Upload notebooks/00_setup/00_install_packages.ipynb with huggingface_hub
Browse files
notebooks/00_setup/00_install_packages.ipynb
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"metadata": {},
|
| 6 |
+
"source": [
|
| 7 |
+
"# Install Analysis Packages\n",
|
| 8 |
+
"\n",
|
| 9 |
+
"Install all required Python packages for the research document analysis system.\n",
|
| 10 |
+
"Run this notebook once to set up the environment."
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"cell_type": "code",
|
| 15 |
+
"metadata": {},
|
| 16 |
+
"source": [
|
| 17 |
+
"!pip install jupyterlab bertopic hdbscan umap-learn plotly seaborn wordcloud kaleido keybert textblob opencv-python-headless ipywidgets papermill kaggle"
|
| 18 |
+
],
|
| 19 |
+
"execution_count": null,
|
| 20 |
+
"outputs": []
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"cell_type": "code",
|
| 24 |
+
"metadata": {},
|
| 25 |
+
"source": [
|
| 26 |
+
"import importlib\n",
|
| 27 |
+
"\n",
|
| 28 |
+
"packages = [\n",
|
| 29 |
+
" (\"jupyterlab\", \"jupyterlab\"),\n",
|
| 30 |
+
" (\"bertopic\", \"BERTopic\"),\n",
|
| 31 |
+
" (\"hdbscan\", \"HDBSCAN\"),\n",
|
| 32 |
+
" (\"umap\", \"UMAP-learn\"),\n",
|
| 33 |
+
" (\"plotly\", \"Plotly\"),\n",
|
| 34 |
+
" (\"seaborn\", \"Seaborn\"),\n",
|
| 35 |
+
" (\"wordcloud\", \"WordCloud\"),\n",
|
| 36 |
+
" (\"kaleido\", \"Kaleido\"),\n",
|
| 37 |
+
" (\"keybert\", \"KeyBERT\"),\n",
|
| 38 |
+
" (\"textblob\", \"TextBlob\"),\n",
|
| 39 |
+
" (\"cv2\", \"OpenCV\"),\n",
|
| 40 |
+
" (\"ipywidgets\", \"ipywidgets\"),\n",
|
| 41 |
+
" (\"papermill\", \"Papermill\"),\n",
|
| 42 |
+
" (\"kaggle\", \"Kaggle\"),\n",
|
| 43 |
+
"]\n",
|
| 44 |
+
"\n",
|
| 45 |
+
"print(f\"{'Package':<25} {'Status':<15} {'Version'}\")\n",
|
| 46 |
+
"print(\"-\" * 60)\n",
|
| 47 |
+
"\n",
|
| 48 |
+
"for module_name, display_name in packages:\n",
|
| 49 |
+
" try:\n",
|
| 50 |
+
" mod = importlib.import_module(module_name)\n",
|
| 51 |
+
" version = getattr(mod, \"__version__\", \"unknown\")\n",
|
| 52 |
+
" print(f\"{display_name:<25} {'OK':<15} {version}\")\n",
|
| 53 |
+
" except ImportError as e:\n",
|
| 54 |
+
" print(f\"{display_name:<25} {'MISSING':<15} {e}\")"
|
| 55 |
+
],
|
| 56 |
+
"execution_count": null,
|
| 57 |
+
"outputs": []
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"cell_type": "code",
|
| 61 |
+
"metadata": {},
|
| 62 |
+
"source": [
|
| 63 |
+
"!python -m textblob.download_corpora"
|
| 64 |
+
],
|
| 65 |
+
"execution_count": null,
|
| 66 |
+
"outputs": []
|
| 67 |
+
}
|
| 68 |
+
],
|
| 69 |
+
"metadata": {
|
| 70 |
+
"kernelspec": {
|
| 71 |
+
"display_name": "Python 3",
|
| 72 |
+
"language": "python",
|
| 73 |
+
"name": "python3"
|
| 74 |
+
},
|
| 75 |
+
"language_info": {
|
| 76 |
+
"name": "python",
|
| 77 |
+
"version": "3.10.0"
|
| 78 |
+
}
|
| 79 |
+
},
|
| 80 |
+
"nbformat": 4,
|
| 81 |
+
"nbformat_minor": 5
|
| 82 |
+
}
|