> For the complete documentation index, see [llms.txt](https://qu-tang.gitbook.io/documentation-real-world-puffing-and-smoking-data/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://qu-tang.gitbook.io/documentation-real-world-puffing-and-smoking-data/2_package_structure.md).

# RealSmoking dataset structure

* Root Path
  * data
    * origin
    * featureset (very large size \~ 3.0G)
    * pkl
  * src
    * venv
    * codes
  * results
  * supplies
    * consolidate\_plots
    * posture\_example\_plots
    * publication\_plots
    * puffing\_example\_plots

1. `data/origin` folder contains raw sensor data and annotation files.
2. `data/featureset` folder contains all generated feature sets used by the detection model.

   *Note that this folder will not normally be included into the version control repository, as they are intermediate results and can be very large size.*
3. `data/pkl` folder contains all binary intermediate files that can be loaded with the python serialization package `pickle`. These intermediate files are featureset files in binary format, with 50% less size).
4. `src` folder contains the python source code used in the paper in `codes` folder, and all required packages in `venv` folder. It is recommended to use *virtual environment* when running the codes.
5. `results` folder stores all results generated by the source code in `.csv` format.
6. `supplies` folder stores all plots.
   1. `publication_plots` stores all plots used in the final publication.
   2. `consolidate_plots` stores supplimentary plots showing and comparison of model prediction and visual inspection along with annotations.
   3. `posture_example_plots` stores raw sensor data plot along with annotations for different posture examples.
   4. `puffing_example_plots` stores raw sensor data plot along with annotations for different puffing examples.