trump-code-market-signals

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Trump Code — Market Signal Analysis

Trump Code — 市场信号分析

Skill by ara.so — Daily 2026 Skills collection.

Trump Code is an open-source system that applies brute-force computation to find statistically significant patterns between Trump's Truth Social/X posting behavior and S&P 500 movements. It has tested 31.5M model combinations, maintains 551 surviving rules, and has a verified 61.3% hit rate across 566 predictions (z=5.39, p<0.05).

由ara.so开发的Skill — 2026每日技能合集。

Trump Code是一个开源系统，通过暴力计算寻找特朗普在Truth Social/X上的发帖行为与标普500指数走势之间的统计显著模式。它已测试了3150万种模型组合，保留了551条有效规则，在566次预测中验证的命中率达61.3%（z=5.39，p<0.05）。

Installation

安装

bash

git clone https://github.com/sstklen/trump-code.git
cd trump-code
pip install -r requirements.txt

bash

git clone https://github.com/sstklen/trump-code.git
cd trump-code
pip install -r requirements.txt

Environment Variables

环境变量

bash

undefined

bash

undefined

Required for AI briefing and chatbot

AI简报和聊天机器人所需

export GEMINI_KEYS="key1,key2,key3" # Comma-separated Gemini API keys

export GEMINI_KEYS="key1,key2,key3" # 逗号分隔的Gemini API密钥

Optional: for Claude Opus deep analysis

可选：用于Claude Opus深度分析

export ANTHROPIC_API_KEY="your-key-here"

Optional: for Polymarket/Kalshi integration

可选：用于Polymarket/Kalshi集成

export POLYMARKET_API_KEY="your-key-here"

undefined

export POLYMARKET_API_KEY="your-key-here"

undefined

CLI — Key Commands

CLI — 核心命令

bash

undefined

bash

undefined

Today's detected signals from Trump's posts

今日从特朗普帖子中检测到的信号

python3 trump_code_cli.py signals

Model performance leaderboard (all 11 named models)

模型性能排行榜（全部11个命名模型）

python3 trump_code_cli.py models

Get LONG/SHORT consensus prediction

获取多模型一致的LONG/SHORT预测

python3 trump_code_cli.py predict

Prediction market arbitrage opportunities

预测市场套利机会

python3 trump_code_cli.py arbitrage

System health check (circuit breaker state)

系统健康检查（熔断机制状态）

python3 trump_code_cli.py health

Full daily report (trilingual)

完整每日报告（三语言）

python3 trump_code_cli.py report

Dump all data as JSON

导出所有数据为JSON格式

python3 trump_code_cli.py json

undefined

python3 trump_code_cli.py json

undefined

Core Scripts

核心脚本

bash

undefined

bash

undefined

Real-time Trump post monitor (polls every 5 min)

实时特朗普帖子监控（每5分钟轮询一次）

python3 realtime_loop.py

Brute-force model search (~25 min, tests millions of combos)

暴力模型搜索（约25分钟，测试数百万种组合）

python3 overnight_search.py

Individual analyses

独立分析脚本

python3 analysis_06_market.py # Posts vs S&P 500 correlation python3 analysis_09_combo_score.py # Multi-signal combo scoring

python3 analysis_06_market.py # 帖子与标普500指数相关性分析 python3 analysis_09_combo_score.py # 多信号组合评分

Web dashboard + AI chatbot on port 8888

网页仪表盘 + AI聊天机器人（端口8888）

export GEMINI_KEYS="key1,key2,key3" python3 chatbot_server.py

→ http://localhost:8888

undefined

undefined

REST API (Live at trumpcode.washinmura.jp)

REST API（部署于trumpcode.washinmura.jp）

python

import requests

BASE = "https://trumpcode.washinmura.jp"

python

import requests

BASE = "https://trumpcode.washinmura.jp"

All dashboard data in one call

一次性获取所有仪表盘数据

data = requests.get(f"{BASE}/api/dashboard").json()

Today's signals + 7-day history

今日信号 + 7天历史数据

signals = requests.get(f"{BASE}/api/signals").json()

Model performance rankings

模型性能排名

models = requests.get(f"{BASE}/api/models").json()

Latest 20 Trump posts with signal tags

带信号标签的最新20条特朗普帖子

posts = requests.get(f"{BASE}/api/recent-posts").json()

Live Polymarket Trump prediction markets (316+)

Polymarket平台上的特朗普相关实时预测市场（316+个）

markets = requests.get(f"{BASE}/api/polymarket-trump").json()

LONG/SHORT playbooks

LONG/SHORT操作指南

playbook = requests.get(f"{BASE}/api/playbook").json()

