Merge pull request #245 from TauricResearch/feat/tooloptim

Y Finance Tools Optimizations

Author: EdwardoSunny

README.md

@@ -127,7 +127,7 @@ cp .env.example .env
 # Edit .env with your actual API keys
 ```
 
-**Note:** The default configuration uses [Alpha Vantage](https://www.alphavantage.co/) for fundamental and news data. You can get a free API key from their website, or upgrade to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for higher rate limits and more stable access. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.
+**Note:** We are happy to partner with Alpha Vantage to provide robust API support for TradingAgents. You can get a free AlphaVantage API [here](https://www.alphavantage.co/support/#api-key), TradingAgents-sourced requests also have increased rate limits to 60 requests per minute with no daily limits. Typically the quota is sufficient for performing complex tasks with TradingAgents thanks to Alpha Vantage’s open-source support program. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.
 
 ### CLI Usage
 

pyproject.toml

@@ -12,6 +12,7 @@ dependencies = [
     "eodhd>=1.0.32",
     "feedparser>=6.0.11",
     "finnhub-python>=2.4.23",
+    "grip>=4.6.2",
     "langchain-anthropic>=0.3.15",
     "langchain-experimental>=0.3.4",
     "langchain-google-genai>=2.1.5",

test.py

@@ -0,0 +1,11 @@
+import time
+from tradingagents.dataflows.y_finance import get_YFin_data_online, get_stock_stats_indicators_window, get_balance_sheet as get_yfinance_balance_sheet, get_cashflow as get_yfinance_cashflow, get_income_statement as get_yfinance_income_statement, get_insider_transactions as get_yfinance_insider_transactions
+
+print("Testing optimized implementation with 30-day lookback:")
+start_time = time.time()
+result = get_stock_stats_indicators_window("AAPL", "macd", "2024-11-01", 30)
+end_time = time.time()
+
+print(f"Execution time: {end_time - start_time:.2f} seconds")
+print(f"Result length: {len(result)} characters")
+print(result)

tradingagents/dataflows/y_finance.py

@@ -137,16 +137,42 @@ def get_stock_stats_indicators_window(
     curr_date_dt = datetime.strptime(curr_date, "%Y-%m-%d")
     before = curr_date_dt - relativedelta(days=look_back_days)
 
-    # online gathering only
-    ind_string = ""
-    while curr_date_dt >= before:
-        indicator_value = get_stockstats_indicator(
-            symbol, indicator, curr_date_dt.strftime("%Y-%m-%d")
-        )
-
-        ind_string += f"{curr_date_dt.strftime('%Y-%m-%d')}: {indicator_value}\n"
-
-        curr_date_dt = curr_date_dt - relativedelta(days=1)
+    # Optimized: Get stock data once and calculate indicators for all dates
+    try:
+        indicator_data = _get_stock_stats_bulk(symbol, indicator, curr_date)
+        
+        # Generate the date range we need
+        current_dt = curr_date_dt
+        date_values = []
+        
+        while current_dt >= before:
+            date_str = current_dt.strftime('%Y-%m-%d')
+            
+            # Look up the indicator value for this date
+            if date_str in indicator_data:
+                indicator_value = indicator_data[date_str]
+            else:
+                indicator_value = "N/A: Not a trading day (weekend or holiday)"
+            
+            date_values.append((date_str, indicator_value))
+            current_dt = current_dt - relativedelta(days=1)
+        
+        # Build the result string
+        ind_string = ""
+        for date_str, value in date_values:
+            ind_string += f"{date_str}: {value}\n"
+        
+    except Exception as e:
+        print(f"Error getting bulk stockstats data: {e}")
+        # Fallback to original implementation if bulk method fails
+        ind_string = ""
+        curr_date_dt = datetime.strptime(curr_date, "%Y-%m-%d")
+        while curr_date_dt >= before:
+            indicator_value = get_stockstats_indicator(
+                symbol, indicator, curr_date_dt.strftime("%Y-%m-%d")
+            )
+            ind_string += f"{curr_date_dt.strftime('%Y-%m-%d')}: {indicator_value}\n"
+            curr_date_dt = curr_date_dt - relativedelta(days=1)
 
     result_str = (
         f"## {indicator} values from {before.strftime('%Y-%m-%d')} to {end_date}:\n\n"
@@ -158,6 +184,89 @@ def get_stock_stats_indicators_window(
     return result_str
 
 
+def _get_stock_stats_bulk(
+    symbol: Annotated[str, "ticker symbol of the company"],
+    indicator: Annotated[str, "technical indicator to calculate"],
+    curr_date: Annotated[str, "current date for reference"]
+) -> dict:
+    """
+    Optimized bulk calculation of stock stats indicators.
+    Fetches data once and calculates indicator for all available dates.
+    Returns dict mapping date strings to indicator values.
+    """
+    from .config import get_config
+    import pandas as pd
+    from stockstats import wrap
+    import os
+    
+    config = get_config()
+    online = config["data_vendors"]["technical_indicators"] != "local"
+    
+    if not online:
+        # Local data path
+        try:
+            data = pd.read_csv(
+                os.path.join(
+                    config.get("data_cache_dir", "data"),
+                    f"{symbol}-YFin-data-2015-01-01-2025-03-25.csv",
+                )
+            )
+            df = wrap(data)
+        except FileNotFoundError:
+            raise Exception("Stockstats fail: Yahoo Finance data not fetched yet!")
+    else:
+        # Online data fetching with caching
+        today_date = pd.Timestamp.today()
+        curr_date_dt = pd.to_datetime(curr_date)
+        
+        end_date = today_date
+        start_date = today_date - pd.DateOffset(years=15)
+        start_date_str = start_date.strftime("%Y-%m-%d")
+        end_date_str = end_date.strftime("%Y-%m-%d")
+        
+        os.makedirs(config["data_cache_dir"], exist_ok=True)
+        
+        data_file = os.path.join(
+            config["data_cache_dir"],
+            f"{symbol}-YFin-data-{start_date_str}-{end_date_str}.csv",
+        )
+        
+        if os.path.exists(data_file):
+            data = pd.read_csv(data_file)
+            data["Date"] = pd.to_datetime(data["Date"])
+        else:
+            data = yf.download(
+                symbol,
+                start=start_date_str,
+                end=end_date_str,
+                multi_level_index=False,
+                progress=False,
+                auto_adjust=True,
+            )
+            data = data.reset_index()
+            data.to_csv(data_file, index=False)
+        
+        df = wrap(data)
+        df["Date"] = df["Date"].dt.strftime("%Y-%m-%d")
+    
+    # Calculate the indicator for all rows at once
+    df[indicator]  # This triggers stockstats to calculate the indicator
+    
+    # Create a dictionary mapping date strings to indicator values
+    result_dict = {}
+    for _, row in df.iterrows():
+        date_str = row["Date"]
+        indicator_value = row[indicator]
+        
+        # Handle NaN/None values
+        if pd.isna(indicator_value):
+            result_dict[date_str] = "N/A"
+        else:
+            result_dict[date_str] = str(indicator_value)
+    
+    return result_dict
+
+
 def get_stockstats_indicator(
     symbol: Annotated[str, "ticker symbol of the company"],
     indicator: Annotated[str, "technical indicator to get the analysis and report of"],