File size: 2,757 Bytes
20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb 20116b4 1094cbb a2fa160 1094cbb 20116b4 1094cbb |
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 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
import importlib
import os
import sys
import pandas as pd
from huggingface_hub import hf_hub_download
from sklearn import metrics
def compute_metrics(params):
if params.metric == "custom":
metric_file = hf_hub_download(
repo_id=params.competition_id,
filename="metric.py",
token=params.token,
repo_type="dataset",
)
sys.path.append(os.path.dirname(metric_file))
metric = importlib.import_module("metric")
evaluation = metric.compute(params)
else:
solution_file = hf_hub_download(
repo_id=params.competition_id,
filename="solution.csv",
token=params.token,
repo_type="dataset",
)
solution_df = pd.read_csv(solution_file)
submission_filename = f"submissions/{params.team_id}-{params.submission_id}.csv"
submission_file = hf_hub_download(
repo_id=params.competition_id,
filename=submission_filename,
token=params.token,
repo_type="dataset",
)
submission_df = pd.read_csv(submission_file)
public_ids = solution_df[solution_df.split == "public"][params.submission_id_col].values
private_ids = solution_df[solution_df.split == "private"][params.submission_id_col].values
public_solution_df = solution_df[solution_df[params.submission_id_col].isin(public_ids)]
public_submission_df = submission_df[submission_df[params.submission_id_col].isin(public_ids)]
private_solution_df = solution_df[solution_df[params.submission_id_col].isin(private_ids)]
private_submission_df = submission_df[submission_df[params.submission_id_col].isin(private_ids)]
public_solution_df = public_solution_df.sort_values(params.submission_id_col).reset_index(drop=True)
public_submission_df = public_submission_df.sort_values(params.submission_id_col).reset_index(drop=True)
private_solution_df = private_solution_df.sort_values(params.submission_id_col).reset_index(drop=True)
private_submission_df = private_submission_df.sort_values(params.submission_id_col).reset_index(drop=True)
_metric = getattr(metrics, params.metric)
target_cols = [col for col in solution_df.columns if col not in [params.submission_id_col, "split"]]
public_score = _metric(public_solution_df[target_cols], public_submission_df[target_cols])
private_score = _metric(private_solution_df[target_cols], private_submission_df[target_cols])
# scores can also be dictionaries for multiple metrics
evaluation = {
"public_score": public_score,
"private_score": private_score,
}
return evaluation
|