System health / circuit breaker state

系统健康状态 / 熔断机制状态

status = requests.get(f"{BASE}/api/status").json()

undefined

status = requests.get(f"{BASE}/api/status").json()

undefined

AI Chatbot API

AI聊天机器人API

python

import requests

response = requests.post(
    "https://trumpcode.washinmura.jp/api/chat",
    json={"message": "What signals fired today and what's the consensus?"}
)
print(response.json()["reply"])

python

import requests

response = requests.post(
    "https://trumpcode.washinmura.jp/api/chat",
    json={"message": "今天触发了哪些信号？一致预测是什么？"}
)
print(response.json()["reply"])

MCP Server (Claude Code / Cursor Integration)

MCP服务器（Claude Code / Cursor集成）

Add to

~/.claude/settings.json

json

{
  "mcpServers": {
    "trump-code": {
      "command": "python3",
      "args": ["/path/to/trump-code/mcp_server.py"]
    }
  }
}

Available MCP tools:

signals

models

predict

arbitrage

health

events

dual_platform

crowd

full_report

添加到

~/.claude/settings.json

json

{
  "mcpServers": {
    "trump-code": {
      "command": "python3",
      "args": ["/path/to/trump-code/mcp_server.py"]
    }
  }
}

可用MCP工具：

signals

models

predict

arbitrage

health

events

dual_platform

crowd

full_report

Open Data Files

开放数据文件

All data lives in

data/

and is updated daily:

python

import json, pathlib

DATA = pathlib.Path("data")

所有数据存储在

data/

目录下，每日更新：

python

import json, pathlib

DATA = pathlib.Path("data")

44,000+ Truth Social posts

44000+条Truth Social帖子

posts = json.loads((DATA / "trump_posts_all.json").read_text())

Posts with signals pre-tagged

预标记信号的帖子

posts_lite = json.loads((DATA / "trump_posts_lite.json").read_text())

566 verified predictions with outcomes

566条带结果的已验证预测

predictions = json.loads((DATA / "predictions_log.json").read_text())

551 active rules (brute-force + evolved)

551条有效规则（暴力测试+进化生成）

rules = json.loads((DATA / "surviving_rules.json").read_text())

384 features × 414 trading days

384个特征 × 414个交易日

features = json.loads((DATA / "daily_features.json").read_text())

S&P 500 OHLC history

标普500指数OHLC历史数据

market = json.loads((DATA / "market_SP500.json").read_text())

Circuit breaker / system health

熔断机制 / 系统健康状态

cb = json.loads((DATA / "circuit_breaker_state.json").read_text())

Rule evolution log (crossover/mutation)

规则进化日志（交叉/突变）

evo = json.loads((DATA / "evolution_log.json").read_text())

undefined

evo = json.loads((DATA / "evolution_log.json").read_text())

undefined

Download Data via API

通过API下载数据

python

import requests

BASE = "https://trumpcode.washinmura.jp"

python

import requests

BASE = "https://trumpcode.washinmura.jp"

List available datasets

查看可用数据集

catalog = requests.get(f"{BASE}/api/data").json()

Download a specific file

下载指定文件

raw = requests.get(f"{BASE}/api/data/surviving_rules.json").content rules = json.loads(raw)

undefined

raw = requests.get(f"{BASE}/api/data/surviving_rules.json").content rules = json.loads(raw)

undefined

Real Code Examples

实际代码示例

Parse Today's Signals

解析今日信号

python

import requests

signals_data = requests.get("https://trumpcode.washinmura.jp/api/signals").json()

today = signals_data.get("today", {})
print("Signals fired today:", today.get("signals", []))
print("Consensus:", today.get("consensus"))        # "LONG" / "SHORT" / "NEUTRAL"
print("Confidence:", today.get("confidence"))      # 0.0–1.0
print("Active models:", today.get("active_models", []))

python

import requests

signals_data = requests.get("https://trumpcode.washinmura.jp/api/signals").json()

today = signals_data.get("today", {})
print("今日触发的信号:", today.get("signals", []))
print("一致预测:", today.get("consensus"))        # "LONG" / "SHORT" / "NEUTRAL"
print("置信度:", today.get("confidence"))      # 0.0–1.0
print("活跃模型:", today.get("active_models", []))

Find Top Performing Rules from Surviving Rules

从有效规则中筛选表现最佳的规则

python

import json

rules = json.loads(open("data/surviving_rules.json").read())

python

import json

rules = json.loads(open("data/surviving_rules.json").read())

