1082 lines
39 KiB
Markdown
1082 lines
39 KiB
Markdown
# L3 Feature Mart - Complete Architecture Plan
|
||
|
||
> **Version**: 2.0 (Complete Redesign)
|
||
> **Date**: 2026-01-28
|
||
> **Status**: Planning Phase
|
||
|
||
---
|
||
|
||
## Executive Summary
|
||
|
||
基于完整的L2 schema和Profile需求，重新设计L3特征层架构。核心原则：
|
||
1. **去除冗余**：消除Profile_summary.md中的重复指标
|
||
2. **深度挖掘**：利用L2的rounds/events数据进行深层次特征工程
|
||
3. **模块化计算**：按照功能域拆分processor，清晰的职责边界
|
||
4. **服务解耦**：web/services只做查询，不做计算
|
||
|
||
---
|
||
|
||
## Part 1: 特征维度重构分析
|
||
|
||
### 1.1 现有Profile问题诊断
|
||
|
||
**重复指标识别**：
|
||
```
|
||
- basic_avg_rating 在 Dashboard + Core Performance 重复
|
||
- basic_avg_kd 在 Dashboard + Core Performance 重复
|
||
- basic_avg_adr 在 Dashboard + Core Performance 重复
|
||
- basic_avg_kast 在 Dashboard + Core Performance 重复
|
||
- FK/FD 在 Opening Impact + SIDE Preference 重复
|
||
- Clutch 数据在 Multi-Frag + HPS + SPECIAL 重复
|
||
- 多个"率"类指标可从原始count计算，不需存储
|
||
```
|
||
|
||
**缺失维度识别**：
|
||
```
|
||
✗ 地图热力维度（基于xyz坐标）
|
||
✗ 武器偏好深度分析（不仅是top5）
|
||
✗ 对手强度分层表现（基于ELO差值）
|
||
✗ 时间序列波动分析（不仅是volatility）
|
||
✗ 队友协同效应（assist network）
|
||
✗ 经济效率分层（不同价位段表现）
|
||
✗ 回合贡献度评分（综合impact）
|
||
```
|
||
|
||
### 1.2 重构后的特征分类体系
|
||
|
||
#### 🎯 Tier 1: 核心基础层 (CORE)
|
||
**目标**：最常用的聚合统计，直接从fact_match_players计算
|
||
|
||
| 特征组 | 指标数量 | 典型指标 | L2来源表 |
|
||
|--------|---------|---------|---------|
|
||
| Basic Stats | 15 | rating, kd, adr, kast, rws, hs% | fact_match_players |
|
||
| Match Stats | 8 | total_matches, win_rate, avg_duration | fact_matches + fact_match_players |
|
||
| Weapon Stats | 12 | awp_kills, knife_kills, zeus_kills, top_weapon | fact_match_players + fact_round_events |
|
||
| Objective Stats | 6 | plants, defuses, mvps, flash_assists | fact_match_players |
|
||
|
||
**特点**：
|
||
- 单表或简单JOIN即可计算
|
||
- 无复杂逻辑，纯聚合函数
|
||
- 用于Dashboard快速展示
|
||
|
||
#### 🔥 Tier 2: 战术能力层 (TACTICAL)
|
||
**目标**：反映玩家战术素养的深度指标
|
||
|
||
| 特征组 | 指标数量 | 典型指标 | 计算复杂度 |
|
||
|--------|---------|---------|-----------|
|
||
| Opening Impact | 8 | fk_rate, fd_rate, fk_success_rate, entry_trade_rate | 中 |
|
||
| Multi-Kill | 6 | 2k/3k/4k/5k rates, ace_count | 低 |
|
||
| Clutch Performance | 10 | 1v1~1v5 win_rate, clutch_impact_score | 中 |
|
||
| Utility Mastery | 12 | nade_dmg_per_round, flash_efficiency, smoke_timing | 高 |
|
||
| Economy Efficiency | 8 | dmg_per_1k, eco_kd, force_buy_performance | 中 |
|
||
|
||
**特点**：
|
||
- 需要JOIN多表（players + events + economy）
|
||
- 涉及条件筛选和比率计算
|
||
- 反映玩家决策质量
|
||
|
||
#### 🧠 Tier 3: 高级智能层 (INTELLIGENCE)
|
||
**目标**：通过复杂计算提取隐藏模式
|
||
|
||
| 特征组 | 指标数量 | 典型指标 | 数据源 |
|
||
|--------|---------|---------|--------|
|
||
| High IQ Kills | 8 | wallbang_rate, smoke_kill_rate, blind_kill_rate, iq_score | fact_round_events (flags) |
|
||
| Timing Analysis | 12 | kill_time_distribution, death_timing_pattern, aggression_index | fact_round_events (event_time) |
|
||
| Pressure Performance | 10 | comeback_kd, losing_streak_kd, matchpoint_kpr | fact_rounds + fact_round_events |
|
||
| Position Mastery | 15 | position_heatmap, site_control_rate, rotation_efficiency | fact_round_events (xyz) |
|
||
| Trade Network | 8 | trade_kill_rate, trade_response_time, teamwork_score | fact_round_events (self-join) |
|
||
|
||
**特点**：
|
||
- 需要时间窗口计算（5s/10s trade window）
|
||
- 涉及空间分析（xyz聚类）
|
||
- 需要序列分析（连败/追分场景）
|
||
|
||
#### 📊 Tier 4: 稳定性与元数据层 (META)
|
||
**目标**：长期表现模式和元特征
|
||
|
||
| 特征组 | 指标数量 | 典型指标 | 计算方式 |
|
||
|--------|---------|---------|---------|
|
||
| Stability | 8 | rating_volatility, map_stability, recent_form | 时间序列STDDEV/滑动窗口 |
|
||
| Side Preference | 14 | ct_rating, t_rating, side_kd_diff, side_win_diff | fact_match_players_ct/t |
|
||
| Opponent Adaptation | 12 | performance_vs_elo_tiers, rank_diff_impact | fact_match_teams (elo) |
|
||
| Map Specialization | 10 | map_rating_by_map, best_map, worst_map | GROUP BY map |
|
||
| Session Pattern | 8 | daily_performance, streak_analysis, fatigue_index | 时间戳分组 |
|
||
|
||
**特点**：
|
||
- 跨match维度聚合
|
||
- 需要分层/分组分析
|
||
- 涉及时间序列特征
|
||
|
||
#### 🎨 Tier 5: 综合评分层 (COMPOSITE)
|
||
**目标**：多维度加权综合评分，用于雷达图
|
||
|
||
| 评分维度 | 权重组成 | 输出范围 | 用途 |
|
||
|---------|---------|---------|------|
|
||
| AIM (枪法) | 25% Rating + 20% KD + 15% ADR + 10% DuelWin + 10% HighEloKD + 20% MultiKill | 0-100 | Radar Axis |
|
||
| CLUTCH (残局) | 25% 1v3+ + 20% MatchPtWin + 20% ComebackKD + 15% PressureEntry + 20% Rating | 0-100 | Radar Axis |
|
||
| PISTOL (手枪) | 30% PistolKills + 30% PistolWin + 20% PistolKD + 20% PistolHS% | 0-100 | Radar Axis |
|
||
| DEFENSE (防守) | 35% CT_Rating + 35% T_Rating + 15% CT_FK + 15% T_FK | 0-100 | Radar Axis |
|
||
| UTIL (道具) | 35% UsageRate + 25% NadeDmg + 20% FlashEff + 20% FlashEnemy | 0-100 | Radar Axis |
|
||
| STABILITY (稳定) | 30% (100-Volatility) + 30% LossRating + 20% WinRating + 20% Consistency | 0-100 | Radar Axis |
|
||
| ECONOMY (经济) | 50% Dmg/$1k + 30% EcoKPR + 20% SaveRoundKD | 0-100 | Radar Axis |
|
||
