AmineTMIRI/backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

model fix

Browse Source
This commit is contained in:
MuslemRahimi 2025-02-17 23:35:02 +01:00
parent 1c1dd11635
commit 387d4e8353
2 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
app/cron_price_analysis.py
View File

@ -65,11 +65,12 @@ async def run():
total_symbols = stock_symbols total_symbols = stock_symbols
print(f"Total tickers: {len(total_symbols)}") print(f"Total tickers: {len(total_symbols)}")
start_date = datetime(2015, 1, 1).strftime("%Y-%m-%d") start_date = datetime(2020, 1, 1).strftime("%Y-%m-%d")
end_date = datetime.today().strftime("%Y-%m-%d") end_date = datetime.today().strftime("%Y-%m-%d")
chunk_size = len(total_symbols) // 70 # Divide the list into N chunks 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 = [total_symbols[i:i + chunk_size] for i in range(0, len(total_symbols), chunk_size)]
#chunks = [['TSLA']]
for chunk in chunks: for chunk in chunks:
tasks = [] tasks = []
for ticker in tqdm(chunk): for ticker in tqdm(chunk):

22
app/ml_models/prophet_model.py
View File

@ -64,9 +64,9 @@ class PricePredictor:
# Apply rolling average to smooth the forecast intervals # Apply rolling average to smooth the forecast intervals
rolling_window = 200 rolling_window = 200
forecast['smoothed_upper'] = forecast['yhat_upper'].rolling(window=rolling_window, min_periods=1).mean().round(2) forecast['smoothed_upper'] = forecast['yhat_upper'].round(2)#.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_lower'] = forecast['yhat_lower'].round(2)#.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) forecast['smoothed_mean'] = forecast['yhat'].round(2)#.rolling(window=rolling_window, min_periods=1).mean().round(2)
# Actual and predicted values for evaluation (optional) # Actual and predicted values for evaluation (optional)
actual_values = df['y'].values actual_values = df['y'].values
@ -81,16 +81,23 @@ class PricePredictor:
historical_date_list = df['ds'][-1200:].dt.strftime('%Y-%m-%d').tolist() historical_date_list = df['ds'][-1200:].dt.strftime('%Y-%m-%d').tolist()
historical_price_list = df['y'][-1200:].round(2).tolist() historical_price_list = df['y'][-1200:].round(2).tolist()
metrics_dict = {
'mse': mean_squared_error(actual_values, predicted_values),
'mae': mean_absolute_error(actual_values, predicted_values),
'r2': r2_score(actual_values, predicted_values)}
print("Metrics:", metrics_dict)
# Get monthly historical data and round the close value # Get monthly historical data and round the close value
monthly_historical_data = get_monthly_historical_data(df) monthly_historical_data = get_monthly_historical_data(df)
monthly_historical_data = [{**item, 'close': round(item['close'], 2)} for item in monthly_historical_data] monthly_historical_data = [{**item, 'close': round(item['close'], 2)} for item in monthly_historical_data]
future_forecast = forecast[forecast['ds'] > df['ds'].max()]['smoothed_mean'] future_forecast = forecast[forecast['ds'] > df['ds'].max()]['smoothed_mean']
if not future_forecast.empty: median_price = round(np.mean([
median_price = round(np.median(future_forecast), 2) forecast['smoothed_lower'].iloc[-1],
else: forecast['smoothed_mean'].iloc[-1],
median_price = round(forecast['smoothed_mean'].iloc[-1], 2) forecast['smoothed_upper'].iloc[-1]
]), 2)
# Latest actual price from the dataset # Latest actual price from the dataset
latest_price = round(df['y'].iloc[-1], 2) latest_price = round(df['y'].iloc[-1], 2)
@ -101,7 +108,6 @@ class PricePredictor:
'highPriceTarget': upper_list[-1], 'highPriceTarget': upper_list[-1],
'lowPriceTarget': lower_list[-1], 'lowPriceTarget': lower_list[-1],
'medianPriceTarget': median_price, 'medianPriceTarget': median_price,
'latestPrice': latest_price
} }