Erroneous float calculations.

[krsna-sentieo]

🐛 Bug Description

When an expression is being evaluated, I think the series is changed into np.float32 and when returning back its being changed back to np.float64. Calculation results are in fact erroneous.

To Reproduce

d = get_quote_data([ticker], fields=['$close', '$volume', 'Mul($close, $volume)'], start_time='2020-10-23', end_time='2020-10-30')

Expected Behavior

The actual value should be 3989893260.0

Screenshot

Environment

Note: One could run python scripts/collect_info.py under the qlib directory to get the following information.

• Qlib version:
• Python version:
• OS (Windows, Linux, MacOS):
• Commit number (optional, please provide it if you are using the dev version):

Additional Notes

[you-n-g]

This is the accuracy issue of float32.
Qlib use np.float32 as the default type to store and calculate values. We may support using higher default accuracy in the future(This may use more resource.)

[krsna-sentieo]

why would you need to change it back to np.float64? This is one more issue.

[you-n-g]

@krsna-sentieo Thanks for your feedback.
The conversion issue is fixed here #62
We'll merge it after your issue is fixed.
Before you test it, please remove previous cache.

rm ~/.qlib/qlib_data/cn_data/dataset_cache -r

The higher accuracy storage and calculation will be supported in the future.

[krsna-sentieo]

@you-n-g Thanks, This is good.

[you-n-g]

#62 has been merged now.
We'll keep this issue open until we add the feature to set the default accuracy.

Your feedbacks are really valuable.
Thanks!