| PACE (节奏) | 40% EntryTiming + 30% TradeSpeed + 30% AggressionIndex | 0-100 | Radar Axis |
|
||
|
||
**特点**：
|
||
- 依赖Tier 1-4的基础特征
|
||
- 标准化 + 加权 = 0-100评分
|
||
- 最后计算，存储为独立字段
|
||
|
||
---
|
||
|
||
## Part 2: L3 Table Schema Design
|
||
|
||
### 2.1 主表：dm_player_features
|
||
|
||
**设计原则**：
|
||
- 一个player一行，steam_id_64为主键
|
||
- 包含所有聚合特征（200+列）
|
||
- 按照Tier分组组织列
|
||
- 添加元数据列（matches_count, last_updated等）
|
||
|
||
```sql
|
||
CREATE TABLE dm_player_features (
|
||
-- 主键与元数据
|
||
steam_id_64 TEXT PRIMARY KEY,
|
||
total_matches INTEGER NOT NULL DEFAULT 0,
|
||
total_rounds INTEGER NOT NULL DEFAULT 0,
|
||
first_match_date INTEGER, -- Unix timestamp
|
||
last_match_date INTEGER,
|
||
last_updated TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
||
|
||
-- ==========================================
|
||
-- Tier 1: CORE - Basic Stats (15 columns)
|
||
-- ==========================================
|
||
core_avg_rating REAL DEFAULT 0.0,
|
||
core_avg_rating2 REAL DEFAULT 0.0,
|
||
core_avg_kd REAL DEFAULT 0.0,
|
||
core_avg_adr REAL DEFAULT 0.0,
|
||
core_avg_kast REAL DEFAULT 0.0,
|
||
core_avg_rws REAL DEFAULT 0.0,
|
||
core_avg_hs_kills REAL DEFAULT 0.0,
|
||
core_hs_rate REAL DEFAULT 0.0, -- hs/total_kills
|
||
core_total_kills INTEGER DEFAULT 0,
|
||
core_total_deaths INTEGER DEFAULT 0,
|
||
core_total_assists INTEGER DEFAULT 0,
|
||
core_avg_assists REAL DEFAULT 0.0,
|
||
core_kpr REAL DEFAULT 0.0, -- kills per round
|
||
core_dpr REAL DEFAULT 0.0, -- deaths per round
|
||
core_survival_rate REAL DEFAULT 0.0, -- survived rounds / total rounds
|
||
|
||
-- Match Stats (8 columns)
|
||
core_win_rate REAL DEFAULT 0.0,
|
||
core_wins INTEGER DEFAULT 0,
|
||
core_losses INTEGER DEFAULT 0,
|
||
core_avg_match_duration INTEGER DEFAULT 0, -- seconds
|
||
core_avg_mvps REAL DEFAULT 0.0,
|
||
core_mvp_rate REAL DEFAULT 0.0, -- mvps per match
|
||
core_avg_elo_change REAL DEFAULT 0.0,
|
||
core_total_elo_gained REAL DEFAULT 0.0,
|
||
|
||
-- Weapon Stats (12 columns)
|
||
core_avg_awp_kills REAL DEFAULT 0.0,
|
||
core_awp_usage_rate REAL DEFAULT 0.0, -- rounds with AWP / total rounds
|
||
core_avg_knife_kills REAL DEFAULT 0.0,
|
||
core_avg_zeus_kills REAL DEFAULT 0.0,
|
||
core_zeus_buy_rate REAL DEFAULT 0.0,
|
||
core_top_weapon TEXT, -- Most used weapon name
|
||
core_top_weapon_kills INTEGER DEFAULT 0,
|
||
core_top_weapon_hs_rate REAL DEFAULT 0.0,
|
||
core_weapon_diversity REAL DEFAULT 0.0, -- Shannon entropy of weapon usage
|
||
core_rifle_hs_rate REAL DEFAULT 0.0,
|
||
core_pistol_hs_rate REAL DEFAULT 0.0,
|
||
core_smg_kills_total INTEGER DEFAULT 0,
|
||
|
||
-- Objective Stats (6 columns)
|
||
core_avg_plants REAL DEFAULT 0.0,
|
||
core_avg_defuses REAL DEFAULT 0.0,
|
||
core_avg_flash_assists REAL DEFAULT 0.0,
|
||
core_plant_success_rate REAL DEFAULT 0.0, -- plants / T rounds
|
||
core_defuse_success_rate REAL DEFAULT 0.0, -- defuses / (CT rounds with plant)
|
||
core_objective_impact REAL DEFAULT 0.0, -- Weighted score: 2*plant + 3*defuse + 0.5*flash_assist
|
||
|
||
-- ==========================================
|
||
-- Tier 2: TACTICAL - Opening Impact (8)
|
||
-- ==========================================
|
||
tac_avg_fk REAL DEFAULT 0.0, -- first kills per match
|
||
tac_avg_fd REAL DEFAULT 0.0, -- first deaths per match
|
||
tac_fk_rate REAL DEFAULT 0.0, -- FK / (FK + FD)
|
||
tac_fd_rate REAL DEFAULT 0.0, -- FD / (FK + FD)
|
||
tac_fk_success_rate REAL DEFAULT 0.0, -- team win rate when player gets FK
|
||
tac_entry_kill_rate REAL DEFAULT 0.0, -- entry_kills per T round
|
||
tac_entry_death_rate REAL DEFAULT 0.0,
|
||
tac_opening_duel_winrate REAL DEFAULT 0.0, -- entry_kills / (entry_kills + entry_deaths)
|
||
|
||
-- Multi-Kill (6)
|
||
tac_avg_2k REAL DEFAULT 0.0,
|
||
tac_avg_3k REAL DEFAULT 0.0,
|
||
tac_avg_4k REAL DEFAULT 0.0,
|
||
tac_avg_5k REAL DEFAULT 0.0,
|
||
tac_multikill_rate REAL DEFAULT 0.0, -- (2k+3k+4k+5k) / rounds
|
||
tac_ace_count INTEGER DEFAULT 0,
|
||
|
||
-- Clutch Performance (10)
|
||
tac_clutch_1v1_attempts INTEGER DEFAULT 0,
|
||
tac_clutch_1v1_wins INTEGER DEFAULT 0,
|
||
tac_clutch_1v1_rate REAL DEFAULT 0.0, -- wins / attempts
|
||
tac_clutch_1v2_attempts INTEGER DEFAULT 0,
|
||
tac_clutch_1v2_wins INTEGER DEFAULT 0,
|
||
tac_clutch_1v2_rate REAL DEFAULT 0.0,
|
||
tac_clutch_1v3_plus_attempts INTEGER DEFAULT 0, -- 1v3+1v4+1v5 combined
|
||
tac_clutch_1v3_plus_wins INTEGER DEFAULT 0,
|
||
tac_clutch_1v3_plus_rate REAL DEFAULT 0.0,
|
||
tac_clutch_impact_score REAL DEFAULT 0.0, -- Weighted: 1v1*1 + 1v2*3 + 1v3*7 + 1v4*15 + 1v5*30
|
||
|
||
-- Utility Mastery (12)
|
||
tac_util_flash_per_round REAL DEFAULT 0.0,
|
||
tac_util_smoke_per_round REAL DEFAULT 0.0,
|
||
tac_util_molotov_per_round REAL DEFAULT 0.0,
|
||
tac_util_he_per_round REAL DEFAULT 0.0,
|
||
tac_util_usage_rate REAL DEFAULT 0.0, -- Total nades / rounds
|
||
tac_util_nade_dmg_per_round REAL DEFAULT 0.0,
|
||
tac_util_nade_dmg_per_nade REAL DEFAULT 0.0,
|
||
tac_util_flash_time_per_round REAL DEFAULT 0.0,
|
||
