Deployed 18ef86a with MkDocs version: 1.3.0
This commit is contained in:
parent
b54bcd78f2
commit
1c4fc1fa73
15 changed files with 151 additions and 138 deletions
265
examples/simple/data/data.ipynb
Normal file
265
examples/simple/data/data.ipynb
Normal file
|
|
@ -0,0 +1,265 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n",
|
||||
"> Part 1: obtain and clean data\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"> The blue boxes show the steps implemented in this notebook.\n",
|
||||
"\n",
|
||||
"### Extract\n",
|
||||
"\n",
|
||||
"This can be achieved by downloading a public dataset (such as in this case), or by having a Data Engineer setup and give us access to the organisation's data.\n",
|
||||
"\n",
|
||||
"In this case, we download the semantic scholar dataset from a public S3 bucket."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"MAX_CHUNK_COUNT = 1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Processing 1 out of the 6002 available chunks'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"from random import shuffle\n",
|
||||
"\n",
|
||||
"manifest = (\n",
|
||||
" urllib.request.urlopen(\n",
|
||||
" \"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/manifest.txt\"\n",
|
||||
" )\n",
|
||||
" .read()\n",
|
||||
" .decode()\n",
|
||||
") # a list of available chunks separated by '\\n' characters\n",
|
||||
"\n",
|
||||
"lines = manifest.split()\n",
|
||||
"shuffle(lines)\n",
|
||||
"chunks = lines[:MAX_CHUNK_COUNT]\n",
|
||||
"\n",
|
||||
"f\"Processing {len(chunks)} out of the {len(manifest.split())} available chunks\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Transform\n",
|
||||
"\n",
|
||||
"- Filter out non-English abstracts using `great_ai.utilities.predict_language`\n",
|
||||
"- Project it to only keep the necessary components (text and labels), clean the textual content using `great_ai.utilities.clean`\n",
|
||||
"- We will speed up processing using `great_ai.utilities.parallel_map`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Spacy model en_core_web_sm not found locally, downloading...\n",
|
||||
"Collecting en-core-web-sm==3.3.0\n",
|
||||
" Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.3.0/en_core_web_sm-3.3.0-py3-none-any.whl (12.8 MB)\n",
|
||||
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.8/12.8 MB 3.6 MB/s eta 0:00:00\n",
|
||||
"Requirement already satisfied: spacy<3.4.0,>=3.3.0.dev0 in ./.env/lib/python3.10/site-packages (from en-core-web-sm==3.3.0) (3.3.1)\n",
|
||||
"Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (4.64.0)\n",
|
||||
"Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.9.1)\n",
|
||||
"Requirement already satisfied: srsly<3.0.0,>=2.4.3 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.4.3)\n",
|
||||
"Requirement already satisfied: typer<0.5.0,>=0.3.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.4.1)\n",
|
||||
"Requirement already satisfied: setuptools in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (59.6.0)\n",
|
||||
"Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.7)\n",
|
||||
"Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.0.2)\n",
|
||||
"Requirement already satisfied: blis<0.8.0,>=0.4.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.7.8)\n",
|
||||
"Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.0.7)\n",
|
||||
"Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.9 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.9)\n",
|
||||
"Requirement already satisfied: requests<3.0.0,>=2.13.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.28.0)\n",
|
||||
"Requirement already satisfied: numpy>=1.15.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.23.0)\n",
|
||||
"Requirement already satisfied: cymem<2.1.0,>=2.0.2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.6)\n",
|
||||
"Requirement already satisfied: pathy>=0.3.5 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.6.1)\n",
|
||||
"Requirement already satisfied: jinja2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.1.2)\n",
|
||||
"Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.3.0)\n",
|
||||
"Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.8.2)\n",
|
||||
"Requirement already satisfied: preshed<3.1.0,>=3.0.2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.6)\n",
|
||||
"Requirement already satisfied: thinc<8.1.0,>=8.0.14 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (8.0.17)\n",
|
||||
"Requirement already satisfied: packaging>=20.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (21.3)\n",
|
||||
"Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in ./.env/lib/python3.10/site-packages (from packaging>=20.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.9)\n",
|
||||
"Requirement already satisfied: smart-open<6.0.0,>=5.0.0 in ./.env/lib/python3.10/site-packages (from pathy>=0.3.5->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (5.2.1)\n",
|
||||
"Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.env/lib/python3.10/site-packages (from pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (4.2.0)\n",
|
||||
"Requirement already satisfied: charset-normalizer~=2.0.0 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.12)\n",
|
||||
"Requirement already satisfied: certifi>=2017.4.17 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2022.6.15)\n",
|
||||
"Requirement already satisfied: idna<4,>=2.5 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.3)\n",
|
||||
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.26.9)\n",
|
||||
"Requirement already satisfied: click<9.0.0,>=7.1.1 in ./.env/lib/python3.10/site-packages (from typer<0.5.0,>=0.3.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (8.1.3)\n",
|
||||
"Requirement already satisfied: MarkupSafe>=2.0 in ./.env/lib/python3.10/site-packages (from jinja2->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.1.1)\n",
