10)
}
model = XGBClassifier(**params)
model.fit(X_train, y_train)
predictions = model.predict(X_val)
return accuracy_score(y_val, predictions)
study = optuna.create_study(direction='maximize')
study.optimize(objective, n_trials=100)
# 模型融合和集成
from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
# 创建异构集成
xgb_model = XGBClassifier(**study.best_params)
rf_model = RandomForestClassifier(n_estimators=200)
lr_model = LogisticRegression()
ensemble_model = VotingClassifier(
estimators=[
('xgb', xgb_model),
('rf', rf_model),
('lr', lr_model)
],
voting='soft'
)
import shap
# SHAP分析
explainer = shap.TreeExplainer(model)
shap_values = explainer.shap_values(X_test)
# 可视化特征重要性
shap.summary_plot(shap_values, X_test)
shap.dependence_plot("feature_name", shap_values, X_test)
max_bin参数减少内存使用tree_method='hist'或'gpu_hist'n_jobs=-1利用多核CPUimport mlflow
import mlflow.xgboost
with mlflow.start_run():
# 记录参数
mlflow.log_params(params)
# 训练模型
model.fit(X_train, y_train)
# 记录指标
mlflow.log_metric("accuracy", accuracy)
# 保存模型
mlflow.xgboost.log_model(model, "model")
optuna_config:
n_trials: 200
timeout: 3600
direction: maximize
sampler:
type: TPE
pruner:
type: Median
n_startup_trials: 10
param_space:
max_depth: [3, 10]
learning_rate: [0.01, 0.3]
n_estimators: [50, 500]
subsample: [0.6, 1.0]
colsample_bytree: [0.6, 1.0]
min_child_weight: [1, 10]
gamma: [0, 5]
reg_alpha: [0, 1]
reg_lambda: [0, 1]
feature-engineering: 特征工程专项（V25.1 自适应引擎）football-prediction: 足球预测系统v26-harvest: V26.1 收割流水线data-engineering: 数据管道工程Last updated: 2025-12-28 Target: 足球赛果预测系统优化