tac_util_flash_enemies_per_round REAL DEFAULT 0.0,
|
||
tac_util_flash_efficiency REAL DEFAULT 0.0, -- flash_enemies / flash_usage
|
||
tac_util_smoke_timing_score REAL DEFAULT 0.0, -- Based on smoke usage in execute (40-60s)
|
||
tac_util_impact_score REAL DEFAULT 0.0, -- Composite utility impact
|
||
|
||
-- Economy Efficiency (8)
|
||
tac_eco_dmg_per_1k REAL DEFAULT 0.0, -- damage / (equipment_value / 1000)
|
||
tac_eco_kpr_eco_rounds REAL DEFAULT 0.0, -- KPR when equipment < $2000
|
||
tac_eco_kd_eco_rounds REAL DEFAULT 0.0,
|
||
tac_eco_kpr_force_rounds REAL DEFAULT 0.0, -- $2000-$4000
|
||
tac_eco_kpr_full_rounds REAL DEFAULT 0.0, -- $4000+
|
||
tac_eco_save_discipline REAL DEFAULT 0.0, -- % of eco rounds with proper save
|
||
tac_eco_force_success_rate REAL DEFAULT 0.0, -- Win rate in force buy rounds
|
||
tac_eco_efficiency_score REAL DEFAULT 0.0, -- Composite economic efficiency
|
||
|
||
-- ==========================================
|
||
-- Tier 3: INTELLIGENCE - High IQ Kills (8)
|
||
-- ==========================================
|
||
int_wallbang_kills INTEGER DEFAULT 0,
|
||
int_wallbang_rate REAL DEFAULT 0.0, -- wallbang / total_kills
|
||
int_smoke_kills INTEGER DEFAULT 0,
|
||
int_smoke_kill_rate REAL DEFAULT 0.0,
|
||
int_blind_kills INTEGER DEFAULT 0,
|
||
int_blind_kill_rate REAL DEFAULT 0.0,
|
||
int_noscope_kills INTEGER DEFAULT 0,
|
||
int_noscope_rate REAL DEFAULT 0.0, -- noscope / awp_kills
|
||
int_high_iq_score REAL DEFAULT 0.0, -- Weighted: wallbang*3 + smoke*2 + blind*1.5 + noscope*2
|
||
|
||
-- Timing Analysis (12)
|
||
int_timing_early_kills INTEGER DEFAULT 0, -- 0-30s
|
||
int_timing_mid_kills INTEGER DEFAULT 0, -- 30-60s
|
||
int_timing_late_kills INTEGER DEFAULT 0, -- 60s+
|
||
int_timing_early_kill_share REAL DEFAULT 0.0,
|
||
int_timing_mid_kill_share REAL DEFAULT 0.0,
|
||
int_timing_late_kill_share REAL DEFAULT 0.0,
|
||
int_timing_avg_kill_time REAL DEFAULT 0.0, -- Avg seconds from round start
|
||
int_timing_early_deaths INTEGER DEFAULT 0,
|
||
int_timing_early_death_rate REAL DEFAULT 0.0,
|
||
int_timing_aggression_index REAL DEFAULT 0.0, -- early_kills / early_deaths
|
||
int_timing_patience_score REAL DEFAULT 0.0, -- late_kills / total_kills
|
||
int_timing_first_contact_time REAL DEFAULT 0.0, -- Avg time to first engagement
|
||
|
||
-- Pressure Performance (10)
|
||
int_pressure_comeback_kd REAL DEFAULT 0.0, -- KD when down 4+ rounds
|
||
int_pressure_comeback_rating REAL DEFAULT 0.0,
|
||
int_pressure_losing_streak_kd REAL DEFAULT 0.0, -- KD during 3+ round loss streak
|
||
int_pressure_matchpoint_kpr REAL DEFAULT 0.0, -- KPR at match point (15-X or 12-X)
|
||
int_pressure_matchpoint_rating REAL DEFAULT 0.0,
|
||
int_pressure_clutch_composure REAL DEFAULT 0.0, -- Clutch rate in must-win situations
|
||
int_pressure_entry_in_loss REAL DEFAULT 0.0, -- FK rate in losing matches
|
||
int_pressure_performance_index REAL DEFAULT 0.0, -- Composite pressure metric
|
||
int_pressure_big_moment_score REAL DEFAULT 0.0, -- Weighted matchpoint + comeback performance
|
||
int_pressure_tilt_resistance REAL DEFAULT 0.0, -- rating_in_loss / rating_in_win
|
||
|
||
-- Position Mastery (15) - Based on xyz clustering
|
||
int_pos_site_a_control_rate REAL DEFAULT 0.0, -- % of rounds controlling A site
|
||
int_pos_site_b_control_rate REAL DEFAULT 0.0,
|
||
int_pos_mid_control_rate REAL DEFAULT 0.0,
|
||
int_pos_favorite_position TEXT, -- Most common position cluster
|
||
int_pos_position_diversity REAL DEFAULT 0.0, -- Entropy of position usage
|
||
int_pos_rotation_speed REAL DEFAULT 0.0, -- Avg distance traveled between kills
|
||
int_pos_map_coverage REAL DEFAULT 0.0, -- % of map areas visited
|
||
int_pos_defensive_positioning REAL DEFAULT 0.0, -- CT: avg distance from site
|
||
int_pos_aggressive_positioning REAL DEFAULT 0.0, -- T: avg distance pushed
|
||
int_pos_lurk_tendency REAL DEFAULT 0.0, -- % of rounds alone vs teammates
|
||
int_pos_site_anchor_score REAL DEFAULT 0.0, -- Consistency holding site
|
||
int_pos_entry_route_diversity REAL DEFAULT 0.0, -- Different entry paths used
|
||
int_pos_retake_positioning REAL DEFAULT 0.0, -- Performance in retake scenarios
|
||
int_pos_postplant_positioning REAL DEFAULT 0.0, -- Position quality after plant
|
||
int_pos_spatial_iq_score REAL DEFAULT 0.0, -- Composite positioning intelligence
|
||
|
||
-- Trade Network (8)
|
||
int_trade_kill_count INTEGER DEFAULT 0, -- Kills within 5s of teammate death
|
||
int_trade_kill_rate REAL DEFAULT 0.0, -- trade_kills / total_kills
|
||
int_trade_response_time REAL DEFAULT 0.0, -- Avg seconds to trade teammate
|
||
int_trade_given_count INTEGER DEFAULT 0, -- Deaths traded by teammate
|
||
int_trade_given_rate REAL DEFAULT 0.0, -- traded_deaths / total_deaths
|
||
int_trade_balance REAL DEFAULT 0.0, -- trades_given - trades_made
|
||
int_trade_efficiency REAL DEFAULT 0.0, -- (trade_kills + traded_deaths) / (total_kills + deaths)
|
||
int_teamwork_score REAL DEFAULT 0.0, -- Composite teamwork metric
