diff options
| author | Eugene Triguba <hello@eugenetriguba.com> | 2026-05-23 14:07:08 +0000 |
|---|---|---|
| committer | Eugene Triguba <hello@eugenetriguba.com> | 2026-05-23 14:07:08 +0000 |
| commit | 2d5e4794886164249a0723fd6a0d38fee300a7f1 (patch) | |
| tree | 8bf2a2d715beaf9217307f57b45dd0dffe5d4107 | |
| parent | Add env to test (diff) | |
| download | nb-2d5e4794886164249a0723fd6a0d38fee300a7f1.zip | |
Remove execution count from outputs when cleaning
| -rw-r--r-- | nb/clean.py | 12 | ||||
| -rw-r--r-- | nbs/clean.ipynb | 73 |
2 files changed, 78 insertions, 7 deletions
diff --git a/nb/clean.py b/nb/clean.py index 27a54c1..1d97104 100644 --- a/nb/clean.py +++ b/nb/clean.py @@ -6,11 +6,19 @@ from nbformat import NotebookNode from nb.export import read_nb, PathOrFileLike +# cell: b436a7c3 +def _clean_cell_output(cell:NotebookNode)->NotebookNode: + for o in cell.get('outputs', []): + if 'execution_count' in o: + o['execution_count'] = None + return cell + # cell: 4c127179 def _clean_cell(cell:NotebookNode): if 'execution_count' in cell: cell['execution_count'] = None - if cell['source'].strip() == '': cell['source'] = [] - return cell + if cell['source'] == '': cell['source'] = [] + cell['metadata'] = {} + return _clean_cell_output(cell) # cell: 944a371b _allowed_nb_metadata_keys = {"kernelspec", "jupytext", "widgets"} diff --git a/nbs/clean.ipynb b/nbs/clean.ipynb index 681a5ce..67519a0 100644 --- a/nbs/clean.ipynb +++ b/nbs/clean.ipynb @@ -7,6 +7,7 @@ "metadata": {}, "outputs": [], "source": [ + "%%capture\n", "%load_ext autoreload\n", "%autoreload 2" ] @@ -42,6 +43,7 @@ "metadata": {}, "outputs": [], "source": [ + "import copy\n", "from nb import test" ] }, @@ -56,6 +58,52 @@ ] }, { + "cell_type": "markdown", + "id": "ecefd668", + "metadata": {}, + "source": [ + "One of the inherent challenges with Jupyter notebooks is they can have noisy diffs when you use them with version control systems. This can make it harder to tell what has actually changed when reviewing.\n", + "\n", + "To alleviate this problem, we can 'clean' the notebooks before we check them in." + ] + }, + { + "cell_type": "markdown", + "id": "4af091bd", + "metadata": {}, + "source": [ + "If a notebook cell is a code cell, then it will have an 'outputs' section. Some of these output cells have 'execution_count's, which we want to clear because it does not matter how many times a cell was executed when reviewing a change." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b436a7c3", + "metadata": {}, + "outputs": [], + "source": [ + "#| export\n", + "def _clean_cell_output(cell:NotebookNode)->NotebookNode:\n", + " for o in cell.get('outputs', []):\n", + " if 'execution_count' in o:\n", + " o['execution_count'] = None\n", + " return cell" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0823ae66", + "metadata": {}, + "outputs": [], + "source": [ + "o = nbformat.v4.new_output('execute_result', data={'text/plain': '42'}, execution_count=5)\n", + "cc = nbformat.v4.new_code_cell(source=[], outputs=[o])\n", + "cleaned = _clean_cell_output(copy.deepcopy(cc))\n", + "test.equal(cleaned, {**cc, 'outputs': [{**o, 'execution_count': None}]})" + ] + }, + { "cell_type": "code", "execution_count": null, "id": "4c127179", @@ -65,8 +113,9 @@ "#| export\n", "def _clean_cell(cell:NotebookNode):\n", " if 'execution_count' in cell: cell['execution_count'] = None\n", - " if cell['source'].strip() == '': cell['source'] = []\n", - " return cell" + " if cell['source'] == '': cell['source'] = []\n", + " cell['metadata'] = {}\n", + " return _clean_cell_output(cell)" ] }, { @@ -77,7 +126,8 @@ "outputs": [], "source": [ "cc = nbformat.v4.new_code_cell(\"print('hello')\", execution_count=10)\n", - "test.equal(_clean_cell(cc.copy()), {**cc, 'execution_count': None})" + "cleaned = _clean_cell(copy.deepcopy(cc))\n", + "test.equal(cleaned, {**cc, 'execution_count': None})" ] }, { @@ -87,8 +137,21 @@ "metadata": {}, "outputs": [], "source": [ - "cc = nbformat.v4.new_code_cell(\" \\n \\t\")\n", - "test.equal(_clean_cell(cc.copy()), {**cc, 'source': []})" + "cc = nbformat.v4.new_code_cell(\"\")\n", + "cleaned = _clean_cell(copy.deepcopy(cc))\n", + "test.equal(cleaned, {**cc, 'source': []})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ef055ecb", + "metadata": {}, + "outputs": [], + "source": [ + "cc = nbformat.v4.new_code_cell(\"print('hello')\", metadata={\"some_key\": 1})\n", + "cleaned = _clean_cell(copy.deepcopy(cc))\n", + "test.equal(cleaned, {**cc, 'metadata': {}})" ] }, { |