Sort by hit rate descending

按命中率降序排序

top_rules = sorted(rules, key=lambda r: r.get("hit_rate", 0), reverse=True)

for rule in top_rules[:10]: print(f"Rule: {rule['id']} | Hit Rate: {rule['hit_rate']:.1%} | " f"Trades: {rule['n_trades']} | Avg Return: {rule['avg_return']:.3%}")

undefined

top_rules = sorted(rules, key=lambda r: r.get("hit_rate", 0), reverse=True)

for rule in top_rules[:10]: print(f"规则ID: {rule['id']} | 命中率: {rule['hit_rate']:.1%} | " f"交易次数: {rule['n_trades']} | 平均收益: {rule['avg_return']:.3%}")

undefined

Check Prediction Market Opportunities

寻找预测市场机会

python

import requests

arb = requests.get("https://trumpcode.washinmura.jp/api/insights").json()
markets = requests.get("https://trumpcode.washinmura.jp/api/polymarket-trump").json()

python

import requests

arb = requests.get("https://trumpcode.washinmura.jp/api/insights").json()
markets = requests.get("https://trumpcode.washinmura.jp/api/polymarket-trump").json()

Markets sorted by volume

按交易量排序的市场

active = [m for m in markets.get("markets", []) if m.get("active")] by_volume = sorted(active, key=lambda m: m.get("volume", 0), reverse=True)

for m in by_volume[:5]: print(f"{m['title']}: YES={m['yes_price']:.0%} | Vol=${m['volume']:,.0f}")

undefined

active = [m for m in markets.get("markets", []) if m.get("active")] by_volume = sorted(active, key=lambda m: m.get("volume", 0), reverse=True)

for m in by_volume[:5]: print(f"{m['title']}: YES={m['yes_price']:.0%} | 交易量=${m['volume']:,.0f}")

undefined

Correlate Post Features with Returns

关联帖子特征与收益

python

import json
import numpy as np

features = json.loads(open("data/daily_features.json").read())
market   = json.loads(open("data/market_SP500.json").read())

python

import json
import numpy as np

features = json.loads(open("data/daily_features.json").read())
market   = json.loads(open("data/market_SP500.json").read())

Build date-indexed return map

构建日期索引的收益映射

returns = {d["date"]: d["close_pct"] for d in market}

Example: correlate post_count with next-day return

示例：关联发帖数量与次日收益

xs, ys = [], [] for day in features: date = day["date"] if date in returns: xs.append(day.get("post_count", 0)) ys.append(returns[date])

correlation = np.corrcoef(xs, ys)[0, 1] print(f"Post count vs same-day return: r={correlation:.3f}")

undefined

xs, ys = [], [] for day in features: date = day["date"] if date in returns: xs.append(day.get("post_count", 0)) ys.append(returns[date])

correlation = np.corrcoef(xs, ys)[0, 1] print(f"发帖数量 vs 当日收益: r={correlation:.3f}")

undefined

Run a Backtest on a Custom Signal

对自定义信号进行回测

python

import json

posts    = json.loads(open("data/trump_posts_lite.json").read())
market   = json.loads(open("data/market_SP500.json").read())

returns  = {d["date"]: d["close_pct"] for d in market}

python

import json

posts    = json.loads(open("data/trump_posts_lite.json").read())
market   = json.loads(open("data/market_SP500.json").read())

returns  = {d["date"]: d["close_pct"] for d in market}

Find days with RELIEF signal before 9:30 AM ET

寻找开盘前（9:30 AM前）出现RELIEF信号的日期

relief_days = [ p["date"] for p in posts if "RELIEF" in p.get("signals", []) and p.get("hour", 24) < 9 ]

hits = [returns[d] for d in relief_days if d in returns] if hits: print(f"RELIEF pre-market: n={len(hits)}, " f"avg={sum(hits)/len(hits):.3%}, " f"hit_rate={sum(1 for h in hits if h > 0)/len(hits):.1%}")

undefined

relief_days = [ p["date"] for p in posts if "RELIEF" in p.get("signals", []) and p.get("hour", 24) < 9 ]

hits = [returns[d] for d in relief_days if d in returns] if hits: print(f"开盘前RELIEF信号: 样本数={len(hits)}, " f"平均收益={sum(hits)/len(hits):.3%}, " f"命中率={sum(1 for h in hits if h > 0)/len(hits):.1%}")

undefined

Key Signal Types

核心信号类型

Signal	Description	Typical Impact
`RELIEF` pre-market	"Relief" language before 9:30 AM	Avg +1.12% same-day
`TARIFF` market hours	Tariff mention during trading	Avg -0.758% next day
`DEAL`	Deal/agreement language	52.2% hit rate
`CHINA` (Truth Social only)	China mentions (never on X)	1.5× weight boost
`SILENCE`	Zero-post day	80% bullish, avg +0.409%
Burst → silence	Rapid posting then goes quiet	65.3% LONG signal

