Upgrade notebook examples with inline metadata

.gitignore

@@ -8,3 +8,4 @@ data/
 dist/
 mair/
 .DS_Store
+data.zip

notebooks/getting-started.ipynb

@@ -1,5 +1,25 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b640237c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# /// script\n",
+    "# requires-python = \"==3.12\"\n",
+    "# dependencies = [\n",
+    "#     \"cev\",\n",
+    "#     \"pooch==1.8.2\",\n",
+    "#     \"pyarrow\",\n",
+    "# ]\n",
+    "#\n",
+    "# [tool.uv.sources]\n",
+    "# cev = { path = \"../\" }\n",
+    "# ///"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8efc6d60-f207-4e54-92b0-a6070b0158b4",
@@ -16,12 +36,13 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "47c31bea-24b3-4d16-a69a-a3ad3a746234",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
+    "import zipfile\n",
+    "\n",
     "import pandas as pd\n",
+    "import pooch\n",
     "\n",
     "from cev.widgets import Embedding, EmbeddingComparisonWidget"
    ]
@@ -43,22 +64,21 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "dbf802bc-f709-4163-9b49-8fa5f6ce59ab",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# download the data\n",
-    "!curl -sL https://figshare.com/ndownloader/articles/23063615/versions/1 -o data.zip\n",
-    "!unzip data.zip -d data"
+    "archive = pooch.retrieve(\n",
+    "    url=\"https://figshare.com/ndownloader/articles/23063615/versions/1\",\n",
+    "    path=pooch.os_cache(\"cev\"),\n",
+    "    fname=\"data.zip\",\n",
+    "    known_hash=None,\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "e62390d2-1242-49a8-9780-be976d39fa42",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "source": [
     "## Comparing Two Embeddings of the same Data\n",
     "\n",
@@ -76,26 +96,23 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "7874813c-810f-40e5-92ab-91f228046a5e",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "tissue_umap_embedding = Embedding.from_ozette(\n",
-    "    df=pd.read_parquet(\"./data/mair-2022-tissue-138-umap.pq\")\n",
-    ")\n",
-    "tissue_ozette_embedding = Embedding.from_ozette(\n",
-    "    df=pd.read_parquet(\"./data/mair-2022-tissue-138-ozette.pq\")\n",
-    ")"
+    "with zipfile.ZipFile(archive, \"r\") as z:\n",
+    "    with z.open(\"mair-2022-tissue-138-umap.pq\") as f:\n",
+    "        tissue_umap_embedding = pd.read_parquet(f).pipe(Embedding.from_ozette)\n",
+    "    with z.open(\"mair-2022-tissue-138-ozette.pq\") as f:\n",
+    "        tissue_ozette_embedding = pd.read_parquet(f).pipe(Embedding.from_ozette)\n",
+    "    with z.open(\"mair-2022-tumor-006-ozette.pq\") as f:\n",
+    "        tumor_ozette_embedding = pd.read_parquet(f).pipe(Embedding.from_ozette)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "c3d7e114-9fd3-4785-bdca-e3f4bbf37df8",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "umap_vs_ozette = EmbeddingComparisonWidget(\n",
@@ -126,9 +143,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ba7a378f-4212-4953-be5b-7a273f8bc75e",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "umap_vs_ozette.select([\"CD3+\", \"CD4+\", \"CD8-\"])"
@@ -144,27 +159,11 @@
     "Instead of comparing identical data, let's take a look at two transformed and aligned embeddings: tissue vs tumor. The embeddings are both annotation-transformed and aligned, ensuring low confusion and high neighborhood similarity (check to confirm!). The abundance metric aids in identifying potential shifts in phenotype abundance, providing a comprehensive and visually intuitive method for analyzing complex cytometry data. Remember, our metric should be used as a exploratory tool guide exploration and quickly surface potentially interesting phenotypes, but robust statical methods must be applied to confirm whether any abundance differences exist."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "180f0945-d97c-4261-aa67-5368e3b560ad",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "tumor_ozette_embedding = Embedding.from_ozette(\n",
-    "    df=pd.read_parquet(\"./data/mair-2022-tumor-006-ozette.pq\")\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "0f99361b-6e96-4a6d-ad65-0533c23bece7",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "tissue_vs_tumor = EmbeddingComparisonWidget(\n",
@@ -183,9 +182,7 @@
   {
    "cell_type": "markdown",
    "id": "6d632c95-dff8-4b90-b763-f3055c4e8047",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "source": [
     "The following **CD8+ T cells** are more abundant in `tissue` (i.e., the relative abundance is higher on the left) compared to `tumor` (i.e., the relative abundance is lower on the right)"
    ]
@@ -194,28 +191,18 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "2f7ebd73-32e7-48ed-8575-8d14d2edc73f",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "tissue_vs_tumor.select(\n",
     "    \"CD4-CD8+CD3+CD45RA+CD27+CD19-CD103-CD28-CD69+PD1+HLADR-GranzymeB-CD25-ICOS-TCRgd-CD38-CD127-Tim3-\"\n",
     ")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "eefac753-7920-4c87-99ef-d155f1ec5114",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -224,12 +211,8 @@
     "name": "ipython",
     "version": 3
    },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,

pyproject.toml

@@ -28,8 +28,6 @@ dependencies = [
     "jupyter-scatter>=0.14.0",
     "pandas>=1.0,<2.0",
     "numpy>=1.0,<2.0",
-    "pyarrow",
-    "pooch>=1.3.0",
 ]
 dynamic = ["version"]