|
||
|
||
-- ==========================================
|
||
-- Tier 4: META - Stability (8)
|
||
-- ==========================================
|
||
meta_rating_volatility REAL DEFAULT 0.0, -- STDDEV of last 20 matches
|
||
meta_recent_form_rating REAL DEFAULT 0.0, -- AVG of last 10 matches
|
||
meta_win_rating REAL DEFAULT 0.0, -- AVG rating in wins
|
||
meta_loss_rating REAL DEFAULT 0.0, -- AVG rating in losses
|
||
meta_rating_consistency REAL DEFAULT 0.0, -- 100 - volatility_normalized
|
||
meta_time_rating_correlation REAL DEFAULT 0.0, -- Correlation(match_time, rating)
|
||
meta_map_stability REAL DEFAULT 0.0, -- STDDEV of rating across maps
|
||
meta_elo_tier_stability REAL DEFAULT 0.0, -- STDDEV of rating across opponent ELO tiers
|
||
|
||
-- Side Preference (14)
|
||
meta_side_ct_rating REAL DEFAULT 0.0,
|
||
meta_side_t_rating REAL DEFAULT 0.0,
|
||
meta_side_ct_kd REAL DEFAULT 0.0,
|
||
meta_side_t_kd REAL DEFAULT 0.0,
|
||
meta_side_ct_win_rate REAL DEFAULT 0.0,
|
||
meta_side_t_win_rate REAL DEFAULT 0.0,
|
||
meta_side_ct_fk_rate REAL DEFAULT 0.0, -- FK per CT round
|
||
meta_side_t_fk_rate REAL DEFAULT 0.0,
|
||
meta_side_ct_kast REAL DEFAULT 0.0,
|
||
meta_side_t_kast REAL DEFAULT 0.0,
|
||
meta_side_rating_diff REAL DEFAULT 0.0, -- CT - T
|
||
meta_side_kd_diff REAL DEFAULT 0.0,
|
||
meta_side_preference TEXT, -- 'CT', 'T', or 'Balanced'
|
||
meta_side_balance_score REAL DEFAULT 0.0, -- 100 - ABS(CT_rating - T_rating)*50
|
||
|
||
-- Opponent Adaptation (12)
|
||
meta_opp_vs_lower_elo_rating REAL DEFAULT 0.0, -- vs opponents -200 ELO
|
||
meta_opp_vs_similar_elo_rating REAL DEFAULT 0.0, -- vs ±200 ELO
|
||
meta_opp_vs_higher_elo_rating REAL DEFAULT 0.0, -- vs +200 ELO
|
||
meta_opp_vs_lower_elo_kd REAL DEFAULT 0.0,
|
||
meta_opp_vs_similar_elo_kd REAL DEFAULT 0.0,
|
||
meta_opp_vs_higher_elo_kd REAL DEFAULT 0.0,
|
||
meta_opp_elo_adaptation REAL DEFAULT 0.0, -- higher_elo_rating / lower_elo_rating
|
||
meta_opp_stomping_score REAL DEFAULT 0.0, -- Performance vs weaker opponents
|
||
meta_opp_upset_score REAL DEFAULT 0.0, -- Performance vs stronger opponents
|
||
meta_opp_consistency_across_elos REAL DEFAULT 0.0, -- 100 - STDDEV(rating by elo tier)
|
||
meta_opp_rank_resistance REAL DEFAULT 0.0, -- Win rate vs higher ELO
|
||
meta_opp_smurf_detection REAL DEFAULT 0.0, -- Abnormally high performance vs lower ELO
|
||
|
||
-- Map Specialization (10)
|
||
meta_map_best_map TEXT,
|
||
meta_map_best_rating REAL DEFAULT 0.0,
|
||
meta_map_worst_map TEXT,
|
||
meta_map_worst_rating REAL DEFAULT 0.0,
|
||
meta_map_diversity REAL DEFAULT 0.0, -- Entropy of map ratings
|
||
meta_map_pool_size INTEGER DEFAULT 0, -- Number of maps with 5+ matches
|
||
meta_map_specialist_score REAL DEFAULT 0.0, -- (best - worst) rating
|
||
meta_map_versatility REAL DEFAULT 0.0, -- 100 - map_stability
|
||
meta_map_comfort_zone_rate REAL DEFAULT 0.0, -- % of matches on top 3 maps
|
||
meta_map_adaptation REAL DEFAULT 0.0, -- Avg rating on non-favorite maps
|
||
|
||
-- Session Pattern (8)
|
||
meta_session_avg_matches_per_day REAL DEFAULT 0.0,
|
||
meta_session_longest_streak INTEGER DEFAULT 0, -- Days played consecutively
|
||
meta_session_weekend_rating REAL DEFAULT 0.0,
|
||
meta_session_weekday_rating REAL DEFAULT 0.0,
|
||
meta_session_morning_rating REAL DEFAULT 0.0, -- 6-12h
|
||
meta_session_afternoon_rating REAL DEFAULT 0.0, -- 12-18h
|
||
meta_session_evening_rating REAL DEFAULT 0.0, -- 18-24h
|
||
meta_session_night_rating REAL DEFAULT 0.0, -- 0-6h
|
||
|
||
-- ==========================================
|
||
-- Tier 5: COMPOSITE - Radar Scores (8)
|
||
-- ==========================================
|
||
score_aim REAL DEFAULT 0.0, -- 0-100 normalized
|
||
score_clutch REAL DEFAULT 0.0,
|
||
score_pistol REAL DEFAULT 0.0,
|
||
score_defense REAL DEFAULT 0.0,
|
||
score_utility REAL DEFAULT 0.0,
|
||
score_stability REAL DEFAULT 0.0,
|
||
score_economy REAL DEFAULT 0.0,
|
||
score_pace REAL DEFAULT 0.0,
|
||
|
||
-- Overall composite
|
||
score_overall REAL DEFAULT 0.0, -- AVG of all 8 scores
|
||
|
||
-- Performance tier classification
|
||
tier_classification TEXT, -- 'Elite', 'Advanced', 'Intermediate', 'Beginner'
|
||
tier_percentile REAL DEFAULT 0.0, -- Overall percentile rank
|
||
|
||
-- Index for queries
|
||
FOREIGN KEY (steam_id_64) REFERENCES dim_players(steam_id_64)
|
||
);
|
||
|
||
CREATE INDEX idx_dm_player_features_rating ON dm_player_features(core_avg_rating DESC);
|
||
CREATE INDEX idx_dm_player_features_matches ON dm_player_features(total_matches DESC);
|
||
CREATE INDEX idx_dm_player_features_tier ON dm_player_features(tier_classification);
|
||
```
|
||
|
||
**列统计**：
|
||
- Tier 1 CORE: 41 columns
|
||
- Tier 2 TACTICAL: 44 columns
|
||
- Tier 3 INTELLIGENCE: 53 columns
|
||
- Tier 4 META: 52 columns
|
||
- Tier 5 COMPOSITE: 11 columns
|
||
- Meta + Keys: 6 columns
|
||
- **Total: ~207 columns**
|
||
|
||
### 2.2 辅助表：dm_player_match_history
|
