File size: 1,087 Bytes
3edbc93 58db0a0 50e75cf 58db0a0 10e69e7 50e75cf 8f9985e 3edbc93 8f9985e 3edbc93 21f87d6 10e69e7 89d69bf 62b6599 3edbc93 |
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 |
import pandas as pd
from datasets import load_dataset
import gradio as gr
from constants import RESULTS_REPO, ASSAY_RENAME, LEADERBOARD_RESULTS_COLUMNS
pd.set_option('display.max_columns', None)
def show_output_box(message):
return gr.update(value=message, visible=True)
def fetch_hf_results():
# For debugging
# # Print current time in EST
# EST = timezone(timedelta(hours=-4))
# print(f"tmp: Fetching results from HF at {datetime.now(EST)}")
# Should cache by default if not using force_redownload
df = load_dataset(
RESULTS_REPO, data_files="auto_submissions/metrics_all.csv",
)["train"].to_pandas()
assert all(col in df.columns for col in LEADERBOARD_RESULTS_COLUMNS), f"Expected columns {LEADERBOARD_RESULTS_COLUMNS} not found in {df.columns}. Missing columns: {set(LEADERBOARD_COLUMNS) - set(df.columns)}"
# Show latest submission only
df = df.sort_values("submission_time", ascending=False).drop_duplicates(subset=["model", "assay", "user"], keep="first")
df["property"] = df["assay"].map(ASSAY_RENAME)
return df
|