diff --git a/AlphaGenerator.py b/AlphaGenerator.py
new file mode 100644
index 0000000..b52a3c7
--- /dev/null
+++ b/AlphaGenerator.py
@@ -0,0 +1,156 @@
+# -*- coding: utf-8 -*-
+import os
+import json
+import openai
+import httpx
+from datetime import datetime
+
+
+def load_config(config_file="ai_config.json"):
+    try:
+        with open(config_file, 'r', encoding='utf-8') as f:
+            return json.load(f)
+    except FileNotFoundError:
+        print(f"创建配置文件: {config_file}")
+        with open(config_file, 'w', encoding='utf-8') as f:
+            json.dump({}, f, indent=4)
+        print("请在config.json中配置siliconflow的api信息")
+        return None
+
+
+def create_prompt_file():
+    if not os.path.exists("alpha_prompt.txt"):
+        with open("alpha_prompt.txt", 'w', encoding='utf-8') as f:
+            f.write("")
+        print("已创建alpha_prompt.txt，请填入提示词后重新运行")
+        return False
+    return True
+
+
+def read_prompt():
+    with open("alpha_prompt.txt", 'r', encoding='utf-8') as f:
+        prompt = f.read().strip()
+    if not prompt:
+        print("alpha_prompt.txt是空的，请填入提示词")
+        return None
+    return prompt
+
+
+def create_result_folder():
+    # 修改这里：创建 generated_alpha 文件夹
+    folder_name = "generated_alpha"
+    if not os.path.exists(folder_name):
+        os.makedirs(folder_name)
+    return folder_name
+
+
+def call_siliconflow(api_key, prompt, model, base_url):
+    try:
+        client = openai.OpenAI(
+            api_key=api_key,
+            base_url=base_url
+        )
+
+        response = client.chat.completions.create(
+            model=model,
+            messages=[{"role": "user", "content": prompt}]
+        )
+
+        return response.choices[0].message.content
+
+    except openai.AuthenticationError:
+        print("API密钥错误")
+    except openai.RateLimitError:
+        print("调用频率限制")
+    except openai.APIError as e:
+        print(f"API错误: {e}")
+    except Exception as e:
+        print(f"其他错误: {e}")
+    return None
+
+
+def save_result(result, folder):
+    timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
+    filename = f"{timestamp}.txt"
+    filepath = os.path.join(folder, filename)
+
+    with open(filepath, 'w', encoding='utf-8') as f:
+        f.write(result)
+    print(f"结果保存到: {filepath}")
+
+
+def get_ai_config(config):
+    if not config:
+        return None
+
+    service_name = list(config.keys())[0]
+    service_config = config[service_name]
+
+    required_fields = ["api_keys", "model", "base_url"]
+    for field in required_fields:
+        if field not in service_config:
+            print(f"缺少配置字段: {field}")
+            return None
+
+    return service_name, service_config
+
+def get_user_info():
+    # 获取用户信息
+    with open('config.json', 'r') as f:
+        config = json.load(f)
+        siliconflow = config['siliconflow']
+        token = siliconflow['api_keys']
+
+    headers = {"Authorization": f"Bearer {token}"}
+
+    url = "https://api.siliconflow.cn/v1/user/info"
+
+    response = httpx.get(url, headers=headers)
+
+    data = response.json()['data']
+    balance = data['balance']
+    print(f"余额: {balance}")
+
+
+def main():
+    get_user_info()
+
+    config = load_config()
+    if not config:
+        return
+
+    if not create_prompt_file():
+        return
+
+    prompt = read_prompt()
+    if not prompt:
+        return
+
+    config_result = get_ai_config(config)
+    if not config_result:
+        return
+
+    service_name, service_config = config_result
+
+    print(f"使用服务: {service_name}")
+    print(f"使用模型: {service_config['model']}")
+
+    folder = create_result_folder()
+
+    print("正在调用AI...")
+    result = call_siliconflow(
+        service_config["api_keys"],
+        prompt,
+        service_config["model"],
+        service_config["base_url"]
+    )
+
+    if result:
+        print(f"AI回复: {result[:200]}...")