||
|
||
**用途**：支持时间序列分析和趋势图
|
||
|
||
```sql
|
||
CREATE TABLE dm_player_match_history (
|
||
steam_id_64 TEXT,
|
||
match_id TEXT,
|
||
match_date INTEGER, -- Unix timestamp
|
||
match_sequence INTEGER, -- Player's N-th match
|
||
|
||
-- Core performance
|
||
rating REAL,
|
||
kd_ratio REAL,
|
||
adr REAL,
|
||
kast REAL,
|
||
is_win BOOLEAN,
|
||
|
||
-- Match context
|
||
map_name TEXT,
|
||
opponent_avg_elo REAL,
|
||
teammate_avg_rating REAL,
|
||
|
||
-- Cumulative stats (for moving averages)
|
||
cumulative_rating REAL, -- AVG up to this match
|
||
rolling_10_rating REAL, -- Last 10 matches AVG
|
||
|
||
PRIMARY KEY (steam_id_64, match_id),
|
||
FOREIGN KEY (steam_id_64) REFERENCES dm_players(steam_id_64),
|
||
FOREIGN KEY (match_id) REFERENCES fact_matches(match_id)
|
||
);
|
||
|
||
CREATE INDEX idx_player_history_player_date ON dm_player_match_history(steam_id_64, match_date DESC);
|
||
```
|
||
|
||
### 2.3 辅助表：dm_player_map_stats
|
||
|
||
**用途**：地图级别细分统计
|
||
|
||
```sql
|
||
CREATE TABLE dm_player_map_stats (
|
||
steam_id_64 TEXT,
|
||
map_name TEXT,
|
||
|
||
matches INTEGER DEFAULT 0,
|
||
wins INTEGER DEFAULT 0,
|
||
win_rate REAL DEFAULT 0.0,
|
||
|
||
avg_rating REAL DEFAULT 0.0,
|
||
avg_kd REAL DEFAULT 0.0,
|
||
avg_adr REAL DEFAULT 0.0,
|
||
avg_kast REAL DEFAULT 0.0,
|
||
|
||
best_rating REAL DEFAULT 0.0,
|
||
worst_rating REAL DEFAULT 0.0,
|
||
|
||
PRIMARY KEY (steam_id_64, map_name),
|
||
FOREIGN KEY (steam_id_64) REFERENCES dm_players(steam_id_64)
|
||
);
|
||
```
|
||
|
||
### 2.4 辅助表：dm_player_weapon_stats
|
||
|
||
**用途**：武器使用统计（Top 10）
|
||
|
||
```sql
|
||
CREATE TABLE dm_player_weapon_stats (
|
||
steam_id_64 TEXT,
|
||
weapon_name TEXT,
|
||
|
||
total_kills INTEGER DEFAULT 0,
|
||
total_headshots INTEGER DEFAULT 0,
|
||
hs_rate REAL DEFAULT 0.0,
|
||
|
||
usage_rounds INTEGER DEFAULT 0, -- Rounds used this weapon
|
||
usage_rate REAL DEFAULT 0.0, -- % of all rounds
|
||
|
||
avg_kills_per_round REAL DEFAULT 0.0, -- When used
|
||
effectiveness_score REAL DEFAULT 0.0, -- Composite weapon skill
|
||
|
||
PRIMARY KEY (steam_id_64, weapon_name),
|
||
FOREIGN KEY (steam_id_64) REFERENCES dm_players(steam_id_64)
|
||
);
|
||
```
|
||
|
||
---
|
||
|
||
## Part 3: Processor Architecture
|
||
|
||
### 3.1 Processor职责划分
|
||
|
||
```
|
||
L3_Builder.py (主控)
|
||
├── BasicProcessor (Tier 1: CORE)
|
||
│ ├── calculate_basic_stats()
|
||
│ ├── calculate_match_stats()
|
||
│ ├── calculate_weapon_stats()
|
||
│ └── calculate_objective_stats()
|
||
│
|
||
├── TacticalProcessor (Tier 2: TACTICAL)
|
||
│ ├── calculate_opening_impact()
|
||
│ ├── calculate_multikill()
|
||
│ ├── calculate_clutch()
|
||
│ ├── calculate_utility()
|
||
│ └── calculate_economy()
|
||
│
|
||
├── IntelligenceProcessor (Tier 3: INTELLIGENCE)
|
||
│ ├── calculate_high_iq_kills()
|
||
│ ├── calculate_timing_analysis()
|
||
│ ├── calculate_pressure_performance()
|
||
│ ├── calculate_position_mastery() # Uses xyz
|
||
│ └── calculate_trade_network()
|
||
│
|
||
├── MetaProcessor (Tier 4: META)
|
||
│ ├── calculate_stability()
|
||
│ ├── calculate_side_preference()
|
||
│ ├── calculate_opponent_adaptation()
|
||
│ ├── calculate_map_specialization()
|
||
│ └── calculate_session_pattern()
|
||
│
|
||
└── CompositeProcessor (Tier 5: COMPOSITE)
|
||
├── normalize_and_standardize() # Z-score normalization
|
||
├── calculate_radar_scores() # 8 dimensions
|
||
└── classify_tier() # Elite/Advanced/Intermediate/Beginner
|
||
```
|
||
|
||
### 3.2 Processor接口标准
|
||
|
||
每个processor实现统一接口：
|
||
|
||
```python
|
||
class BaseFeatureProcessor:
|
||
@staticmethod
|
||
def calculate(steam_id: str, conn_l2: sqlite3.Connection) -> dict:
|
||
"""
|
||
计算该processor负责的所有特征
|
||
|
||
Args:
|
||
steam_id: 玩家Steam ID
|
||
conn_l2: L2数据库连接
|
||
|
||
Returns:
|
||
dict: {column_name: value, ...}
|
||
"""
|
||
pass
|
||
```
|
||
|
||
### 3.3 依赖关系
|
||
|
||
```
|
||
Tier 1 (CORE) → 无依赖，直接从L2计算
|
||
Tier 2 (TACTICAL) → 可能依赖Tier 1的total_rounds等基础值
|
||
Tier 3 (INTELLIGENCE) → 独立计算，从L2 events表
|
||
Tier 4 (META) → 依赖Tier 1的rating等基础统计
|
||
Tier 5 (COMPOSITE) → 依赖Tier 1-4的所有特征，最后计算
|
||
```
|
||
|
||
**计算顺序**：
|
||
1. BasicProcessor (CORE)
|
||
2. TacticalProcessor + IntelligenceProcessor (并行，无依赖)
|
||
3. MetaProcessor (需要CORE的rating)
|
||
4. CompositeProcessor (需要所有前置特征)
|
||
|
||
---
|
||
|
||
## Part 4: Web Services 架构
|
||
|
||
### 4.1 Service层重构
|
||
|
||
**原则**：
|
||
- **Services只做查询，不做计算**
|
||
- 复杂聚合逻辑在L3 Processor完成
|
||
- Service提供便捷的数据访问接口
|
||
|
||
```python
|
||
# web/services/player_service.py (新建)
|
||
class PlayerService:
|
||
"""玩家特征查询服务"""
|
||
|
||
@staticmethod
|
||
def get_player_features(steam_id: str) -> dict:
|
||
"""获取玩家完整特征（dm_player_features一行）"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_player_radar_data(steam_id: str) -> dict:
|
||
"""获取雷达图数据（8个维度）"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_player_core_stats(steam_id: str) -> dict:
|
||
