app.py

import os
from datetime import datetime, timedelta, timezone
from typing import Any, Dict

import gradio as gr
import pandas as pd
from cachetools import TTLCache, cached
from dotenv import load_dotenv
from httpx import Client
from huggingface_hub import DatasetCard, hf_hub_url, list_datasets
from tqdm.auto import tqdm
from tqdm.contrib.concurrent import thread_map

load_dotenv()

LIMIT = 3_000
CACHE_TIME = 60 * 60 * 12  # 12 hours
REMOVE_ORGS = {
    "HuggingFaceM4",
    "HuggingFaceBR4",
    "open-llm-leaderboard",
    "TrainingDataPro",
}

HF_TOKEN = os.getenv("HF_TOKEN")
USER_AGENT = os.getenv("USER_AGENT")


headers = {"authorization": f"Bearer ${HF_TOKEN}", "user-agent": USER_AGENT}


client = Client(
    headers=headers,
    timeout=120,
)
# LOCAL = False
# if platform == "darwin":
#     LOCAL = True
# cache_dir = "cache" if LOCAL else "/data/diskcache"
# cache = Cache(cache_dir)
cache = TTLCache(maxsize=10, ttl=CACHE_TIME)


def get_three_months_ago():
    now = datetime.now(timezone.utc)
    return now - timedelta(days=90)


def add_created_data(dataset):
    _id = dataset._id
    created = dataset.created_at
    dataset_dict = dataset.__dict__
    dataset_dict["createdAt"] = created
    return dataset_dict


def get_readme_len(dataset: Dict[str, Any]):
    try:
        url = hf_hub_url(dataset["id"], "README.md", repo_type="dataset")
        resp = client.get(url)
        if resp.status_code == 200:
            card = DatasetCard(resp.text)
            dataset["len"] = len(card.text)
            return dataset
    except Exception as e:
        print(e)
        return None


def check_ds_server_valid(id):
    url = f"https://datasets-server.huggingface.co/is-valid?dataset={id}"
    response = client.get(url)
    if response.status_code != 200:
        return False
    try:
        data = response.json()
        preview = data.get("preview")
        return preview is not None
    except Exception as e:
        print(e)
        return False


def has_server_preview(dataset):
    dataset["server_preview"] = check_ds_server_valid(dataset["id"])
    return dataset


def render_model_hub_link(hub_id):
    link = f"https://huggingface.co/datasets/{hub_id}"
    return (
        f'<a target="_blank" href="{link}" style="color: var(--link-text-color);'
        f' text-decoration: underline;text-decoration-style: dotted;">{hub_id}</a>'
    )


@cached(cache)
def get_datasets():
    return list(
        tqdm(
            iter(
                list_datasets(limit=LIMIT, full=True, sort="lastModified", direction=-1)
            )
        )
    )


@cached(cache)
def load_data():
    datasets = get_datasets()
    datasets = [add_created_data(dataset) for dataset in tqdm(datasets)]
    # datasets = [dataset.__dict__ for dataset in tqdm(datasets)]
    filtered = [ds for ds in datasets if ds["createdAt"] > get_three_months_ago()]
    ds_with_len = thread_map(get_readme_len, filtered)
    ds_with_len = [ds for ds in ds_with_len if ds is not None]
    ds_with_valid_status = thread_map(has_server_preview, ds_with_len)
    ds_with_valid_status = [ds for ds in ds_with_valid_status if ds is not None]
    return ds_with_valid_status


columns_to_drop = [
    "cardData",
    "gated",
    "sha",
    "tags",
    "description",
    "siblings",
    "disabled",
    "_id",
    "private",
    "author",
  #  "citation",
    "lastModified",
]


def prep_dataframe(remove_orgs_and_users=REMOVE_ORGS, columns_to_drop=columns_to_drop):
    ds_with_len = load_data()
    if remove_orgs_and_users:
        ds_with_len = [
            ds for ds in ds_with_len if ds["author"] not in remove_orgs_and_users
        ]
    df = pd.DataFrame(ds_with_len)
    df["id"] = df["id"].apply(render_model_hub_link)
    if columns_to_drop:
        df = df.drop(columns=columns_to_drop)
    df = df.sort_values(by=["likes", "downloads", "len"], ascending=False)
    return df


def filter_df_by_max_age(df, max_age_days=None):
    df = df.dropna(subset=["createdAt"])
    now = datetime.now(timezone.utc)
    if max_age_days is not None:
        max_date = now - timedelta(days=max_age_days)
        df = df[df["createdAt"] >= max_date]
    return df


def filter_by_readme_len(df, min_len=None):
    if min_len is not None:
        df = df[df["len"] >= min_len]
    return df


def filter_df(max_age_days=None, min_len=None, needs_server_preview: bool = False):
    df = prep_dataframe()
    if needs_server_preview:
        df = df[df["server_preview"] == True]
    if max_age_days is not None:
        df = filter_df_by_max_age(df, max_age_days=max_age_days)
    if min_len is not None:
        df = filter_by_readme_len(df, min_len=min_len)
    df = df.sort_values(by=["likes", "downloads", "len"], ascending=False)
    return df


with gr.Blocks() as demo:
    gr.Markdown("# Recent Datasets on the Hub")
    gr.Markdown(
        "Datasets added in the past 90 days with a README.md and some metadata."
    )
    with gr.Row():
        max_age_days = gr.Slider(
            label="Max Age (days)",
            value=7,
            minimum=0,
            maximum=90,
            step=1,
            interactive=True,
        )
        min_len = gr.Slider(
            label="Minimum README Length",
            value=300,
            minimum=0,
            maximum=1000,
            step=50,
            interactive=True,
        )
        needs_server_preview = gr.Checkbox(
            label="Exclude datasets without datasets-server preview?",
            value=False,
            interactive=True,
        )

    output = gr.DataFrame(filter_df, datatype="markdown", min_width=160 * 2.5, height=1000)
    max_age_days.input(
        filter_df,
        inputs=[max_age_days, min_len, needs_server_preview],
        outputs=[output],
    )
    min_len.input(
        filter_df,
        inputs=[max_age_days, min_len, needs_server_preview],
        outputs=[output],
    )
    needs_server_preview.change(
        filter_df,
        inputs=[max_age_days, min_len, needs_server_preview],
        outputs=[output],
    )

demo.launch()