SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.02764 · 2024

Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
jetbrains-research/pandasplotbench canonical 0 of 7
FunctionStatusWhere it lives
add_index_to_filename Not yet run jetbrains-research/pandasplotbench/plotting_benchmark/vis_generator.py
code served (permissive licence) · get_code("c1f9d7fdda583070")
dict_of_lists_to_list_of_dicts Not yet run jetbrains-research/pandasplotbench/plotting_benchmark/code_plot_generator.py
code served (permissive licence) · get_code("260ccf7e5f32f1e6")
get_model_by_name Not yet run jetbrains-research/pandasplotbench/plotting_benchmark/generation_engines/get_model.py
code served (permissive licence) · get_code("a208895e835dd0f2")
get_task_changing_single_task Not yet run jetbrains-research/pandasplotbench/alter_tasks.py
code served (permissive licence) · get_code("aae9fcb300a70dcf")
get_task_shanging_task Not yet run jetbrains-research/pandasplotbench/alter_tasks.py
code served (permissive licence) · get_code("931f899aa47f50a2")
read_jsonl Not yet run jetbrains-research/pandasplotbench/plotting_benchmark/vis_generator.py
code served (permissive licence) · get_code("e661693417b2d5b1")
read_responses Not yet run jetbrains-research/pandasplotbench/plotting_benchmark/vis_generator.py
code served (permissive licence) · get_code("1877a815145d7f0b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper introduces the human-curated PandasPlotBench dataset, designed to evaluate language models' effectiveness as assistants in visual data exploration. Our benchmark focuses on generating code for visualizing tabular data - such as a Pandas DataFrame - based on natural language instructions, complementing current evaluation tools and expanding their scope. The dataset includes 175 unique tasks. Our experiments assess several leading Large Language Models (LLMs) across three visualization libraries: Matplotlib, Seaborn, and Plotly. We show that the shortening of tasks has a minimal effect on plotting capabilities, allowing for the user interface that accommodates concise user input without sacrificing functionality or accuracy. Another of our findings reveals that while LLMs perform well with popular libraries like Matplotlib and Seaborn, challenges persist with Plotly, highlighting areas for improvement. We hope that the modular design of our benchmark will broaden the current studies on generating visualizations. Our dataset and benchmark code are available online: https://huggingface.co/datasets/JetBrains-Research/PandasPlotBench; https://github.com/JetBrains-Research/PandasPlotBench.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2412.02764")
get_code_for_paper("2412.02764")
have("2412.02764")

Connect an agent — have() is free.