"""获取核心统计（Dashboard用）"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_player_history(steam_id: str, limit: int = 20) -> list:
|
||
"""获取最近N场历史（趋势图用）"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_player_map_stats(steam_id: str) -> list:
|
||
"""获取各地图统计"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_player_weapon_stats(steam_id: str, top_n: int = 10) -> list:
|
||
"""获取Top N武器统计"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_players_ranking(
|
||
order_by: str = 'core_avg_rating',
|
||
limit: int = 100,
|
||
offset: int = 0
|
||
) -> list:
|
||
"""获取玩家排行榜"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def compare_players(steam_ids: list) -> dict:
|
||
"""对比多个玩家的特征"""
|
||
pass
|
||
```
|
||
|
||
```python
|
||
# web/services/stats_service.py (重构)
|
||
class StatsService:
|
||
"""统计分析服务（保留现有L2查询方法）"""
|
||
|
||
# 保留原有方法，用于match detail等非profile页面
|
||
@staticmethod
|
||
def get_match_stats(match_id: str) -> dict:
|
||
"""获取比赛统计（从L2 fact_matches）"""
|
||
pass
|
||
|
||
@staticmethod
|
||
def get_round_events(match_id: str, round_num: int) -> list:
|
||
"""获取回合事件（从L2 fact_round_events）"""
|
||
pass
|
||
|
||
# 新增：全局统计查询
|
||
@staticmethod
|
||
def get_global_stats() -> dict:
|
||
"""全局统计：总场次、总玩家、平均rating等"""
|
||
pass
|
||
```
|
||
|
||
### 4.2 Routes层适配
|
||
|
||
```python
|
||
# web/routes/players.py (重构)
|
||
from web.services.player_service import PlayerService
|
||
|
||
@bp.route('/profile/<steam_id>')
|
||
def player_profile(steam_id):
|
||
"""玩家Profile页面"""
|
||
# 1. 获取玩家基本信息（dim_players）
|
||
player_info = PlayerService.get_player_info(steam_id)
|
||
|
||
# 2. 获取特征数据（dm_player_features）
|
||
features = PlayerService.get_player_features(steam_id)
|
||
|
||
# 3. 获取历史趋势（dm_player_match_history）
|
||
history = PlayerService.get_player_history(steam_id, limit=20)
|
||
|
||
# 4. 获取地图统计（dm_player_map_stats）
|
||
map_stats = PlayerService.get_player_map_stats(steam_id)
|
||
|
||
# 5. 获取武器统计（dm_player_weapon_stats）
|
||
weapon_stats = PlayerService.get_player_weapon_stats(steam_id, top_n=10)
|
||
|
||
return render_template('players/profile.html',
|
||
player=player_info,
|
||
features=features,
|
||
history=history,
|
||
map_stats=map_stats,
|
||
weapon_stats=weapon_stats)
|
||
|
||
@bp.route('/api/players/<steam_id>/features')
|
||
def api_player_features(steam_id):
|
||
"""API: 获取玩家特征（JSON）"""
|
||
features = PlayerService.get_player_features(steam_id)
|
||
return jsonify(features)
|
||
|
||
@bp.route('/api/players/ranking')
|
||
def api_ranking():
|
||
"""API: 玩家排行榜"""
|
||
order_by = request.args.get('order_by', 'core_avg_rating')
|
||
limit = int(request.args.get('limit', 100))
|
||
offset = int(request.args.get('offset', 0))
|
||
|
||
players = PlayerService.get_players_ranking(
|
||
order_by=order_by,
|
||
limit=limit,
|
||
offset=offset
|
||
)
|
||
return jsonify(players)
|
||
```
|
||
|
||
### 4.3 Template数据映射
|
||
|
||
**profile.html结构**：
|
||
|
||
```jinja2
|
||
{# Dashboard Cards #}
|
||
<div class="dashboard">
|
||
<div class="card">Rating: {{ features.core_avg_rating }}</div>
|
||
<div class="card">K/D: {{ features.core_avg_kd }}</div>
|
||
<div class="card">ADR: {{ features.core_avg_adr }}</div>
|
||
<div class="card">KAST: {{ features.core_avg_kast }}%</div>
|
||
</div>
|
||
|
||
{# Radar Chart #}
|
||
<canvas id="radarChart" data-scores='{{
|
||
{
|
||
"aim": features.score_aim,
|
||
"clutch": features.score_clutch,
|
||
"pistol": features.score_pistol,
|
||
"defense": features.score_defense,
|
||
"utility": features.score_utility,
|
||
"stability": features.score_stability,
|
||
"economy": features.score_economy,
|
||
"pace": features.score_pace
|
||
} | tojson
|
||
}}'></canvas>
|
||
|
||
{# Trend Chart #}
|
||
<canvas id="trendChart" data-history='{{ history | tojson }}'></canvas>
|
||
|
||
{# Core Performance Section #}
|
||
<div class="stats-grid">
|
||
<div>Rating: {{ features.core_avg_rating | round(2) }}</div>
|
||
<div>K/D: {{ features.core_avg_kd | round(2) }}</div>
|
||
<div>KAST: {{ (features.core_avg_kast * 100) | round(1) }}%</div>
|
||
<div>RWS: {{ features.core_avg_rws | round(1) }}</div>
|
||
<div>ADR: {{ features.core_avg_adr | round(1) }}</div>
|
||
</div>
|
||
|
||
{# Gunfight Section #}
|
||
<div class="stats-grid">
|
||
<div>Avg HS: {{ features.core_avg_hs_kills | round(1) }}</div>
|
||
<div>HS Rate: {{ (features.core_hs_rate * 100) | round(1) }}%</div>
|
||
<div>Assists: {{ features.core_avg_assists | round(1) }}</div>
|
||
<div>AWP K: {{ features.core_avg_awp_kills | round(1) }}</div>
|
||
<div>Knife K: {{ features.core_avg_knife_kills | round(2) }}</div>
|
||
<div>Zeus K: {{ features.core_avg_zeus_kills | round(2) }}</div>
|
||
</div>
|
||
|
||
{# Opening Impact Section #}
|
||
<div class="stats-grid">
|
||
<div>FK: {{ features.tac_avg_fk | round(1) }}</div>
|
||
<div>FD: {{ features.tac_avg_fd | round(1) }}</div>
|
||
<div>FK Rate: {{ (features.tac_fk_rate * 100) | round(1) }}%</div>
|
||
<div>FD Rate: {{ (features.tac_fd_rate * 100) | round(1) }}%</div>