+        save_result(result, folder)
+    else:
+        print("AI调用失败")
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/FactorSimulator.py b/FactorSimulator.py
new file mode 100644
index 0000000..7179d33
--- /dev/null
+++ b/FactorSimulator.py
@@ -0,0 +1,202 @@
+# -*- coding: utf-8 -*-
+import os
+import time
+import json
+import httpx
+from httpx import BasicAuth
+
+
+class AlphaSimulator:
+    def __init__(self, credentials_file='account.txt'):
+        self.credentials_file = credentials_file
+        self.client = None
+        self.brain_api_url = 'https://api.worldquantbrain.com'
+
+    def load_credentials(self):
+        if not os.path.exists(self.credentials_file):
+            print("未找到 account.txt 文件")
+            with open(self.credentials_file, 'w') as f:
+                f.write("")
+            print("account.txt 文件已创建，请填写账号密码, 格式: ['username', 'password]")
+            exit(1)
+
+        with open(self.credentials_file) as f:
+            credentials = eval(f.read())
+        return credentials[0], credentials[1]
+
+    def login(self):
+        username, password = self.load_credentials()
+        self.client = httpx.Client(auth=BasicAuth(username, password))
+
+        response = self.client.post(f'{self.brain_api_url}/authentication')
+        print(f"登录状态: {response.status_code}")
+
+        if response.status_code == 201:
+            print("登录成功!")
+            return True
+        else:
+            print(f"登录失败: {response.json()}")
+            return False
+
+    def load_alpha_list(self, file_path='alpha.txt'):
+        if not os.path.exists(file_path):
+            print(f"{file_path} 文件不存在")
+            with open(file_path, 'w', encoding='utf-8') as file:
+                file.write("")
+            print(f"已创建 {file_path} 文件, 请添加因子后重新运行, 一行一个因子")
+            return []
+
+        with open(file_path, 'r', encoding='utf-8') as file:
+            alpha_list = [line.strip() for line in file if line.strip()]
+
+        return alpha_list
+
+    def simulate_alpha(self, expression):
+        if self.client is None:
+            raise Exception("请先登录")
+
+        settings = {
+            'instrumentType': 'EQUITY',
+            'region': 'USA',
+            'universe': 'TOP3000',
+            'delay': 1,
+            'decay': 0,
+            'neutralization': 'INDUSTRY',
+            'truncation': 0.08,
+            'pasteurization': 'ON',
+            'unitHandling': 'VERIFY',
+            'nanHandling': 'OFF',
+            'language': 'FASTEXPR',
+            'visualization': False,
+        }
+
+        simulation_data = {
+            'type': 'REGULAR',
+            'settings': settings,
+            'regular': expression
+        }
+
+        sim_resp = self.client.post(f'{self.brain_api_url}/simulations', json=simulation_data)
+        print(f"模拟提交状态: {sim_resp.status_code}")
+
+        sim_progress_url = sim_resp.headers['location']
+
+        while True:
+            sim_progress_resp = self.client.get(sim_progress_url)
+            retry_after_sec = float(sim_progress_resp.headers.get("Retry-After", 0))
+
+            if retry_after_sec == 0:
+                break
+
+            if sim_progress_resp.json():
+                result = sim_progress_resp.json()
+                progress = result.get('progress', 0)
+                print(f"模拟进度: {float(progress) * 100}%")
+
+            print(f"等待 {retry_after_sec} 秒...")
