andras/great-ai
andras/great-ai
Watch
1
0
Fork
You've already forked great-ai
 0
Code Issues Pull requests 2 Projects Releases 4 Packages 1 Wiki Activity Actions

Simplify notebook setup

Browse source
This commit is contained in:
Andras Schmelczer 2026-10-28 22:34:22 +00:00
commit 13dadc74ed
4 changed files with 66 additions and 531 deletions
Download patch file Download diff file Expand all files Collapse all files

56
docs/examples/simple/data.ipynb
View file

@ -29,56 +29,18 @@
"\n",
"Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
"See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
"and full-data options. Generated artifacts stay under `.cache/notebooks/`.\n"
"and full-data options. Run related notebooks from the same working directory\n",
"to share the default `.cache/` model store and `tracing_database.json` database.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "a800dc4d",
"metadata": {},
"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;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n",
"\u001b[38;5;39mGreatAI (v0.1.11): 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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Notebook artifacts: /Users/schmelczer/Projects/great-ai/.cache/notebooks/simple\n"
]
}
],
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"# Works when opened from the repository root or any notebook directory.\n",
"_start = Path(globals().get(\"__file__\", Path.cwd())).resolve()\n",
"ROOT = next(\n",
" p\n",
" for p in [_start, *_start.parents]\n",
" if (p / \"pyproject.toml\").is_file() and (p / \"great_ai\").is_dir()\n",
")\n",
"sys.path.insert(0, str(ROOT / \"docs\"))\n",
"from notebook_support import setup_notebook, mag_lines\n",
"\n",
"FULL_RUN = os.environ.get(\"GREAT_AI_NOTEBOOK_FULL\") == \"1\"\n",
"WORK_DIR = setup_notebook(ROOT, \"simple\")\n",
"DATA_DIR = ROOT / \"docs/tutorial/data\""
"from docs.notebook_support import DATA_DIR, FULL_RUN, mag_lines"
]
},
{
@ -157,10 +119,10 @@
"source": [
"### Load\n",
"\n",
"Store the dataset in the local TinyDB tracing database. All notebooks in\n",
"this example share `.cache/notebooks/simple/` (or `simple-full/`). No S3 or\n",
"MongoDB credentials are needed. A dataset tag makes rerunning this cell\n",
"replace just this example's ground truth instead of duplicating it."
"Store the dataset in the default local TinyDB tracing database,\n",
"`tracing_database.json`. Run the data, training and deployment notebooks\n",
"from the same working directory to share it. A dataset tag makes rerunning\n",
"this cell replace just this example's ground truth instead of duplicating it."
]
},
{

52
docs/examples/simple/deploy.ipynb
View file

@ -28,56 +28,8 @@
"\n",
"Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
"See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
"and full-data options. Generated artifacts stay under `.cache/notebooks/`.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "b7a9d250",
"metadata": {},
"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;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n",
"\u001b[38;5;39mGreatAI (v0.1.11): 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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Notebook artifacts: /Users/schmelczer/Projects/great-ai/.cache/notebooks/simple\n"
]
}
],
"source": [
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"# Works when opened from the repository root or any notebook directory.\n",
"_start = Path(globals().get(\"__file__\", Path.cwd())).resolve()\n",
"ROOT = next(\n",
" p\n",
" for p in [_start, *_start.parents]\n",
" if (p / \"pyproject.toml\").is_file() and (p / \"great_ai\").is_dir()\n",
")\n",
"sys.path.insert(0, str(ROOT / \"docs\"))\n",
"from notebook_support import setup_notebook, mag_lines\n",
"\n",
"FULL_RUN = os.environ.get(\"GREAT_AI_NOTEBOOK_FULL\") == \"1\"\n",
"WORK_DIR = setup_notebook(ROOT, \"simple\")\n",
"DATA_DIR = ROOT / \"docs/tutorial/data\""
"and full-data options. Run related notebooks from the same working directory\n",
"to share the default `.cache/` model store and `tracing_database.json` database.\n"
]
},
{

54
docs/examples/simple/stacked-bars.ipynb
View file

@ -9,56 +9,8 @@
"\n",
"Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
"See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
"and full-data options. Generated artifacts stay under `.cache/notebooks/`.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f0cae36d",
"metadata": {},
"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;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n",
"\u001b[38;5;39mGreatAI (v0.1.11): 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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Notebook artifacts: /Users/schmelczer/Projects/great-ai/.cache/notebooks/simple\n"
]
}
],
"source": [
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"# Works when opened from the repository root or any notebook directory.\n",
"_start = Path(globals().get(\"__file__\", Path.cwd())).resolve()\n",
"ROOT = next(\n",
" p\n",
" for p in [_start, *_start.parents]\n",
" if (p / \"pyproject.toml\").is_file() and (p / \"great_ai\").is_dir()\n",
")\n",
"sys.path.insert(0, str(ROOT / \"docs\"))\n",
"from notebook_support import setup_notebook, mag_lines\n",
"\n",
"FULL_RUN = os.environ.get(\"GREAT_AI_NOTEBOOK_FULL\") == \"1\"\n",
"WORK_DIR = setup_notebook(ROOT, \"simple\")\n",
"DATA_DIR = ROOT / \"docs/tutorial/data\""
"and full-data options. Run related notebooks from the same working directory\n",
"to share the default `.cache/` model store and `tracing_database.json` database.\n"
]
},
{
@ -126,7 +78,7 @@
"ax.legend()\n",
"ax.set_ylabel(\"Ratio of all publications\")\n",
"fig.tight_layout()\n",
"fig.savefig(WORK_DIR / \"ss-distribution.png\", dpi=500)\n",
"fig.savefig(\"ss-distribution.png\", dpi=500)\n",
"None"
]
}

48
docs/examples/simple/train.ipynb
View file

@ -26,56 +26,18 @@
"\n",
"Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
"See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
"and full-data options. Generated artifacts stay under `.cache/notebooks/`.\n"
"and full-data options. Run related notebooks from the same working directory\n",
"to share the default `.cache/` model store and `tracing_database.json` database.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "d8ae0655",
"metadata": {},
"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;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n",
"\u001b[38;5;39mGreatAI (v0.1.11): 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"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Notebook artifacts: /Users/schmelczer/Projects/great-ai/.cache/notebooks/simple\n"
]
}
],
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"# Works when opened from the repository root or any notebook directory.\n",
"_start = Path(globals().get(\"__file__\", Path.cwd())).resolve()\n",
"ROOT = next(\n",
" p\n",
" for p in [_start, *_start.parents]\n",
" if (p / \"pyproject.toml\").is_file() and (p / \"great_ai\").is_dir()\n",
")\n",
"sys.path.insert(0, str(ROOT / \"docs\"))\n",
"from notebook_support import setup_notebook, mag_lines\n",
"\n",
"FULL_RUN = os.environ.get(\"GREAT_AI_NOTEBOOK_FULL\") == \"1\"\n",
"WORK_DIR = setup_notebook(ROOT, \"simple\")\n",
"DATA_DIR = ROOT / \"docs/tutorial/data\""
"from docs.notebook_support import FULL_RUN"
]
},
{