Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[GPT] enable historical signals fetch #1089

Merged
merged 7 commits into from
Oct 27, 2023
Merged

[GPT] enable historical signals fetch #1089

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
505eae5
[GPT] enable historical signals fetch
GuillaumeDSM Oct 25, 2023
f016c10
[GPT] ask gpt in async_evaluation
GuillaumeDSM Oct 27, 2023
eea6b3b
[GPT] add full candles request
GuillaumeDSM Oct 27, 2023
f663668
[Profiles] do not select duplicated profiles
GuillaumeDSM Oct 27, 2023
ea9c9c1
[GPT] docs update
GuillaumeDSM Oct 27, 2023
b7192d4
[DisplayedElements] add symbols and timeframe params to fill
GuillaumeDSM Oct 27, 2023
c140f56
[GPTEvaluator] fix tests
GuillaumeDSM Oct 27, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Evaluator/TA/ai_evaluator/ai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ def __init__(self, tentacles_setup_config):
self.indicator = None
self.source = None
self.period = None
self.min_confidence_threshold = 0
self.min_confidence_threshold = 100
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the default value?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, we don't want to round to 1 below 100% confidence by default

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not sure I understand. I haven't seen any 100% confidence value sent by gpt

self.gpt_model = gpt_service.GPTService.DEFAULT_MODEL
self.is_backtesting = False
self.min_allowed_timeframe = os.getenv("MIN_GPT_TIMEFRAME", None)
Expand Down
7 changes: 6 additions & 1 deletion Evaluator/TA/ai_evaluator/tests/test_ai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,8 @@ def test_indicators(GPT_evaluator):
def test_get_candles_data_api(GPT_evaluator):
for source in GPT_evaluator.SOURCES:
GPT_evaluator.source = source
assert isinstance(GPT_evaluator.get_candles_data_api(), types.FunctionType)
if GPT_evaluator.source not in GPT_evaluator.get_unformated_sources():
assert isinstance(GPT_evaluator.get_candles_data_api(), types.FunctionType)


def test_parse_prediction_side(GPT_evaluator):
Expand All @@ -57,3 +58,7 @@ def test_parse_confidence(GPT_evaluator):
assert GPT_evaluator._parse_confidence("up 54.33%") == 54.33
assert GPT_evaluator._parse_confidence("down 70% confidence blablabla") == 70
assert GPT_evaluator._parse_confidence("Prediction: down 70%") == 70
GPT_evaluator.min_confidence_threshold = 60
assert GPT_evaluator._parse_confidence("up 70%") == 100
assert GPT_evaluator._parse_confidence("up 60%") == 100
assert GPT_evaluator._parse_confidence("up 59%") == 59