+            time.sleep(retry_after_sec)
+
+        if sim_progress_resp.json().get("status") == "ERROR":
+            result = sim_progress_resp.json().get("message", "未知错误")
+            print(f"因子模拟失败: {result}")
+            return {"status": "error", "message": result}
+
+        alpha_id = sim_progress_resp.json().get("alpha")
+        print(f"生成的Alpha ID: {alpha_id}")
+
+        return {"status": "success", "alpha_id": alpha_id}
+
+    def run_batch_simulation(self, alpha_list, batch_size=3):
+        success_results = []
+        fail_results = []
+
+        for i in range(0, len(alpha_list), batch_size):
+            batch = alpha_list[i:i + batch_size]
+            print(f"\n开始处理第 {i // batch_size + 1} 批因子，共 {len(batch)} 个")
+
+            for expression in batch:
+                print(f"\n模拟因子: {expression}")
+                start_time = time.time()
+
+                try:
+                    result = self.simulate_alpha(expression)
+                    end_time = time.time()
+                    time_consuming = end_time - start_time
+
+                    result_data = {
+                        "expression": expression,
+                        "time_consuming": round(time_consuming, 2),
+                        "status": result["status"],
+                        "timestamp": time.strftime("%Y-%m-%d %H:%M:%S")
+                    }
+
+                    if result["status"] == "success":
+                        result_data["alpha_id"] = result["alpha_id"]
+                        success_results.append(result_data)
+                        print(f"✅ 模拟成功 - Alpha ID: {result['alpha_id']} - 耗时: {time_consuming:.2f}秒")
+                    else:
+                        result_data["message"] = result.get("message", "")
+                        fail_results.append(result_data)
+                        print(f"❌ 模拟失败 - {result.get('message', '未知错误')}")
+
+                except Exception as e:
+                    end_time = time.time()
+                    time_consuming = end_time - start_time
+                    error_result = {
+                        "expression": expression,
+                        "time_consuming": round(time_consuming, 2),
+                        "status": "error",
+                        "message": str(e),
+                        "timestamp": time.strftime("%Y-%m-%d %H:%M:%S")
+                    }
+                    fail_results.append(error_result)
+                    print(f"❌ 模拟异常 - {str(e)}")
+
+            print(f"第 {i // batch_size + 1} 批处理完成")
+
+        self._save_results(success_results, fail_results)
+        return success_results, fail_results
+
+    def _save_results(self, success_results, fail_results):
+        base_dir = 'simulator_result'
+        success_dir = os.path.join(base_dir, 'success')
+        fail_dir = os.path.join(base_dir, 'fail')
+
+        os.makedirs(success_dir, exist_ok=True)
+        os.makedirs(fail_dir, exist_ok=True)
+
+        timestamp = str(int(time.time()))
+
+        if success_results:
+            success_file = os.path.join(success_dir, f"success_results_{timestamp}.json")
+            with open(success_file, 'w', encoding='utf-8') as f:
+                json.dump(success_results, f, ensure_ascii=False, indent=2)
+            print(f"成功结果已保存到 {success_file}")
+
+        if fail_results:
+            fail_file = os.path.join(fail_dir, f"fail_results_{timestamp}.json")
+            with open(fail_file, 'w', encoding='utf-8') as f:
+                json.dump(fail_results, f, ensure_ascii=False, indent=2)
+            print(f"失败结果已保存到 {fail_file}")
+
+        print(f"\n总计: 成功 {len(success_results)} 个, 失败 {len(fail_results)} 个")
+
+
+def main():
+    simulator = AlphaSimulator()
+
+    if not simulator.login():
+        return
+
+    alpha_list = simulator.load_alpha_list('alpha.txt')
+    if not alpha_list:
+        print("未找到有效的因子表达式，请检查 alpha.txt 文件")
+        return
+
+    print(f"共加载 {len(alpha_list)} 个因子表达式")
+
+    simulator.run_batch_simulation(alpha_list, batch_size=3)
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/FieldDownloader.py b/FieldDownloader.py
new file mode 100644
index 0000000..1ba8597
--- /dev/null
+++ b/FieldDownloader.py
@@ -0,0 +1,195 @@
+import os
+import json
+import random
+import time
+import httpx
+from httpx import BasicAuth
+
+
+class BrainLogin:
+    def __init__(self, credentials_file='account.txt'):
+        self.credentials_file = credentials_file
+        self.client = None
+        self.brain_api_url = 'https://api.worldquantbrain.com'
+
+    def load_credentials(self):
+        if not os.path.exists(self.credentials_file):
+            print("未找到 account.txt 文件")
+            with open(self.credentials_file, 'w') as f:
+                f.write("")
+            print("account.txt 文件已创建，请填写账号密码, 格式: ['username', 'password']")
+            exit(1)
+
+        with open(self.credentials_file) as f:
+            credentials = eval(f.read())
+        return credentials[0], credentials[1]
+
+    def login(self):
+        try:
+            username, password = self.load_credentials()
+            self.client = httpx.Client(auth=BasicAuth(username, password))
+
+            response = self.client.post(f'{self.brain_api_url}/authentication')
+            print(f"登录状态: {response.status_code}")
+
+            if response.status_code in [200, 201]:
+                print("登录成功!")
