This is Intel® Scalable Dataframe Compiler (Intel® SDC), which is an extension of Numba* that enables compilation of Pandas* operations. It automatically vectorizes and parallelizes the code by leveraging modern hardware instructions and by utilizing all available cores.

User Manual

• What is Intel® SDC?
• Getting Started
  • Installation
  • Basic Usage
  • What If I Get A Compilation Error
  • Measuring Performance
  • What If I Get Poor Performance?
  • Build Instructions
• Compiling With Intel® SDC
  • What if I get a compilation error
• Getting Performance With Intel® SDC
  • Compilation Overheads
  • Boxing And Unboxing Overheads
  • Automatic Parallelization
  • Other Performance Tips
• Step by step on typical data analysis workflow
• API Reference
  • Input/output
  • Series: Columnar Data Structure
  • Dataframe: Tabular Data Structure
  • Window
  • GroupBy
• List of examples
• Contribute to Intel® Scalable Dataframe Compiler Development
• Other Intel projects for high-performance Python

User Manual To-Do List

Todo

Add support of parameters center, win_type, on, axis and closed

original entry

Todo

Fix SDC behavior and add the expected output of the > python ./series_getitem.py to the docstring

original entry

Todo

Add support of parameters center, win_type, on, axis and closed

original entry

Todo

Add support of 32-bit Unicode for str.center()

original entry

Todo

• Add support of matching the end of each string by a pattern

• Add support of parameter na

original entry

Todo

Add support of parameters start and end

original entry

Todo

Add support of 32-bit Unicode for str.ljust()

original entry

Todo

Add support of 32-bit Unicode for str.rjust()

original entry

Todo

• Add support of matching the start of each string by a pattern

• Add support of parameter na

original entry

Todo

Add support of 32-bit Unicode for str.zfill()

original entry