Commit graph

52 commits

Author SHA1 Message Date
Paul Gauthier
af2f4b73e9 aider: Use the released field directly in the plot instead of parsing it with datetime.strptime.
# Aider chat conversation:

USER: I ran this command:

 python benchmark/over_time.py

And got this output:

Traceback (most recent call last):
  File "/Users/gauthier/Projects/aider/benchmark/over_time.py", line 33, in <module>
    plot_over_time('_data/edit_leaderboard.yml')
  File "/Users/gauthier/Projects/aider/benchmark/over_time.py", line 15, in plot_over_time
    dates.append(datetime.strptime(entry['released'], '%Y-%m-%d'))
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: strptime() argument 1 must be str, not datetime.date

ASSISTANT: The error indicates that the `released` field in the YAML file is already a `datetime.date` object, so we don't need to parse it with `datetime.strptime`. We can directly use it in the plot.

Here are the changes:

benchmark/over_time.py
```python
<<<<<<< SEARCH
            dates.append(datetime.strptime(entry['released'], '%Y-%m-%d'))
=======
            dates.append(entry['released'])
>>>>>>> REPLACE
```
2024-05-15 11:03:07 -07:00
Paul Gauthier
49ac9ca357 aider: Added scatter plot functionality for YAML entries with a released date and pass_rate_2.
# Aider chat conversation:

USER: in over_time.py, draw a graph for each of the yaml entries with a `released` date. plot date on x, `pass_rate_2` on y and label with the `model` name. do a scatter plot. use colors/styles similar to the other graphs.

ASSISTANT: To draw a scatter plot for each of the YAML entries with a `released` date, we need to:

1. Read the YAML file.
2. Extract the `released` date and `pass_rate_2` for each entry.
3. Plot the data using matplotlib.

Here are the changes:

benchmark/over_time.py
```python
<<<<<<< SEARCH
=======
import matplotlib.pyplot as plt
import yaml
from datetime import datetime

def plot_over_time(yaml_file):
    with open(yaml_file, 'r') as file:
        data = yaml.safe_load(file)

    dates = []
    pass_rates = []
    models = []

    for entry in data:
        if 'released' in entry and 'pass_rate_2' in entry:
            dates.append(datetime.strptime(entry['released'], '%Y-%m-%d'))
            pass_rates.append(entry['pass_rate_2'])
            models.append(entry['model'])

    plt.figure(figsize=(10, 6))
    plt.scatter(dates, pass_rates, c='blue', alpha=0.5)

    for i, model in enumerate(models):
        plt.annotate(model, (dates[i], pass_rates[i]), fontsize=8, alpha=0.75)

    plt.xlabel('Release Date')
    plt.ylabel('Pass Rate 2')
    plt.title('Model Performance Over Time')
    plt.grid(True)
    plt.tight_layout()
    plt.show()

# Example usage
plot_over_time('_data/edit_leaderboard.yml')
>>>>>>> REPLACE
```
2024-05-15 11:02:44 -07:00