Turning Level-2 Minute Bars into Daily High-Frequency Features

Summary

This platform support note explains the intended use of a high-frequency feature extraction module. It takes fields from a specified Level-2, one-minute Chinese stock bar table and applies expressions compatible with pandas and NumPy to calculate daily-frequency factors. The key point is that the module aggregates or transforms minute-level inputs into daily features; it is not a general-purpose interface for arbitrary inputs.

The note points users to reference materials but does not provide a worked expression, an example of a missing-value failure, or diagnostic steps for a None result. Its guidance is therefore limited to the expected input table and expression conventions. Researchers still need to check that their selected fields exist in the source data and that the expression produces a valid daily output.

Key ideas

• The feature extraction module is designed to convert minute-level Level-2 stock data into daily factors.
• Its inputs should be fields from the specified one-minute Chinese stock bar table.
• Expressions are expected to follow pandas- and NumPy-compatible conventions.
• The note gives platform usage guidance but no concrete example explaining a None output.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.