andras/great-ai
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases 4 Packages Wiki Activity Actions

Fix notebooks, improve charts

Browse source
This commit is contained in:
Andras Schmelczer 2022-07-16 12:23:17 +02:00
parent 9999b7ef29
commit 4b919ee757
No known key found for this signature in database
GPG key ID: 0EA1BC97D0AB076E
6 changed files with 306 additions and 1666 deletions
Download patch file Download diff file Expand all files Collapse all files

29
docs/examples/simple/data.ipynb
View file

@ -87,7 +87,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 4/4 [04:42<00:00, 70.62s/it] \n"
"100%|██████████| 4/4 [04:22<00:00, 65.51s/it] \n"
]
}
],
@ -103,10 +103,11 @@
" unchunk,\n",
")\n",
"\n",
"\n",
"def preprocess_chunk(chunk_key: str) -> List[Tuple[str, List[str]]]:\n",
" response = urllib.request.urlopen(\n",
" f\"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/\"\n",
" \"open-corpus/2022-02-01/{chunk_key}\"\n",
" f\"open-corpus/2022-02-01/{chunk_key}\"\n",
" ) # a gzipped JSON Lines file\n",
"\n",
" decompressed = gzip.decompress(response.read())\n",
@ -165,9 +166,29 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 5,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n",
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n",
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n",
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n",
"\u001b[38;5;39mGreatAI (v0.1.6): configured ✅\u001b[0m\n",
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n",
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n",
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n",
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n",
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n",
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n",
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n",
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
}
],
"source": [
"from great_ai import add_ground_truth\n",
"\n",