|
||
</div>
|
||
|
||
{# Clutch Section #}
|
||
<div class="stats-grid">
|
||
<div>1v1: {{ features.tac_clutch_1v1_wins }}/{{ features.tac_clutch_1v1_attempts }} ({{ (features.tac_clutch_1v1_rate * 100) | round(1) }}%)</div>
|
||
<div>1v2: {{ features.tac_clutch_1v2_wins }}/{{ features.tac_clutch_1v2_attempts }} ({{ (features.tac_clutch_1v2_rate * 100) | round(1) }}%)</div>
|
||
<div>1v3+: {{ features.tac_clutch_1v3_plus_wins }}/{{ features.tac_clutch_1v3_plus_attempts }} ({{ (features.tac_clutch_1v3_plus_rate * 100) | round(1) }}%)</div>
|
||
</div>
|
||
|
||
{# High IQ Kills Section #}
|
||
<div class="stats-grid">
|
||
<div>Wallbang: {{ features.int_wallbang_kills }} ({{ (features.int_wallbang_rate * 100) | round(2) }}%)</div>
|
||
<div>Smoke: {{ features.int_smoke_kills }} ({{ (features.int_smoke_kill_rate * 100) | round(2) }}%)</div>
|
||
<div>Blind: {{ features.int_blind_kills }} ({{ (features.int_blind_kill_rate * 100) | round(2) }}%)</div>
|
||
<div>NoScope: {{ features.int_noscope_kills }} ({{ (features.int_noscope_rate * 100) | round(2) }}%)</div>
|
||
<div>IQ Score: {{ features.int_high_iq_score | round(1) }}</div>
|
||
</div>
|
||
|
||
{# Map Stats Section #}
|
||
{% for map_stat in map_stats %}
|
||
<div class="map-row">
|
||
<span>{{ map_stat.map_name }}</span>
|
||
<span>{{ map_stat.matches }}场</span>
|
||
<span>{{ (map_stat.win_rate * 100) | round(1) }}%</span>
|
||
<span>{{ map_stat.avg_rating | round(2) }}</span>
|
||
</div>
|
||
{% endfor %}
|
||
|
||
{# Weapon Stats Section #}
|
||
{% for weapon in weapon_stats %}
|
||
<div class="weapon-row">
|
||
<span>{{ weapon.weapon_name }}</span>
|
||
<span>{{ weapon.total_kills }}击杀</span>
|
||
<span>{{ (weapon.hs_rate * 100) | round(1) }}% HS</span>
|
||
<span>{{ (weapon.usage_rate * 100) | round(1) }}%使用率</span>
|
||
</div>
|
||
{% endfor %}
|
||
```
|
||
|
||
---
|
||
|
||
## Part 5: 实施计划
|
||
|
||
### Phase 1: Schema & Infrastructure (1-2 days)
|
||
1. ✅ 创建L3 schema (dm_player_features + 辅助表)
|
||
2. ✅ 初始化L3.db
|
||
3. ✅ 创建processor基类
|
||
|
||
### Phase 2: Core Processors (2-3 days)
|
||
1. 实现BasicProcessor (Tier 1)
|
||
2. 实现TacticalProcessor (Tier 2)
|
||
3. 测试基础特征计算
|
||
|
||
### Phase 3: Advanced Processors (2-3 days)
|
||
1. 实现IntelligenceProcessor (Tier 3)
|
||
2. 实现MetaProcessor (Tier 4)
|
||
3. 实现CompositeProcessor (Tier 5)
|
||
|
||
### Phase 4: Services Refactoring (1-2 days)
|
||
1. 创建PlayerService
|
||
2. 重构StatsService
|
||
3. 更新Routes层
|
||
|
||
### Phase 5: Testing & Validation (1 day)
|
||
1. 运行L3_Builder完整构建
|
||
2. 验证特征计算正确性
|
||
3. Performance测试
|
||
|
||
### Phase 6: Frontend Integration (2 days)
|
||
1. 更新profile.html模板
|
||
2. 适配新的feature字段
|
||
3. 测试UI展示
|
||
|
||
---
|
||
|
||
## Part 6: 关键技术点
|
||
|
||
### 6.1 标准化与归一化
|
||
|
||
**Z-score标准化**（用于Composite Score）：
|
||
```python
|
||
def z_score_normalize(value, mean, std):
|
||
"""Z-score标准化到0-100"""
|
||
if std == 0:
|
||
return 50.0
|
||
z = (value - mean) / std
|
||
# 将z-score映射到0-100，mean=50
|
||
normalized = 50 + (z * 15) # ±3σ覆盖约99.7%
|
||
return max(0, min(100, normalized))
|
||
```
|
||
|
||
### 6.2 加权评分计算
|
||
|
||
**示例：AIM Score**
|
||
```python
|
||
def calculate_aim_score(features, all_players_stats):
|
||
"""
|
||
AIM Score = 25% Rating + 20% KD + 15% ADR + 10% DuelWin + 10% HighEloKD + 20% MultiKill
|
||
"""
|
||
weights = {
|
||
'rating': 0.25,
|
||
'kd': 0.20,
|
||
'adr': 0.15,
|
||
'duel_win': 0.10,
|
||
'high_elo_kd': 0.10,
|
||
'multikill': 0.20
|
||
}
|
||
|
||
# 分别标准化每个组件
|
||
rating_norm = z_score_normalize(features['core_avg_rating'],
|
||
all_players_stats['rating_mean'],
|
||
all_players_stats['rating_std'])
|
||
kd_norm = z_score_normalize(features['core_avg_kd'],
|
||
all_players_stats['kd_mean'],
|
||
all_players_stats['kd_std'])
|
||
# ... 其他组件
|
||
|
||
# 加权求和
|
||
aim_score = (rating_norm * weights['rating'] +
|
||
kd_norm * weights['kd'] +
|
||
# ... 其他)
|
||
|
||
return aim_score
|
||
```
|
||
|
||
### 6.3 时间窗口分析
|
||
|
||
**Trade Kill识别**（5秒窗口）：
|
||
```sql
|
||
WITH death_events AS (
|
||
SELECT
|
||
match_id, round_num, event_time,
|
||
victim_steam_id as dead_player,
|
||
attacker_steam_id as killer
|
||
FROM fact_round_events
|
||
WHERE event_type = 'kill' AND victim_steam_id IN (
|
||
SELECT steam_id FROM team_mates -- 同队队友
|
||
)
|
||
),
|
||
trade_kills AS (
|
||
SELECT
|
||
e1.attacker_steam_id,
|
||
COUNT(*) as trade_count
|
||
FROM fact_round_events e1
|
||
JOIN death_events d
|
||
ON e1.match_id = d.match_id
|
||
AND e1.round_num = d.round_num
|
||
AND e1.victim_steam_id = d.killer -- 杀死队友的敌人
|
||
AND e1.event_time BETWEEN d.event_time AND d.event_time + 5 -- 5秒内
|
||
WHERE e1.event_type = 'kill'
|
||
GROUP BY e1.attacker_steam_id
|
||
)
|
||
```
|
||
|
||
### 6.4 位置聚类分析
|
||
|
||
**基于xyz的位置分类**：
|
||
```python
|
||
from sklearn.cluster import DBSCAN
|
||
import numpy as np
|
||
|
||
def cluster_positions(xyz_data):
|
||
"""
|
||
使用DBSCAN聚类识别常用位置
|
||
|
||
Args:
|
||
xyz_data: [(x, y, z), ...]
