pranjal-joshi / Screeni-py

A Python-based stock screener to find stocks with potential breakout probability from NSE India.
MIT License
552 stars 195 forks source link

Lorentzian Classifier (Machine Learning based indicator) doesn't work for 7D candle duration #228

Closed adityaladwa closed 8 months ago

adityaladwa commented 9 months ago

Describe the bug The Lorentzian Classifier, when used with option 6 as screening criteria and option 7 as type of reversal doesn't give results for 7D candle duration instead returns for 1D candle duration

To Reproduce

Select the following configuration

Screenshot 2023-12-17 at 5 47 49 PM Screenshot 2023-12-17 at 5 47 42 PM

Expected behavior The screener should output stocks for the given options using 7D candle duration

pranjal-joshi commented 9 months ago

Hi @adityaladwa Use duration of 1wk instead of 7d Also increase the period to 3y or 5y as you need more historical data as because the timeframe is weekly now Also, in the second screenshot, I can see 7 results are found. So please describe the issue with further details if it doesn't work with the configuration suggested above

adityaladwa commented 9 months ago

thanks, using 1wk worked for duration 👍

Also, in the second screenshot, I can see 7 results are found. So please describe the issue with further details if it doesn't work with the configuration suggested above

yes, when using 7D, I'm still getting same results as for 1D so raised this issue

Also, is there any reference I can use to understand the configurations in more detail?

pranjal-joshi commented 9 months ago

@adityaladwa

Looks like you're running an older version The latest version provides drop-downs for configuration attributes so you can choose the valid configuration

adityaladwa commented 9 months ago

thank you @pranjal-joshi using latest version now 👍

github-actions[bot] commented 8 months ago

This Issue is marked as Stale due to Inactivity. This Issue will be Closed soon.