+                print(f"账户信息: {response.json()}")
+                return self.client
+            else:
+                print(f"登录失败: {response.json()}")
+                return None
+
+        except Exception as e:
+            print(f"登录过程中出现错误: {e}")
+            return None
+
+    def get_client(self):
+        return self.client
+
+
+class DataSetDownloader:
+    def __init__(self, client):
+        self.client = client
+        self.base_api_url = 'https://api.worldquantbrain.com'
+
+    def debug_detailed_response(self, endpoint, data_set_id, offset, limit=20):
+        print(f"\n=== 调试请求: {endpoint} ===")
+        url = f"{self.base_api_url}/{endpoint}"
+        params = {
+            'dataset.id': data_set_id,
+            'delay': 1,
+            'instrumentType': 'EQUITY',
+            'limit': limit,
+            'offset': offset,
+            'region': 'USA',
+            'universe': 'TOP3000'
+        }
+
+        response = self.client.get(url, params=params)
+
+        if response.status_code == 200:
+            data = response.json()
+            print(f"count: {data.get('count')}")
+            print(f"results 长度: {len(data.get('results', []))}")
+            print(f"响应键: {list(data.keys())}")
+
+    def process_data(self, raw_data):
+        processed_data = []
+
+        for item in raw_data:
+            processed_item = {
+                'id': item.get('id', ''),
+                'description': item.get('description', ''),
+                'dataset_id': item.get('dataset', {}).get('id', ''),
+                'dataset_name': item.get('dataset', {}).get('name', ''),
+                'category_id': item.get('category', {}).get('id', ''),
+                'category_name': item.get('category', {}).get('name', ''),
+                'region': item.get('region', ''),
+                'delay': item.get('delay', ''),
+                'universe': item.get('universe', ''),
+                'type': item.get('type', '')
+            }
+            processed_data.append(processed_item)
+
+        return processed_data
+
+    def download_data_set(self, endpoint, data_set_id):
+        output_dir = 'reference_fields'
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+
+        self.debug_detailed_response(endpoint, data_set_id, offset=0, limit=20)
+
+        url = f"{self.base_api_url}/{endpoint}"
+        params = {
+            'dataset.id': data_set_id,
+            'delay': 1,
+            'instrumentType': 'EQUITY',
+            'limit': 1,
+            'offset': 0,
+            'region': 'USA',
+            'universe': 'TOP3000'
+        }
+
+        response = self.client.get(url, params=params)
+        data = response.json()
+        total_count = data.get('count', 0)
+
+        print(f"📊 数据集总数: {total_count}")
+
+        if total_count == 0:
+            print("❌ 没有找到数据")
+            return
+
+        limit = 50
+        all_data = []
+
+        print("🚀 开始下载数据...")
+        for offset in range(0, total_count, limit):
+            sleep_time = random.uniform(1.0, 1.5)
+            time.sleep(sleep_time)
+
+            params = {
+                'dataset.id': data_set_id,
+                'delay': 1,
+                'instrumentType': 'EQUITY',
+                'limit': limit,
+                'offset': offset,
+                'region': 'USA',
+                'universe': 'TOP3000'
+            }
+
+            print(f"📥 下载进度: {offset}/{total_count} ({offset / total_count * 100:.1f}%)")
+
+            try:
+                response = self.client.get(url, params=params)
+
+                if response.status_code == 200:
+                    data = response.json()
+                    results = data.get('results', [])
+
+                    print(f"✅ 本页获取到 {len(results)} 条记录")
+                    all_data.extend(results)
+                    print(f"✅ 累计获取 {len(all_data)} 条记录")
+
+                    if len(results) < limit:
+                        print("🎯 到达数据末尾")
+                        break
+                else:
+                    print(f"❌ 请求失败: {response.status_code}")
+                    break
+
+            except Exception as e:
+                print(f"❌ 下载过程中出错: {e}")
+                break
+
+        print("🔄 处理数据中...")
