aider/benchmark
Paul Gauthier 0c9deaa118 aider: Sort the grouped columns by descending average.
# Context:
USER: sort the grouped columns by descending average
ASSISTANT: To sort the grouped columns by descending average, we need to modify the `show_stats` function in the `benchmark/benchmark.py` file. Specifically, we need to sort the `df_grouped` DataFrame by its values in descending order.

Here is the change:

```python
benchmark/benchmark.py
<<<<<<< ORIGINAL
    df_grouped = df.groupby(["model", "edit_format"])["pass_rate_1"].mean()
=======
    df_grouped = df.groupby(["model", "edit_format"])["pass_rate_1"].mean().sort_values(ascending=False)
>>>>>>> UPDATED
```

This change will sort the grouped DataFrame `df_grouped` by its values in descending order. The `ascending=False` argument in the `sort_values` function ensures that the sorting is done in descending order.
2023-06-29 19:05:16 -07:00
..
__init__.py initial 2023-06-28 18:32:09 -07:00
benchmark.py aider: Sort the grouped columns by descending average. 2023-06-29 19:05:16 -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 show with imgcat 2023-06-29 19:04:48 -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