Spaces:
Running
Running
Bump pandas / hfh
Browse files- Untitled.ipynb +266 -0
- app.py +4 -2
- requirements.txt +2 -2
Untitled.ipynb
ADDED
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"id": "ed2ddd96-57f3-452e-9d28-e44654edbb65",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [],
|
9 |
+
"source": [
|
10 |
+
"from huggingface_hub import DatasetFilter, list_datasets, HfApi, ModelFilter, DatasetSearchArguments\n",
|
11 |
+
"from pathlib import Path\n",
|
12 |
+
"from dotenv import load_dotenv\n",
|
13 |
+
"import os\n"
|
14 |
+
]
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"cell_type": "code",
|
18 |
+
"execution_count": 2,
|
19 |
+
"id": "c45ae63c-4e02-47e3-a3e9-895a7bc2702d",
|
20 |
+
"metadata": {},
|
21 |
+
"outputs": [],
|
22 |
+
"source": [
|
23 |
+
"if Path(\".env\").is_file():\n",
|
24 |
+
" load_dotenv(\".env\")\n",
|
25 |
+
"\n",
|
26 |
+
"auth_token = os.getenv(\"HF_HUB_TOKEN\")"
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"cell_type": "code",
|
31 |
+
"execution_count": 7,
|
32 |
+
"id": "23e088a3-276a-45bf-9373-4dfe934b5556",
|
33 |
+
"metadata": {},
|
34 |
+
"outputs": [],
|
35 |
+
"source": [
|
36 |
+
"filt = DatasetFilter(benchmark=\"raft\")\n",
|
37 |
+
"submissions = list_datasets(filter=filt, full=True, use_auth_token=auth_token)"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"cell_type": "code",
|
42 |
+
"execution_count": 8,
|
43 |
+
"id": "641c4060",
|
44 |
+
"metadata": {},
|
45 |
+
"outputs": [
|
46 |
+
{
|
47 |
+
"name": "stdout",
|
48 |
+
"output_type": "stream",
|
49 |
+
"text": [
|
50 |
+
"\u001b[0;31mSignature:\u001b[0m\n",
|
51 |
+
"\u001b[0mlist_datasets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
|
52 |
+
"\u001b[0;34m\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
|
53 |
+
"\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",
|
54 |
+
"\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",
|
55 |
+
"\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",
|
56 |
+
"\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",
|
57 |
+
"\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",
|
58 |
+
"\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",
|
59 |
+
"\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",
|
60 |
+
"\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",
|
61 |
+
"\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",
|
62 |
+
"\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",
|
63 |
+
"\u001b[0;31mDocstring:\u001b[0m\n",
|
64 |
+
"Get the public list of all the datasets on huggingface.co\n",
|
65 |
+
"\n",
|
66 |
+
"Args:\n",
|
67 |
+
" filter ([`DatasetFilter`] or `str` or `Iterable`, *optional*):\n",
|
68 |
+
" A string or [`DatasetFilter`] which can be used to identify\n",
|
69 |
+
" datasets on the hub.\n",
|
70 |
+
" author (`str`, *optional*):\n",
|
71 |
+
" A string which identify the author of the returned models\n",
|
72 |
+
" search (`str`, *optional*):\n",
|
73 |
+
" A string that will be contained in the returned models.\n",
|
74 |
+
" sort (`Literal[\"lastModified\"]` or `str`, *optional*):\n",
|
75 |
+
" The key with which to sort the resulting datasets. Possible\n",
|
76 |
+
" values are the properties of the [`huggingface_hub.hf_api.DatasetInfo`] class.\n",
|
77 |
+
" direction (`Literal[-1]` or `int`, *optional*):\n",
|
78 |
+
" Direction in which to sort. The value `-1` sorts by descending\n",
|
79 |
+
" order while all other values sort by ascending order.\n",
|
80 |
+
" limit (`int`, *optional*):\n",
|
81 |
+
" The limit on the number of datasets fetched. Leaving this option\n",
|
82 |
+
" to `None` fetches all datasets.\n",
|
83 |
+
" cardData (`bool`, *optional*):\n",
|
84 |
+
" Whether to grab the metadata for the dataset as well. Can\n",
|
85 |
+
" contain useful information such as the PapersWithCode ID.\n",
|
86 |
+
" full (`bool`, *optional*):\n",
|
87 |
+