+        processed_data = self.process_data(all_data)
+
+        output_file = os.path.join(output_dir, f"{data_set_id}_{endpoint}.json")
+        with open(output_file, 'w', encoding='utf-8') as f:
+            json.dump(processed_data, f, ensure_ascii=False, indent=2)
+
+        print(f"💾 处理后的数据已保存到: {output_file}")
+        print(f"🎉 总共处理了 {len(processed_data)} 条记录")
+
+        if processed_data:
+            print("\n📋 处理后数据示例:")
+            print(json.dumps(processed_data[0], indent=2, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    brain_login = BrainLogin()
+    client = brain_login.login()
+
+    if client:
+        downloader = DataSetDownloader(client)
+
+        endpoint_list = ['data-sets', 'data-fields']
+        endpoint = endpoint_list[1]
+        data_set_id = 'news18'
+
+        downloader.download_data_set(endpoint, data_set_id)
+    else:
+        print("❌ 登录失败，无法下载数据")
\ No newline at end of file
diff --git a/wqb-filter-alpha/account.txt b/account.txt
similarity index 100%
rename from wqb-filter-alpha/account.txt
rename to account.txt
diff --git a/ai_config.json b/ai_config.json
new file mode 100644
index 0000000..ba31892
--- /dev/null
+++ b/ai_config.json
@@ -0,0 +1,7 @@
+{
+  "siliconflow": {
+    "base_url": "https://api.siliconflow.cn/v1",
+    "api_keys": "sk-pvdiisdowmuwkrpnxsrlhxaovicqibmlljwrwwvbbdjaitdl",
+    "model": "Qwen/Qwen3-VL-235B-A22B-Instruct"
+  }
+}
\ No newline at end of file
diff --git a/alpha.txt b/alpha.txt
new file mode 100644
index 0000000..6224201
--- /dev/null
+++ b/alpha.txt
@@ -0,0 +1 @@
+group_mean(ts_rank(volume, 252), industry)
\ No newline at end of file
diff --git a/alpha_prompt.txt b/alpha_prompt.txt
new file mode 100644
index 0000000..11e72c8
--- /dev/null
+++ b/alpha_prompt.txt
@@ -0,0 +1,37 @@
+【重要平台约束】
+平台：WorldQuant WebSim
+可用函数：ts_*(时间序列), group_*(横截面), 基础数学运算
+可用字段：open, high, low, close, volume, vwap, sector, industry, country, market_cap
+禁用函数：pandas, numpy, 自定义Python函数，机器学习库
+输出格式：严格一行WebSim表达式，使用WQ平台函数
+表达式要求：必须能直接在WebSim中运行
+
+我正在WorldQuant研究行业轮动策略，请设计行业选择因子：
+
+**策略背景**：
+- 目标：在不同经济周期中选择强势行业
+- 数据：使用sector, industry分类字段
+- 频率：月度调仓
+- 风险：控制行业集中度
+
+**需要5个行业因子**：
+1. 行业动量因子（相对强度）
+2. 行业估值修复因子（均值回归）
+3. 行业资金流向因子（量价结合）
+4. 行业波动率特征因子（风险调整）
+5. 行业间相对强度因子（横截面）
+
+**具体要求**：
+- 必须使用group函数处理行业分组
+- 每个因子包含清晰的行业轮动逻辑
+- 考虑行业特性的持久性
+- 提供经济周期适应的解释
+
+**输出格式**(一行一个, 不要输出多余的东西)：
+[表达式]
+[表达式]
+[表达式]
+...
+
+请提供具体的WQ表达式。
+重申：请确保所有表达式都使用WorldQuant WebSim平台函数，不要使用pandas、numpy或其他Python库函数。输出必须是一行有效的WQ表达式。
\ No newline at end of file
diff --git a/wq101alphas/alpha101_code/01-alpha因子编写 b/reference_data/wq101alphas/alpha101_code/01-alpha因子编写
similarity index 100%
rename from wq101alphas/alpha101_code/01-alpha因子编写
rename to reference_data/wq101alphas/alpha101_code/01-alpha因子编写
diff --git a/wq101alphas/alpha101_code/02-基于万矿计算因子数据 b/reference_data/wq101alphas/alpha101_code/02-基于万矿计算因子数据
similarity index 100%
rename from wq101alphas/alpha101_code/02-基于万矿计算因子数据
rename to reference_data/wq101alphas/alpha101_code/02-基于万矿计算因子数据
diff --git a/wq101alphas/alpha101_code/03-单因子IC测试 b/reference_data/wq101alphas/alpha101_code/03-单因子IC测试
similarity index 100%
rename from wq101alphas/alpha101_code/03-单因子IC测试
rename to reference_data/wq101alphas/alpha101_code/03-单因子IC测试
diff --git a/wq101alphas/alpha101_code/04-单因子分层测试 b/reference_data/wq101alphas/alpha101_code/04-单因子分层测试
similarity index 100%
rename from wq101alphas/alpha101_code/04-单因子分层测试
rename to reference_data/wq101alphas/alpha101_code/04-单因子分层测试
diff --git a/wq101alphas/alpha101_code/05-回测相关处理函数 b/reference_data/wq101alphas/alpha101_code/05-回测相关处理函数
similarity index 100%
rename from wq101alphas/alpha101_code/05-回测相关处理函数
rename to reference_data/wq101alphas/alpha101_code/05-回测相关处理函数
diff --git a/wq101alphas/alpha101_code/06-有效因子回测 b/reference_data/wq101alphas/alpha101_code/06-有效因子回测
similarity index 100%
rename from wq101alphas/alpha101_code/06-有效因子回测
rename to reference_data/wq101alphas/alpha101_code/06-有效因子回测
diff --git a/wq101alphas/alpha101_code/README.md b/reference_data/wq101alphas/alpha101_code/README.md
similarity index 100%
rename from wq101alphas/alpha101_code/README.md
rename to reference_data/wq101alphas/alpha101_code/README.md
diff --git a/wq101alphas/wq101alpha.dos b/reference_data/wq101alphas/wq101alpha.dos
similarity index 100%
rename from wq101alphas/wq101alpha.dos
rename to reference_data/wq101alphas/wq101alpha.dos
diff --git a/wq101alphas/wq101alpha.json b/reference_data/wq101alphas/wq101alpha.json
similarity index 100%
rename from wq101alphas/wq101alpha.json
rename to reference_data/wq101alphas/wq101alpha.json
diff --git a/wq101alphas/wq101alpha2json.py b/reference_data/wq101alphas/wq101alpha2json.py
similarity index 100%
rename from wq101alphas/wq101alpha2json.py
rename to reference_data/wq101alphas/wq101alpha2json.py
diff --git a/reference_fields/news18_data-fields.json b/reference_fields/news18_data-fields.json
new file mode 100644
index 0000000..9f0876e
--- /dev/null
+++ b/reference_fields/news18_data-fields.json
@@ -0,0 +1,902 @@
+[
+  {
+    "id": "nws18_acb",
+    "description": "News sentiment specializing in corporate action announcements",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_bam",
+    "description": "News sentiment specializing in mergers and acquisitions",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_bee",
+    "description": "News sentiment specializing in growth of earnings",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_ber",
+    "description": "News sentiment specializing in earnings result",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_event_relevance",
+    "description": "Relevance of the event to the story",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_event_similarity_days",
+    "description": "Days since a similar event was detected",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_ghc_lna",
+    "description": "Change in analyst recommendation",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_nip",
+    "description": "Degree of impact of the news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_qcm",
+    "description": "News sentiment of relevant news with high confidence",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_qep",
+    "description": "News sentiment based on positive and negative words on global equity",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_qmb",
+    "description": "News sentiment specializing in editorials on global markets",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_relevance",
+    "description": "Relevance of news to the company",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_ssc",
+    "description": "Sentiment of the news calculated using multiple techniques",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "nws18_sse",
+    "description": "Sentiment of phrases impacting the company",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "VECTOR"
+  },
+  {
+    "id": "rp_css_assets",
+    "description": "Composite sentiment score of assets news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_business",
+    "description": "Composite sentiment score of business-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_credit",
+    "description": "Composite sentiment score of credit news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_credit_ratings",
+    "description": "Composite sentiment score of credit ratings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_dividends",
+    "description": "Composite sentiment score of dividends news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_earnings",
+    "description": "Composite sentiment score of earnings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_equity",
+    "description": "Composite sentiment score of equity action news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_insider",
