Name		Name	Last commit message	Last commit date
parent directory ..
0.1_Parse_DEBS_UCR_BTC.ipynb		0.1_Parse_DEBS_UCR_BTC.ipynb
0.2.1_Data_space_metrics.ipynb		0.2.1_Data_space_metrics.ipynb
0.2.2_Data_space_representativity.ipynb		0.2.2_Data_space_representativity.ipynb
0.2_Create_agg_data.ipynb		0.2_Create_agg_data.ipynb
0.3_Fig_construction.ipynb		0.3_Fig_construction.ipynb
0.4_Fig_metrics.ipynb		0.4_Fig_metrics.ipynb
1.1_Visual_representativity.ipynb		1.1_Visual_representativity.ipynb
1.2_Visual_stability.ipynb		1.2_Visual_stability.ipynb
README.md		README.md
construct_bokeh_figs.py		construct_bokeh_figs.py
varia_Analyze_metrics.ipynb		varia_Analyze_metrics.ipynb
varia_OR_conv.ipynb		varia_OR_conv.ipynb
varia_pixelperfect_m4.ipynb		varia_pixelperfect_m4.ipynb
varia_toolkit_comparison.ipynb		varia_toolkit_comparison.ipynb

README.md

Main notebooks

Name	Description
🔧 Data parsing
parse DEBS UCR	This notebook parses the DEBS 2012, DEBS 2013, UCR time series archive CINECG, and a bitcoin dataset. The parsed data is stored in a (more convenient) parquet format.
create agg data	This notebook creates and stores the reference and subsampled time series for the parsed datasets (in the previous notebook).
Subsampled Figure Generation	This notebook performs an extensive grid search over the following parameters: - Subsampling algorithm - 🚧 x-range based or size-based binning - `n_out`: the number of aggregated datapoints - Template time series and its data size - Visualization toolkit (plotly / matplotlib / :construction: Bokeh ) - Visualization configuration (e.g., line width / line shape) For each combination of parameters, a figure is generated and stored in the path_conf's `figure_root_dir` folder.
Figure Metrics computation	This notebook computes the PSNR and SSIM metrics for the subsampled figures generated in the previous notebook. To do so, an `OR-conv` mask is utilized to mitigate the variable range that which template time-series span over the image
core 📷
Visual Representativeness	This notebook asesses the visual representativeness using the image-space metrics (PSNR and SSIM). Specifically this notebook highlights: - The trend of the aggregator performance over `n_out` - Analyzing hte effect of line width and anti-aliasing - Showing toolkit robustness via the noise data - Distribution plots of the aggregator performances - Dynamic frames showing the performance curves for varying `n_out` / line-width / toolkits
Visual Stability	This notebook explores the visual stability of the subsampling algorithms. Specifically it demonstrates: - The trend in stability of the various aggregators (as `n_out` increases)
🔍 analysis
OR-conv mask	This notebook demonstrates the `OR-conv` mask on the SSIM metric.
pixelperfect m4	This notebook investigates the pixel-perfectness of the M4 data aggregation algorithm. More specifically, the pixel errors are are investigated for: - different visualization toolkits - different visualization configurations And an interpretation of the results is given.
toolkit comparison	This notebook analyzes the rasterization differences between `plotly`, `bokeh`, and `matplotlib` toolkits for the same templates.
analyze metrics	This notebook analyzes the SSIM-PSNR metric discrepancies for the `VW` and `RDP` algorithms, which is further elaborated upon in the visual representativity README.

The playground folder contains notebooks that validate other data aggregation methods.