|
||
|
||
Returns:
|
||
cluster_labels, position_names
|
||
"""
|
||
coords = np.array(xyz_data)
|
||
|
||
# DBSCAN参数：eps=距离阈值，min_samples=最小点数
|
||
clustering = DBSCAN(eps=500, min_samples=5).fit(coords)
|
||
|
||
labels = clustering.labels_
|
||
|
||
# 为每个cluster分配语义化名称（基于map区域）
|
||
position_names = map_cluster_to_semantic_name(coords, labels)
|
||
|
||
return labels, position_names
|
||
```
|
||
|
||
---
|
||
|
||
## Part 7: 数据质量保证
|
||
|
||
### 7.1 空值处理策略
|
||
|
||
```python
|
||
class SafeAggregator:
|
||
@staticmethod
|
||
def safe_divide(numerator, denominator, default=0.0):
|
||
"""安全除法"""
|
||
if denominator == 0 or denominator is None:
|
||
return default
|
||
return numerator / denominator
|
||
|
||
@staticmethod
|
||
def safe_avg(values, default=0.0):
|
||
"""安全平均"""
|
||
if not values or len(values) == 0:
|
||
return default
|
||
return sum(values) / len(values)
|
||
```
|
||
|
||
### 7.2 最小样本量要求
|
||
|
||
```python
|
||
MIN_MATCHES_FOR_FEATURES = {
|
||
'core': 5, # 基础统计至少5场
|
||
'tactical': 10, # 战术分析至少10场
|
||
'intelligence': 15, # 智能分析至少15场
|
||
'meta': 20, # 元数据分析至少20场
|
||
'composite': 20, # 综合评分至少20场
|
||
}
|
||
|
||
def check_sample_size(steam_id, tier):
|
||
"""检查是否满足最小样本量"""
|
||
match_count = get_player_match_count(steam_id)
|
||
return match_count >= MIN_MATCHES_FOR_FEATURES[tier]
|
||
```
|
||
|
||
---
|
||
|
||
## Part 8: 性能优化策略
|
||
|
||
### 8.1 批量计算
|
||
|
||
```python
|
||
# L3_Builder.py 主循环
|
||
def rebuild_all_features():
|
||
"""批量重建所有玩家特征"""
|
||
players = get_all_players() # 从dim_players获取
|
||
|
||
for player in players:
|
||
steam_id = player['steam_id_64']
|
||
|
||
# 计算所有特征
|
||
features = {}
|
||
features.update(BasicProcessor.calculate(steam_id, conn_l2))
|
||
features.update(TacticalProcessor.calculate(steam_id, conn_l2))
|
||
features.update(IntelligenceProcessor.calculate(steam_id, conn_l2))
|
||
features.update(MetaProcessor.calculate(steam_id, conn_l2))
|
||
features.update(CompositeProcessor.calculate(steam_id, conn_l2, features))
|
||
|
||
# 批量写入
|
||
upsert_player_features(steam_id, features)
|
||
|
||
# 每100个玩家提交一次
|
||
if len(batch) >= 100:
|
||
conn_l3.commit()
|
||
```
|
||
|
||
### 8.2 增量更新
|
||
|
||
```python
|
||
def update_player_features_incremental(steam_id, new_match_id):
|
||
"""增量更新：仅计算新增match影响的特征"""
|
||
# 1. 获取现有特征
|
||
old_features = get_player_features(steam_id)
|
||
|
||
# 2. 计算新match的统计
|
||
new_match_stats = get_match_player_stats(new_match_id, steam_id)
|
||
|
||
# 3. 增量更新（rolling average等）
|
||
updated_features = incremental_update(old_features, new_match_stats)
|
||
|
||
# 4. 更新数据库
|
||
upsert_player_features(steam_id, updated_features)
|
||
```
|
||
|
||
### 8.3 查询优化
|
||
|
||
```sql
|
||
-- 创建必要的索引
|
||
CREATE INDEX idx_match_players_steam ON fact_match_players(steam_id_64);
|
||
CREATE INDEX idx_round_events_attacker ON fact_round_events(attacker_steam_id);
|
||
CREATE INDEX idx_round_events_victim ON fact_round_events(victim_steam_id);
|
||
CREATE INDEX idx_round_events_time ON fact_round_events(match_id, round_num, event_time);
|
||
```
|
||
|
||
---
|
||
|
||
## 总结
|
||
|
||
本架构方案实现了：
|
||
|
||
✅ **特征去重**：消除Profile中的所有重复指标
|
||
✅ **深度挖掘**：利用rounds/events/economy数据进行高级特征工程
|
||
✅ **模块化设计**：5层processor清晰分工，易于维护扩展
|
||
✅ **服务解耦**：web/services只做查询，不做计算
|
||
✅ **性能优化**：批量计算 + 增量更新 + 查询索引
|
||
✅ **质量保证**：空值处理 + 最小样本量 + 标准化流程
|
||
|
||
**预期效果**：
|
||
- L3表包含207列精心设计的特征
|
||
- 支持完整的Profile界面展示
|
||
- 计算性能：1000玩家约10-15分钟
|
||
- 查询性能：单玩家profile加载 < 100ms
|
||
|
||
下一步开始实施！
|