|
||||
"Installing collected packages: en-core-web-sm\n",
|
||||
"Successfully installed en-core-web-sm-3.3.0\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;226m2022-06-25 14:21:57,983 | WARNING | Limiting concurrency to 1 because there are only 1 chunks\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:21:57,984 | INFO | Starting parallel map (concurrency: 1, chunk size: 1)\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:21:57,984 | WARNING | Running in series, there is no reason for parallelism\u001b[0m\n",
|
||||
"100%|██████████| 1/1 [03:26<00:00, 206.86s/it]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from typing import List, Tuple\n",
|
||||
"import json\n",
|
||||
"import gzip\n",
|
||||
"from great_ai import parallel_map, clean, is_english, predict_language\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def preprocess_chunk(chunk_key: str) -> List[Tuple[str, List[str]]]:\n",
|
||||
" # Extract\n",
|
||||
" response = urllib.request.urlopen(\n",
|
||||
" f\"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/{chunk_key}\"\n",
|
||||
" ) # a gzipped JSON Lines file\n",
|
||||
"\n",
|
||||
" decompressed = gzip.decompress(response.read())\n",
|
||||
" decoded = decompressed.decode()\n",
|
||||
" chunk = [json.loads(line) for line in decoded.split(\"\\n\") if line]\n",
|
||||
"\n",
|
||||
" # Transform\n",
|
||||
" return [\n",
|
||||
" (\n",
|
||||
" clean(\n",
|
||||
" f'{c[\"title\"]} {c[\"paperAbstract\"]} {c[\"journalName\"]} {c[\"venue\"]}',\n",
|
||||
" convert_to_ascii=True,\n",
|
||||
" ), # The text is cleaned to remove PDF extraction, web scraping, and other common artifacts\n",
|
||||
" c[\"fieldsOfStudy\"],\n",
|
||||
" ) # Create pairs of `(text, [...domains])`\n",
|
||||
" for c in chunk\n",
|
||||
" if c[\"fieldsOfStudy\"] and is_english(predict_language(c[\"paperAbstract\"]))\n",
|
||||
" ]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"preprocessed_chunks = parallel_map(preprocess_chunk, chunks)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from itertools import chain\n",
|
||||
"\n",
|
||||
"preprocessed_data = list(chain(*preprocessed_chunks))\n",
|
||||
"X, y = zip(\n",
|
||||
" *preprocessed_data\n",
|
||||
") # X is the input, y is the expected (ground truth) output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load\n",
|
||||
"\n",
|
||||
"Upload the dataset (or a part of it) to a central repository using `great_ai.add_ground_truth`. This step automatically tags each datapoint with a split label according to the ratios we set. Additional tags can be also given.\n",
|
||||
"\n",
|
||||
"#### Production-ready backend\n",
|
||||
"\n",
|
||||
"The MongoDB driver is automatically configured if `mongo.ini` exists with the following scheme:\n",
|
||||
"\n",
|
||||
"```ini\n",
|
||||
"mongo_connection_string=mongodb://localhost:27017/\n",
|
||||
"mongo_database=my_great_ai_db\n",
|
||||
"```\n",
|
||||
"> You can install MongoDB from [here](https://www.mongodb.com/docs/manual/installation) or [use it as a service](https://www.mongodb.com/cloud/atlas/register)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,989 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,990 | INFO | Found credentials file (/data/projects/great_ai_example/mongo.ini), initialising MongodbDriver\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,991 | INFO | Found credentials file (/data/projects/great_ai_example/mongo.ini), initialising LargeFileMongo\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,992 | INFO | Settings: configured ✅\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,993 | INFO | 🔩 tracing_database: MongodbDriver\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,994 | INFO | 🔩 large_file_implementation: LargeFileMongo\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,994 | INFO | 🔩 is_production: False\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,995 | INFO | 🔩 should_log_exception_stack: True\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,996 | INFO | 🔩 prediction_cache_size: 512\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,997 | INFO | 🔩 dashboard_table_size: 50\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,998 | WARNING | You still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,998 | WARNING | > Find out more at https://se-ml.github.io/practices/\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from great_ai import add_ground_truth\n",
|
||||
"\n",
|
||||
"add_ground_truth(X, y, train_split_ratio=0.8, test_split_ratio=0.2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Next: [Part 2](train.ipynb)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.10.4 ('.env': venv)",
|
||||
"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": "3.10.4"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "c1f394f9662881005685eeb18d8f9f77079b1b8b9a5ece1f825bfa01fcb7f52f"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
2135
examples/simple/data/index.html
Normal file
2135
examples/simple/data/index.html
Normal file
File diff suppressed because one or more lines are too long
242
examples/simple/deploy/deploy.ipynb
Normal file
242
examples/simple/deploy/deploy.ipynb
Normal file
File diff suppressed because one or more lines are too long
2048
examples/simple/deploy/index.html
Normal file
2048
examples/simple/deploy/index.html
Normal file
File diff suppressed because one or more lines are too long
2655
examples/simple/train/index.html
Normal file
2655
examples/simple/train/index.html
Normal file
File diff suppressed because one or more lines are too long
1811
examples/simple/train/train.ipynb
Normal file
1811
examples/simple/train/train.ipynb
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue