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
1 changed files with 66 additions and 531 deletions
Download patch file Download diff file Expand all files Collapse all files

56
docs/examples/simple-mag/train.ipynb
View file

@ -10,8 +10,8 @@
"By default this notebook uses 100 training and 30 test samples per class\n",
"and a small Naive Bayes parameter search for a quick local run. Set\n",
"`GREAT_AI_NOTEBOOK_FULL=1` before launching Jupyter to use all bundled data\n",
"and the larger search. Generated figures are saved under the printed\n",
"artifact directory. Local subset scores do not reproduce the historical\n",
"and the larger search. Generated figures are saved in the working directory.\n",
"Local subset scores do not reproduce the historical\n",
"full-dataset comparison with the 2019 SciBERT baseline (macro F1 0.6571)."
]
},
@ -24,56 +24,18 @@
"\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": "4a11c71a",
"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-mag\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-mag\")\n",
"DATA_DIR = ROOT / \"docs/tutorial/data\""
"from docs.notebook_support import DATA_DIR, FULL_RUN, mag_lines"
]
},
{
@ -149,7 +111,7 @@
"ax.bar(domains, counts)\n",
"ax.set_ylabel(\"Count\")\n",
"fig.tight_layout()\n",
"fig.savefig(WORK_DIR / \"mag-distribution.png\", dpi=500)\n",
"fig.savefig(\"mag-distribution.png\", dpi=500)\n",
"None"
]
},
@ -2806,7 +2768,7 @@
" values_format=\".2f\",\n",
")\n",
"plt.tight_layout()\n",
"plt.savefig(WORK_DIR / \"mag-confusion.png\", dpi=600)"
"plt.savefig(\"mag-confusion.png\", dpi=600)"
]
}
],