bugfixing

app/cron_price_analysis.py

@@ -8,6 +8,7 @@
 from tqdm import tqdm
 import concurrent.futures
 import orjson
+import os
 
 def convert_symbols(symbol_list):
     converted_symbols = []
@@ -50,10 +51,13 @@ async def download_data(ticker: str, start_date: str, end_date: str):
         # Apply filtering logic if enough data exists
         if len(df) > 252 * 2:  # At least 2 years of history is necessary
             q_high = df["y"].quantile(0.99)
-            q_low = df["y"].quantile(0.01)
+            q_low = df["y"].quantile(0.1)
             df = df[(df["y"] > q_low) & (df["y"] < q_high)]
 
-        return df
+        # Calculate Simple Moving Average (SMA)
+        #df["y"] = df["y"].rolling(window=50).mean()  # 50-day SMA
+
+        return df.dropna()  # Drop initial NaN values due to rolling window
     except Exception as e:
         print(f"Error processing {ticker}: {e}")
         return None
@@ -62,10 +66,19 @@ async def process_symbol(ticker, start_date, end_date):
     try:
         df = await download_data(ticker, start_date, end_date)
         data = PricePredictor().run(df)
-        await save_json(ticker, data)
+        file_path = f"json/price-analysis/{ticker}.json"
+
+        if data and data['lowPriceTarget'] > 0:
+            print(data)
+            await save_json(ticker, data)
+        else:
+            await asyncio.to_thread(os.remove, file_path)
 
     except Exception as e:
-        print(e)
+        try:
+            await asyncio.to_thread(os.remove, file_path)
+        except FileNotFoundError:
+            pass  # The file might not exist, so we ignore the error
 
 
 async def run():
@@ -79,12 +92,16 @@ async def run():
 
     total_symbols = stock_symbols
     print(f"Total tickers: {len(total_symbols)}")
-    start_date = datetime(2017, 1, 1).strftime("%Y-%m-%d")
+    start_date = datetime(2015, 1, 1).strftime("%Y-%m-%d")
     end_date = datetime.today().strftime("%Y-%m-%d")
 
+    df_sp500 = await download_data('SPY', start_date, end_date)
+    df_sp500 = df_sp500.rename(columns={"y": "sp500"})
+    #print(df_sp500)
+
     chunk_size = len(total_symbols) // 70  # Divide the list into N chunks
     chunks = [total_symbols[i:i + chunk_size] for i in range(0, len(total_symbols), chunk_size)]
-    #chunks = [['NVDA','GME','TSLA','AAPL']]
+    #chunks = [['GME']]
     for chunk in chunks:
         tasks = []
         for ticker in tqdm(chunk):

app/ml_models/prophet_model.py

@@ -55,28 +55,34 @@ def __init__(self, predict_ndays=365):
             interval_width=0.8,
             daily_seasonality=True,
             yearly_seasonality=True,
+            changepoint_prior_scale= 0.1,
+            seasonality_prior_scale=0.1,
         )
+        #self.model.add_regressor('volume')
+
 
     def run(self, df):
+        df = df.copy()
+
         self.model.fit(df)
         future = self.model.make_future_dataframe(periods=self.predict_ndays)
         forecast = self.model.predict(future)
 
         # Apply rolling average to smooth the forecast intervals
         rolling_window = 200
-        forecast['smoothed_upper'] = forecast['yhat_upper'].round(2)#.rolling(window=rolling_window, min_periods=1).mean().round(2)
-        forecast['smoothed_lower'] = forecast['yhat_lower'].round(2)#.rolling(window=rolling_window, min_periods=1).mean().round(2)
-        forecast['smoothed_mean']  = forecast['yhat'].round(2)#.rolling(window=rolling_window, min_periods=1).mean().round(2)
+        forecast['smoothed_upper'] = forecast['yhat_upper'].rolling(window=rolling_window, min_periods=1).mean().round(2)
+        forecast['smoothed_lower'] = forecast['yhat_lower'].rolling(window=rolling_window, min_periods=1).mean().round(2)
+        forecast['smoothed_mean']  = forecast['yhat'].rolling(window=rolling_window, min_periods=1).mean().round(2)
 
         # Actual and predicted values for evaluation (optional)
         actual_values = df['y'].values
         predicted_values = forecast['yhat'].values[:-self.predict_ndays]
 
         # Extract forecast values for plotting or analysis (if needed)
         pred_date_list = forecast['ds'][-1200 - self.predict_ndays:].dt.strftime('%Y-%m-%d').tolist()
-        upper_list    = forecast['smoothed_upper'][-1200 - self.predict_ndays:].tolist()
-        lower_list    = forecast['smoothed_lower'][-1200 - self.predict_ndays:].tolist()
-        mean_list     = forecast['smoothed_mean'][-1200 - self.predict_ndays:].tolist()
+        upper_list = forecast['smoothed_upper'][-1200 - self.predict_ndays:].tolist()
+        lower_list = forecast['smoothed_lower'][-1200 - self.predict_ndays:].tolist()
+        mean_list = forecast['smoothed_mean'][-1200 - self.predict_ndays:].tolist()
 
         historical_date_list = df['ds'][-1200:].dt.strftime('%Y-%m-%d').tolist()
         historical_price_list = df['y'][-1200:].round(2).tolist()