File size: 1,068 Bytes
f1e08ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 |
import pandas as pd
import wandb
def get_wandb_data(entity: str, project: str, api_key: str, job_type: str) -> pd.DataFrame:
api = wandb.Api(api_key=api_key)
# Project is specified by <entity/project-name>
filter_dict = {"jobType": job_type}
runs = api.runs(f"{entity}/{project}", filters=filter_dict)
summary_list, config_list, name_list = [], [], []
for run in runs:
# .summary contains the output keys/values for metrics like accuracy.
# We call ._json_dict to omit large files
summary_list.append(run.summary._json_dict)
# .config contains the hyperparameters.
# We remove special values that start with _.
config_list.append({k: v for k, v in run.config.items()})
# .name is the human-readable name of the run.
name_list.append(run.name)
summary_df = pd.json_normalize(summary_list, max_level=1)
config_df = pd.json_normalize(config_list, max_level=2)
runs_df = pd.concat([summary_df, config_df], axis=1)
runs_df.index = name_list
return runs_df
|