Bump pandas / hfh

Untitled.ipynb

@@ -0,0 +1,266 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ed2ddd96-57f3-452e-9d28-e44654edbb65",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import DatasetFilter, list_datasets, HfApi, ModelFilter, DatasetSearchArguments\n",
+    "from pathlib import Path\n",
+    "from dotenv import load_dotenv\n",
+    "import os\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c45ae63c-4e02-47e3-a3e9-895a7bc2702d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if Path(\".env\").is_file():\n",
+    "    load_dotenv(\".env\")\n",
+    "\n",
+    "auth_token = os.getenv(\"HF_HUB_TOKEN\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "23e088a3-276a-45bf-9373-4dfe934b5556",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "filt = DatasetFilter(benchmark=\"raft\")\n",
+    "submissions = list_datasets(filter=filt, full=True, use_auth_token=auth_token)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "641c4060",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[0;31mSignature:\u001b[0m\n",
+      "\u001b[0mlist_datasets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0;34m*\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mfilter\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mhuggingface_hub\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mendpoint_helpers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDatasetFilter\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIterable\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mauthor\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0msearch\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0msort\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mLiteral\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'lastModified'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mdirection\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mLiteral\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mlimit\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mcardData\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mbool\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0mfull\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mbool\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m    \u001b[0muse_auth_token\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mUnion\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNoneType\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
+      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mList\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mhuggingface_hub\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhf_api\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDatasetInfo\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mDocstring:\u001b[0m\n",
+      "Get the public list of all the datasets on huggingface.co\n",
+      "\n",
+      "Args:\n",
+      "    filter ([`DatasetFilter`] or `str` or `Iterable`, *optional*):\n",
+      "        A string or [`DatasetFilter`] which can be used to identify\n",
+      "        datasets on the hub.\n",
+      "    author (`str`, *optional*):\n",
+      "        A string which identify the author of the returned models\n",
+      "    search (`str`, *optional*):\n",
+      "        A string that will be contained in the returned models.\n",
+      "    sort (`Literal[\"lastModified\"]` or `str`, *optional*):\n",
+      "        The key with which to sort the resulting datasets. Possible\n",
+      "        values are the properties of the [`huggingface_hub.hf_api.DatasetInfo`] class.\n",
+      "    direction (`Literal[-1]` or `int`, *optional*):\n",
+      "        Direction in which to sort. The value `-1` sorts by descending\n",
+      "        order while all other values sort by ascending order.\n",
+      "    limit (`int`, *optional*):\n",
+      "        The limit on the number of datasets fetched. Leaving this option\n",
+      "        to `None` fetches all datasets.\n",
+      "    cardData (`bool`, *optional*):\n",
+      "        Whether to grab the metadata for the dataset as well. Can\n",
+      "        contain useful information such as the PapersWithCode ID.\n",
+      "    full (`bool`, *optional*):\n",
+      "        Whether to fetch all dataset data, including the `lastModified`\n",
+      "        and the `cardData`.\n",
+      "    use_auth_token (`bool` or `str`, *optional*):\n",
+      "        Whether to use the `auth_token` provided from the\n",
+      "        `huggingface_hub` cli. If not logged in, a valid `auth_token`\n",
+      "        can be passed in as a string.\n",
+      "\n",
+      "Example usage with the `filter` argument:\n",
+      "\n",
+      "```python\n",
+      ">>> from huggingface_hub import HfApi\n",
+      "\n",
+      ">>> api = HfApi()\n",
+      "\n",
+      ">>> # List all datasets\n",
