Spaces:
Sleeping
Sleeping
File size: 3,210 Bytes
bb6bec5 bffa030 bb6bec5 bffa030 bb6bec5 bffa030 bb6bec5 4c11522 bb6bec5 bffa030 8152262 7709561 bb6bec5 4c11522 bb6bec5 |
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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
from huggingface_hub import list_datasets
from toolz import concat
from toolz import frequencies
import gradio as gr
import pandas as pd
from huggingface_hub import list_models
from huggingface_hub import ModelFilter
from tqdm.auto import tqdm
"""## Grab datasets with `token-classification` task"""
datasets = list(list_datasets(filter="task_categories:token-classification"))
datasets[0]
with_language = [
dataset
for dataset in datasets
if "language" in [t.split(":")[0] for t in dataset.tags]
]
with_language[0]
def get_languages(dataset):
tags = list(dataset.tags)
languages = [t for t in tags if t.split(":")[0] == "language"]
languages = [language for language in languages if len(language.split(":")) == 2]
return [t.split(":")[1] for t in languages]
freqs = frequencies(concat(get_languages(dataset) for dataset in with_language))
freqs = dict(sorted(freqs.items(), key=lambda x: x[1], reverse=True))
no_model = []
for lang in tqdm(freqs.keys()):
models_for_lang_with_task_token_classification = list(
list_models(filter=ModelFilter(language=lang, task="token-classification"))
)
models_for_lang_any_task = list(list_models(filter=ModelFilter(language=lang)))
datasets_for_lang_any_task = list(list_datasets(filter=f"language:{lang}"))
if not models_for_lang_with_task_token_classification:
data = {
"language": lang,
"datasets_for_token_classification": freqs[lang],
"datasets": len(datasets_for_lang_any_task),
"token_classification_models": len(
models_for_lang_with_task_token_classification
),
"all_models": len(models_for_lang_any_task),
}
no_model.append(data)
len(no_model)
df = pd.DataFrame(no_model)
df = df.sort_values(
by=[
"datasets_for_token_classification",
"datasets",
"token_classification_models",
"all_models",
],
ascending=[False, False, True, True],
)
def report_summary():
summary = ""
for row in df.head(30).itertuples():
language = row[1]
summary += f"# Summary for language: {language}\n"
summary += f"This language has {(row[2])} token classification datasets, {row[3]} datasets overall, {row[4]} token classification models, and {row[5]} models overall.\n"
summary += f"- [Datasets for token classification task for {language}](https://huggingface.co/datasets?task_categories=task_categories:token-classification&language=language:{language})\n"
summary += f"- [Token classification models for {language}](https://huggingface.co/models?task_categories=task_categories:token-classification&language=language:{language})\n"
summary += f"- [All models for {language}](https://huggingface.co/models?language={language}&sort=trending)\n"
summary += "<br>\n"
return summary
with gr.Blocks() as demo:
gr.DataFrame(df)
gr.Markdown("# Top 30 candidates")
gr.Markdown(
"Candiates generated by sorting by most token classification datasets, then least token classification models, then least models overall"
)
gr.Markdown(report_summary())
demo.launch()
|