" Whether to fetch all dataset data, including the `lastModified`\n",
|
88 |
+
" and the `cardData`.\n",
|
89 |
+
" use_auth_token (`bool` or `str`, *optional*):\n",
|
90 |
+
" Whether to use the `auth_token` provided from the\n",
|
91 |
+
" `huggingface_hub` cli. If not logged in, a valid `auth_token`\n",
|
92 |
+
" can be passed in as a string.\n",
|
93 |
+
"\n",
|
94 |
+
"Example usage with the `filter` argument:\n",
|
95 |
+
"\n",
|
96 |
+
"```python\n",
|
97 |
+
">>> from huggingface_hub import HfApi\n",
|
98 |
+
"\n",
|
99 |
+
">>> api = HfApi()\n",
|
100 |
+
"\n",
|
101 |
+
">>> # List all datasets\n",
|
102 |
+
">>> api.list_datasets()\n",
|
103 |
+
"\n",
|
104 |
+
">>> # Get all valid search arguments\n",
|
105 |
+
">>> args = DatasetSearchArguments()\n",
|
106 |
+
"\n",
|
107 |
+
">>> # List only the text classification datasets\n",
|
108 |
+
">>> api.list_datasets(filter=\"task_categories:text-classification\")\n",
|
109 |
+
">>> # Using the `DatasetFilter`\n",
|
110 |
+
">>> filt = DatasetFilter(task_categories=\"text-classification\")\n",
|
111 |
+
">>> # With `DatasetSearchArguments`\n",
|
112 |
+
">>> filt = DatasetFilter(task=args.task_categories.text_classification)\n",
|
113 |
+
">>> api.list_models(filter=filt)\n",
|
114 |
+
"\n",
|
115 |
+
">>> # List only the datasets in russian for language modeling\n",
|
116 |
+
">>> api.list_datasets(\n",
|
117 |
+
"... filter=(\"languages:ru\", \"task_ids:language-modeling\")\n",
|
118 |
+
"... )\n",
|
119 |
+
">>> # Using the `DatasetFilter`\n",
|
120 |
+
">>> filt = DatasetFilter(languages=\"ru\", task_ids=\"language-modeling\")\n",
|
121 |
+
">>> # With `DatasetSearchArguments`\n",
|
122 |
+
">>> filt = DatasetFilter(\n",
|
123 |
+
"... languages=args.languages.ru,\n",
|
124 |
+
"... task_ids=args.task_ids.language_modeling,\n",
|
125 |
+
"... )\n",
|
126 |
+
">>> api.list_datasets(filter=filt)\n",
|
127 |
+
"```\n",
|
128 |
+
"\n",
|
129 |
+
"Example usage with the `search` argument:\n",
|
130 |
+
"\n",
|
131 |
+
"```python\n",
|
132 |
+
">>> from huggingface_hub import HfApi\n",
|
133 |
+
"\n",
|
134 |
+
">>> api = HfApi()\n",
|
135 |
+
"\n",
|
136 |
+
">>> # List all datasets with \"text\" in their name\n",
|
137 |
+
">>> api.list_datasets(search=\"text\")\n",
|
138 |
+
"\n",
|
139 |
+
">>> # List all datasets with \"text\" in their name made by google\n",
|
140 |
+
">>> api.list_datasets(search=\"text\", author=\"google\")\n",
|
141 |
+
"```\n",
|
142 |
+
"\u001b[0;31mFile:\u001b[0m ~/miniconda3/envs/raft-leaderboard/lib/python3.8/site-packages/huggingface_hub/hf_api.py\n",
|
143 |
+
"\u001b[0;31mType:\u001b[0m method\n"
|
144 |
+
]
|
145 |
+
}
|
146 |
+
],
|
147 |
+
"source": [
|
148 |
+
"?list_datasets"
|
149 |
+
]
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"cell_type": "code",
|
153 |
+
"execution_count": 9,
|
154 |
+
"id": "228750aa-6d92-4d26-971f-5248e056f54b",
|
155 |
+
"metadata": {},
|
156 |
+
"outputs": [
|
157 |
+
{
|
158 |
+
"data": {
|
159 |
+
"text/plain": [
|
160 |
+
"5"
|
161 |
+
]
|
162 |
+
},
|
163 |
+
"execution_count": 9,
|
164 |
+
"metadata": {},
|
165 |
+
"output_type": "execute_result"
|
166 |
+
}
|
167 |
+
],
|
168 |
+
"source": [
|
169 |
+
"len(submissions)"
|
170 |
+
]
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"cell_type": "code",
|
174 |
+
"execution_count": 11,
|
175 |
+
"id": "6dc34fa3-be44-4170-8daf-39f87aae5b34",
|
176 |
+
"metadata": {},
|
177 |
+
"outputs": [
|
178 |
+
{
|
179 |
+
"name": "stdout",
|
180 |
+
"output_type": "stream",
|
181 |
+
"text": [
|
182 |
+
"benchmark\n",
|
183 |
+
"type\n",
|
184 |
+
"submission_name\n"
|
185 |
+
]
|
186 |
+
}
|
187 |
+
],
|
188 |
+
"source": [
|
189 |
+
"for k,v in submissions[3].cardData.items():\n",
|
190 |
+
" print(k)"
|
191 |
+
]
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"cell_type": "code",
|
195 |
+
"execution_count": 12,
|
196 |
+
