aider/benchmark
Paul Gauthier 0f6a90bfed aider: Switched the plt stuff to use an explicit fig.
# Context:
USER: switch the plt stuff to use an explicit fig
ASSISTANT: To switch the matplotlib plotting to use an explicit figure, we need to modify the `show_stats` function in the `benchmark/benchmark.py` file.

Here are the changes:

```python
benchmark/benchmark.py
<<<<<<< ORIGINAL
    df_grouped.unstack().plot(kind="barh", figsize=(10, 6))

    plt.xlabel("Pass Rate 1")
    plt.ylabel("Model")
    plt.title("Pass Rate 1 for each Model/Edit Format")
    plt.legend(title="Edit Format")
    plt.show()
=======
    fig, ax = plt.subplots(figsize=(10, 6))
    df_grouped.unstack().plot(kind="barh", ax=ax)

    ax.set_xlabel("Pass Rate 1")
    ax.set_ylabel("Model")
    ax.set_title("Pass Rate 1 for each Model/Edit Format")
    ax.legend(title="Edit Format")
    plt.show()
>>>>>>> UPDATED
```

This change creates a new figure and axes before plotting, and then uses the axes for setting labels, title, and legend. This is a more explicit way of handling figures and axes in matplotlib.
2023-06-29 18:58:50 -07:00
..
__init__.py initial 2023-06-28 18:32:09 -07:00
benchmark.py aider: Switched the plt stuff to use an explicit fig. 2023-06-29 18:58:50 -07:00
docker.sh AIDER_BENCHMARK_DIR 2023-06-29 18:13:54 -07:00
docker_build.sh docker environment for the whole benchmark 2023-06-29 14:19:00 -07:00
Dockerfile pull summary data into a df 2023-06-29 18:48:20 -07:00
prompts.py move benchmark prompts into their own file 2023-06-28 18:25:39 -07:00
test_benchmark.py remove long ==--- lines to save tokens 2023-06-28 15:44:23 -07:00