+    "description": "Composite sentiment score of insider trading news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_inverstor",
+    "description": "Composite sentiment score of investor relations news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_labor",
+    "description": "Composite sentiment score of labor issues news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_legal",
+    "description": "Composite sentiment score of legal news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_marketing",
+    "description": "Composite sentiment score of marketing news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_mna",
+    "description": "Composite sentiment score of mergers and acquisitions-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_partner",
+    "description": "Composite sentiment score of partnership news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_price",
+    "description": "Composite sentiment score of stock price news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_product",
+    "description": "Composite sentiment score of product and service-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_ptg",
+    "description": "Composite sentiment score of price target news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_ratings",
+    "description": "Composite sentiment score of analyst ratings-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_revenue",
+    "description": "Composite sentiment score of revenue news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_society",
+    "description": "Composite sentiment score of society-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_css_technical",
+    "description": "Composite sentiment score based on technical analysis",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_assets",
+    "description": "Event sentiment score of assets news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_business",
+    "description": "Event sentiment score of business-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_credit",
+    "description": "Event sentiment score of credit news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_credit_ratings",
+    "description": "Event sentiment score of credit ratings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_dividends",
+    "description": "Event sentiment score of dividends news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_earnings",
+    "description": "Event sentiment score of earnings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_equity",
+    "description": "Event sentiment score of equity action news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_insider",
+    "description": "Event sentiment score of insider trading news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_labor",
+    "description": "Event sentiment score of labor issues news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_legal",
+    "description": "Event sentiment score of legal news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_mna",
+    "description": "Event sentiment score of mergers and acquisitions-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_partner",
+    "description": "Event sentiment score of partnership news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_price",
+    "description": "Event sentiment score of stock price news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_product",
+    "description": "Event sentiment score of product and service-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_ptg",
+    "description": "Event sentiment score of price target news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_ratings",
+    "description": "Event sentiment score of analyst ratings-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_revenue",
+    "description": "Event sentiment score of revenue news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_society",
+    "description": "Event sentiment score of society-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_ess_technical",
+    "description": "Event sentiment score based on technical analysis",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_assets",
+    "description": "News impact projection of assets news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_business",
+    "description": "News impact projection of business-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_credit",
+    "description": "News impact projection of credit news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_credit_ratings",
+    "description": "News impact projection of credit ratings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_dividends",
+    "description": "News impact projection of dividends news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_earnings",
+    "description": "News impact projection of earnings news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_equity",
+    "description": "News impact projection of equity action news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_insider",
+    "description": "News impact projection of insider trading news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_inverstor",
+    "description": "News impact projection of investor relations news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_labor",
+    "description": "News impact projection of labor issues news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_legal",