"id": "f4dd2dbc",
|
197 |
+
"metadata": {},
|
198 |
+
"outputs": [
|
199 |
+
{
|
200 |
+
"data": {
|
201 |
+
"text/plain": [
|
202 |
+
"DatasetInfo: {\n",
|
203 |
+
"\tid: moshew/my_raft\n",
|
204 |
+
"\tsha: 534086adc3aec801687316b3fe162e4231ab0a6b\n",
|
205 |
+
"\tlastModified: 2022-07-16T17:01:04.000Z\n",
|
206 |
+
"\ttags: ['benchmark:raft']\n",
|
207 |
+
"\tprivate: False\n",
|
208 |
+
"\tauthor: moshew\n",
|
209 |
+
"\tdescription: \n",
|
210 |
+
"\tcitation: @InProceedings{huggingface:dataset,\n",
|
211 |
+
"title = {A great new dataset},\n",
|
212 |
+
"author={huggingface, Inc.\n",
|
213 |
+
"},\n",
|
214 |
+
"year={2020}\n",
|
215 |
+
"}\n",
|
216 |
+
"\tcardData: {'benchmark': 'raft', 'type': 'prediction', 'submission_name': 'SetFit300'}\n",
|
217 |
+
"\tsiblings: None\n",
|
218 |
+
"\t_id: 621ffdd236468d709f183ac3\n",
|
219 |
+
"\tdisabled: False\n",
|
220 |
+
"\tgated: auto\n",
|
221 |
+
"\tgitalyUid: 0d29a8b3b8364fb2d86b3ad56d62ea4aaf13a5cf95884aa0381b966d79b045e1\n",
|
222 |
+
"\tlikes: 0\n",
|
223 |
+
"\tdownloads: 0\n",
|
224 |
+
"}"
|
225 |
+
]
|
226 |
+
},
|
227 |
+
"execution_count": 12,
|
228 |
+
"metadata": {},
|
229 |
+
"output_type": "execute_result"
|
230 |
+
}
|
231 |
+
],
|
232 |
+
"source": [
|
233 |
+
"submissions[0]"
|
234 |
+
]
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"cell_type": "code",
|
238 |
+
"execution_count": null,
|
239 |
+
"id": "27079f0b",
|
240 |
+
"metadata": {},
|
241 |
+
"outputs": [],
|
242 |
+
"source": []
|
243 |
+
}
|
244 |
+
],
|
245 |
+
"metadata": {
|
246 |
+
"kernelspec": {
|
247 |
+
"display_name": "raft-leaderboard",
|
248 |
+
"language": "python",
|
249 |
+
"name": "python3"
|
250 |
+
},
|
251 |
+
"language_info": {
|
252 |
+
"codemirror_mode": {
|
253 |
+
"name": "ipython",
|
254 |
+
"version": 3
|
255 |
+
},
|
256 |
+
"file_extension": ".py",
|
257 |
+
"mimetype": "text/x-python",
|
258 |
+
"name": "python",
|
259 |
+
"nbconvert_exporter": "python",
|
260 |
+
"pygments_lexer": "ipython3",
|
261 |
+
"version": "3.8.15"
|
262 |
+
}
|
263 |
+
},
|
264 |
+
"nbformat": 4,
|
265 |
+
"nbformat_minor": 5
|
266 |
+
}
|
app.py
CHANGED
@@ -21,7 +21,7 @@ FORMATTED_TASK_NAMES = sorted([" ".join(t.capitalize() for t in task.split("_"))
|
|
21 |
|
22 |
def download_submissions():
|
23 |
filt = DatasetFilter(benchmark="raft")
|
24 |
-
all_submissions = list_datasets(filter=filt,
|
25 |
submissions = []
|
26 |
|
27 |
for dataset in all_submissions:
|
@@ -97,7 +97,9 @@ To submit to RAFT, follow the instruction posted on [this page](https://huggingf
|
|
97 |
submissions = download_submissions()
|
98 |
print(f"INFO - downloaded {len(submissions)} submissions")
|
99 |
df = format_submissions(submissions)
|
100 |
-
styler =
|
|
|
|
|
101 |
# hack to remove index column: https://discuss.streamlit.io/t/questions-on-st-table/6878/3
|
102 |
st.markdown(
|
103 |
"""
|
|
|
21 |
|
22 |
def download_submissions():
|
23 |
filt = DatasetFilter(benchmark="raft")
|
24 |
+
all_submissions = list_datasets(filter=filt, full=True, use_auth_token=auth_token)
|
25 |
submissions = []
|
26 |
|
27 |
for dataset in all_submissions:
|
|
|
97 |
submissions = download_submissions()
|
98 |
print(f"INFO - downloaded {len(submissions)} submissions")
|
99 |
df = format_submissions(submissions)
|
100 |
+
styler = pd.io.formats.style.Styler(df, precision=3).set_properties(
|
101 |
+
**{"white-space": "pre-wrap", "text-align": "center"}
|
102 |
+
)
|
103 |
# hack to remove index column: https://discuss.streamlit.io/t/questions-on-st-table/6878/3
|
104 |
st.markdown(
|
105 |
"""
|
requirements.txt
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
-
pandas
|
2 |
python-dotenv
|
3 |
protobuf~=3.19.0
|
4 |
-
huggingface-hub==0.
|
5 |
datasets==2.8.0
|
6 |
altair<5
|
|
|
1 |
+
pandas==2.0.3
|
2 |
python-dotenv
|
3 |
protobuf~=3.19.0
|
4 |
+
huggingface-hub==0.18.0
|
5 |
datasets==2.8.0
|
6 |
altair<5
|