+      ">>> api.list_datasets()\n",
+      "\n",
+      ">>> # Get all valid search arguments\n",
+      ">>> args = DatasetSearchArguments()\n",
+      "\n",
+      ">>> # List only the text classification datasets\n",
+      ">>> api.list_datasets(filter=\"task_categories:text-classification\")\n",
+      ">>> # Using the `DatasetFilter`\n",
+      ">>> filt = DatasetFilter(task_categories=\"text-classification\")\n",
+      ">>> # With `DatasetSearchArguments`\n",
+      ">>> filt = DatasetFilter(task=args.task_categories.text_classification)\n",
+      ">>> api.list_models(filter=filt)\n",
+      "\n",
+      ">>> # List only the datasets in russian for language modeling\n",
+      ">>> api.list_datasets(\n",
+      "...     filter=(\"languages:ru\", \"task_ids:language-modeling\")\n",
+      "... )\n",
+      ">>> # Using the `DatasetFilter`\n",
+      ">>> filt = DatasetFilter(languages=\"ru\", task_ids=\"language-modeling\")\n",
+      ">>> # With `DatasetSearchArguments`\n",
+      ">>> filt = DatasetFilter(\n",
+      "...     languages=args.languages.ru,\n",
+      "...     task_ids=args.task_ids.language_modeling,\n",
+      "... )\n",
+      ">>> api.list_datasets(filter=filt)\n",
+      "```\n",
+      "\n",
+      "Example usage with the `search` argument:\n",
+      "\n",
+      "```python\n",
+      ">>> from huggingface_hub import HfApi\n",
+      "\n",
+      ">>> api = HfApi()\n",
+      "\n",
+      ">>> # List all datasets with \"text\" in their name\n",
+      ">>> api.list_datasets(search=\"text\")\n",
+      "\n",
+      ">>> # List all datasets with \"text\" in their name made by google\n",
+      ">>> api.list_datasets(search=\"text\", author=\"google\")\n",
+      "```\n",
+      "\u001b[0;31mFile:\u001b[0m      ~/miniconda3/envs/raft-leaderboard/lib/python3.8/site-packages/huggingface_hub/hf_api.py\n",
+      "\u001b[0;31mType:\u001b[0m      method\n"
+     ]
+    }
+   ],
+   "source": [
+    "?list_datasets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "228750aa-6d92-4d26-971f-5248e056f54b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "5"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(submissions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "6dc34fa3-be44-4170-8daf-39f87aae5b34",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "benchmark\n",
+      "type\n",
+      "submission_name\n"
+     ]
+    }
+   ],
+   "source": [
+    "for k,v in submissions[3].cardData.items():\n",
+    "    print(k)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f4dd2dbc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DatasetInfo: {\n",
+       "\tid: moshew/my_raft\n",
+       "\tsha: 534086adc3aec801687316b3fe162e4231ab0a6b\n",
+       "\tlastModified: 2022-07-16T17:01:04.000Z\n",
+       "\ttags: ['benchmark:raft']\n",
+       "\tprivate: False\n",
+       "\tauthor: moshew\n",
+       "\tdescription: \n",
+       "\tcitation: @InProceedings{huggingface:dataset,\n",
+       "title = {A great new dataset},\n",
+       "author={huggingface, Inc.\n",
+       "},\n",
+       "year={2020}\n",
+       "}\n",
+       "\tcardData: {'benchmark': 'raft', 'type': 'prediction', 'submission_name': 'SetFit300'}\n",
+       "\tsiblings: None\n",
+       "\t_id: 621ffdd236468d709f183ac3\n",
+       "\tdisabled: False\n",
+       "\tgated: auto\n",
+       "\tgitalyUid: 0d29a8b3b8364fb2d86b3ad56d62ea4aaf13a5cf95884aa0381b966d79b045e1\n",
+       "\tlikes: 0\n",
+       "\tdownloads: 0\n",
+       "}"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "submissions[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27079f0b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "raft-leaderboard",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -21,7 +21,7 @@ FORMATTED_TASK_NAMES = sorted([" ".join(t.capitalize() for t in task.split("_"))
 
 def download_submissions():
     filt = DatasetFilter(benchmark="raft")
-    all_submissions = list_datasets(filter=filt, cardData=True, use_auth_token=auth_token)
+    all_submissions = list_datasets(filter=filt, full=True, use_auth_token=auth_token)
     submissions = []
 
     for dataset in all_submissions:
@@ -97,7 +97,9 @@ To submit to RAFT, follow the instruction posted on [this page](https://huggingf
 submissions = download_submissions()
 print(f"INFO - downloaded {len(submissions)} submissions")
 df = format_submissions(submissions)
-styler = df.style.set_precision(3).set_properties(**{"white-space": "pre-wrap", "text-align": "center"})
+styler = pd.io.formats.style.Styler(df, precision=3).set_properties(
+    **{"white-space": "pre-wrap", "text-align": "center"}
+)
 # hack to remove index column: https://discuss.streamlit.io/t/questions-on-st-table/6878/3
 st.markdown(
     """

requirements.txt

@@ -1,6 +1,6 @@
-pandas<=1.4
+pandas==2.0.3
 python-dotenv
 protobuf~=3.19.0
-huggingface-hub==0.9.1
+huggingface-hub==0.18.0
 datasets==2.8.0
 altair<5