+    "description": "News impact projection of legal news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_marketing",
+    "description": "News impact projection of marketing news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_mna",
+    "description": "News impact projection of mergers and acquisitions-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_partner",
+    "description": "News impact projection of partnership news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_price",
+    "description": "News impact projection of stock price news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_product",
+    "description": "News impact projection of product and service-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_ptg",
+    "description": "News impact projection of price target news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_ratings",
+    "description": "News impact projection of analyst ratings-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_revenue",
+    "description": "News impact projection of revenue news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_society",
+    "description": "News impact projection of society-related news",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  },
+  {
+    "id": "rp_nip_technical",
+    "description": "News impact projection based on technical analysis",
+    "dataset_id": "news18",
+    "dataset_name": "Ravenpack News Data",
+    "category_id": "news",
+    "category_name": "News",
+    "region": "USA",
+    "delay": 1,
+    "universe": "TOP3000",
+    "type": "MATRIX"
+  }
+]
\ No newline at end of file
diff --git a/simulator_result/fail/fail_results_1764034041.json b/simulator_result/fail/fail_results_1764034041.json
new file mode 100644
index 0000000..a3d2fd3
--- /dev/null
+++ b/simulator_result/fail/fail_results_1764034041.json
@@ -0,0 +1,9 @@
+[
+  {
+    "expression": "group_mean(ts_rank(volume, 252), industry)",
+    "time_consuming": 6.65,
+    "status": "error",
+    "timestamp": "2025-11-25 09:27:21",
+    "message": "Invalid number of inputs : 2, should be exactly 3 input(s)"
+  }
+]
\ No newline at end of file
diff --git a/demo_generating_factor/test001.py b/test/demo_generating_factor/test001.py
similarity index 100%
rename from demo_generating_factor/test001.py
rename to test/demo_generating_factor/test001.py
diff --git a/demo_yfinance/demo.py b/test/demo_yfinance/demo.py
similarity index 100%
rename from demo_yfinance/demo.py
rename to test/demo_yfinance/demo.py
diff --git a/wqb-demo/alphas.json b/test/wqb-demo/alphas.json
similarity index 100%
rename from wqb-demo/alphas.json
rename to test/wqb-demo/alphas.json
diff --git a/wqb-demo/brain_credentials.txt b/test/wqb-demo/brain_credentials.txt
similarity index 100%
rename from wqb-demo/brain_credentials.txt
rename to test/wqb-demo/brain_credentials.txt
diff --git a/wqb-demo/main.py b/test/wqb-demo/main.py
similarity index 100%
rename from wqb-demo/main.py
rename to test/wqb-demo/main.py
diff --git a/wqb-demo/main_simple.py b/test/wqb-demo/main_simple.py
similarity index 100%
rename from wqb-demo/main_simple.py
rename to test/wqb-demo/main_simple.py
diff --git a/wqb-demo/simulation_results.json b/test/wqb-demo/simulation_results.json
similarity index 100%
rename from wqb-demo/simulation_results.json
rename to test/wqb-demo/simulation_results.json
diff --git a/wqb-simulate/account.txt b/test/wqb-filter-alpha/account.txt
similarity index 100%
rename from wqb-simulate/account.txt
rename to test/wqb-filter-alpha/account.txt
diff --git a/wqb-filter-alpha/filter-alpha.py b/test/wqb-filter-alpha/filter-alpha.py
similarity index 100%
rename from wqb-filter-alpha/filter-alpha.py
rename to test/wqb-filter-alpha/filter-alpha.py
diff --git a/wqb-login/brain_credentials.txt b/test/wqb-login/account.txt
similarity index 100%
rename from wqb-login/brain_credentials.txt
rename to test/wqb-login/account.txt
diff --git a/wqb-login/login.py b/test/wqb-login/login.py
similarity index 73%
rename from wqb-login/login.py
rename to test/wqb-login/login.py
index b30249a..9532230 100644
--- a/wqb-login/login.py
+++ b/test/wqb-login/login.py
@@ -1,9 +1,16 @@
 import httpx
 from httpx import BasicAuth
+import os
 
-def login(credentials_file='brain_credentials.txt'):
+def login(credentials_file='account.txt'):
     """登录WorldQuant Brain API"""
     # 读取本地账号密码
+    if not os.path.exists(credentials_file):
+        print("未找到 account.txt 文件")
+        with open(credentials_file, 'w') as f: f.write("")
+        print("account.txt 文件已创建，请填写账号密码, 格式: ['username', 'password]")
+        exit(1)
+
     with open(credentials_file) as f:
         credentials = eval(f.read())
     username, password = credentials[0], credentials[1]
diff --git a/test/wqb-simulate/account.txt b/test/wqb-simulate/account.txt
new file mode 100644
index 0000000..5cfaa62
--- /dev/null
+++ b/test/wqb-simulate/account.txt
@@ -0,0 +1 @@
+['jack0210_@hotmail.com', '!QAZ2wsx+0913']
\ No newline at end of file
diff --git a/wqb-simulate/alpha.txt b/test/wqb-simulate/alpha.txt
similarity index 100%
rename from wqb-simulate/alpha.txt
rename to test/wqb-simulate/alpha.txt
diff --git a/wqb-simulate/simulate.py b/test/wqb-simulate/simulate.py
similarity index 100%
rename from wqb-simulate/simulate.py
rename to test/wqb-simulate/simulate.py
diff --git a/wqb-test/main.py b/test/wqb-test/main.py
similarity index 100%
rename from wqb-test/main.py
rename to test/wqb-test/main.py