信号	描述	典型影响
`RELIEF` 开盘前	9:30 AM前发布含“宽慰”类语言的帖子	当日平均涨幅+1.12%
`TARIFF` 交易时段	交易时间内提及关税	次日平均跌幅-0.758%
`DEAL`	提及交易/协议相关内容	命中率52.2%
`CHINA` （仅Truth Social）	提及中国（从未在X上出现）	权重提升1.5倍
`SILENCE`	当日无发帖	80%概率上涨，平均涨幅+0.409%
爆发式发帖→沉默	快速发帖后陷入沉寂	65.3%概率触发LONG信号

Model Reference

模型参考

Model	Strategy	Hit Rate	Avg Return
A3	Pre-market RELIEF → surge	72.7%	+1.206%
D3	Volume spike → panic bottom	70.2%	+0.306%
D2	Signature switch → formal statement	70.0%	+0.472%
C1	Burst → long silence → LONG	65.3%	+0.145%
C3 ⚠️	Late-night tariff (anti-indicator)	37.5%	−0.414%

Note: C3 is an anti-indicator — if it fires, the circuit breaker auto-inverts it to LONG (62% accuracy after inversion).

模型	策略	命中率	平均收益
A3	开盘前RELIEF信号→上涨	72.7%	+1.206%
D3	交易量激增→恐慌底部	70.2%	+0.306%
D2	发帖风格切换→正式声明	70.0%	+0.472%
C1	爆发式发帖→长时间沉寂→LONG	65.3%	+0.145%
C3 ⚠️	深夜提及关税（反向指标）	37.5%	−0.414%

注意： C3是反向指标——若触发该信号，熔断机制会自动将其反转成LONG信号（反转后准确率62%）。

System Architecture Flow

系统架构流程

Truth Social post detected (every 5 min)
    → Classify signals (RELIEF / TARIFF / DEAL / CHINA / etc.)
    → Dual-platform boost (TS-only China = 1.5× weight)
    → Snapshot Polymarket + S&P 500
    → Run 551 surviving rules → generate prediction
    → Track at 1h / 3h / 6h
    → Verify outcome → update rule weights
    → Circuit breaker: if system degrades → pause/invert
    → Daily: evolve rules (crossover / mutation / distillation)
    → Sync data to GitHub

检测到Truth Social新帖子（每5分钟一次）
    → 信号分类（RELIEF / TARIFF / DEAL / CHINA 等）
    → 双平台权重提升（仅Truth Social的China提及权重×1.5）
    → 快照Polymarket数据 + 标普500指数
    → 运行551条有效规则→生成预测
    → 按1小时/3小时/6小时跟踪结果
    → 验证结果→更新规则权重
    → 熔断机制：若系统性能下降→暂停/反转信号
    → 每日：规则进化（交叉/突变/蒸馏）
    → 同步数据至GitHub

Troubleshooting

故障排除

realtime_loop.py
not detecting new posts

Check your network access to Truth Social scraper endpoints
Verify
```
data/trump_posts_all.json
```
timestamp is recent
Run
```
python3 trump_code_cli.py health
```
to see circuit breaker state

chatbot_server.py
fails to start

Ensure

GEMINI_KEYS

env var is set:

export GEMINI_KEYS="key1,key2"

Port 8888 may be in use:
```
lsof -i :8888
```

overnight_search.py
runs out of memory

Runs ~31.5M combinations — needs ~4GB RAM
Run on a machine with 8GB+ or reduce search space in script config

Hit rate dropping below 55%

Check
```
data/circuit_breaker_state.json
```
— system may have auto-paused
Review
```
data/learning_report.json
```
for demoted rules
Re-run
```
overnight_search.py
```
to refresh surviving rules

Stale data in
data/
directory

Daily pipeline syncs to GitHub automatically if running
Manually trigger:
```
python3 trump_code_cli.py report
```
to force refresh
Or pull latest from remote:
```
git pull origin main
```

realtime_loop.py
无法检测到新帖子

检查Truth Social爬虫端点的网络访问权限
验证
```
data/trump_posts_all.json
```
的时间戳是否为近期
运行
```
python3 trump_code_cli.py health
```
查看熔断机制状态

chatbot_server.py
启动失败

确保已设置

GEMINI_KEYS

环境变量：

export GEMINI_KEYS="key1,key2"

端口8888可能被占用：使用
```
lsof -i :8888
```
检查

overnight_search.py
内存不足

需测试约3150万种组合——需约4GB内存
在8GB+内存的机器上运行，或在脚本配置中缩小搜索范围

命中率降至55%以下

查看
```
data/circuit_breaker_state.json
```
——系统可能已自动暂停
查看
```
data/learning_report.json
```
了解被降级的规则
重新运行
```
overnight_search.py
```
刷新有效规则

data/
目录数据过时

若系统正常运行，每日流水线会自动同步至GitHub
手动触发刷新：运行
```
python3 trump_code_cli.py report
```
或从远程拉取最新数据：
```
git pull origin main
```