From c3cd4ce537a2084609cd091cfcf4f6144b5e129f Mon Sep 17 00:00:00 2001
From: Alex Wolf <f.alexander.wolf@gmail.com>
Date: Fri, 18 Oct 2024 23:06:58 +0200
Subject: [PATCH] =?UTF-8?q?=F0=9F=92=9A=20Fix=20&=20polish=20analysis-flow?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../register_example_file.py                  |  1 -
 docs/analysis-flow.ipynb                      | 62 ++++++++-----------
 2 files changed, 25 insertions(+), 38 deletions(-)

diff --git a/docs/analysis-flow-scripts/register_example_file.py b/docs/analysis-flow-scripts/register_example_file.py
index e0f6da9..9594882 100644
--- a/docs/analysis-flow-scripts/register_example_file.py
+++ b/docs/analysis-flow-scripts/register_example_file.py
@@ -1,7 +1,6 @@
 import lamindb as ln
 import bionty as bt
 
-
 ln.track("K4wsS5DTYdFp0000")
 
 # an example dataset that has a few cell type, tissue and disease annotations
diff --git a/docs/analysis-flow.ipynb b/docs/analysis-flow.ipynb
index 306e9d8..e14d861 100644
--- a/docs/analysis-flow.ipynb
+++ b/docs/analysis-flow.ipynb
@@ -19,9 +19,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Here, we'll track typical data transformations like subsetting that occur during analysis.\n",
-    "\n",
-    "If exploring more generally, read this first: {doc}`/project-flow`."
+    "Here, we'll track typical data transformations like subsetting that occur during analysis."
    ]
   },
   {
@@ -35,7 +33,7 @@
    "outputs": [],
    "source": [
     "# !pip install 'lamindb[jupyter,bionty]'\n",
-    "!lamin init --storage ./analysis-usecase --schema bionty"
+    "!lamin init --storage ./analysis-flow --schema bionty"
    ]
   },
   {
@@ -45,8 +43,7 @@
    "outputs": [],
    "source": [
     "import lamindb as ln\n",
-    "import bionty as bt\n",
-    "from lamin_utils import logger"
+    "import bionty as bt"
    ]
   },
   {
@@ -54,14 +51,18 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Register an initial dataset"
+    "## Save an initial dataset"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Here we register an initial artifact with a pipeline script [register_example_file.py](https://github.com/laminlabs/lamin-usecases/blob/main/docs/analysis-flow-scripts/register_example_file.py)."
+    "```{eval-rst}\n",
+    ".. literalinclude:: analysis-flow-scripts/register_example_file.py\n",
+    "   :language: python\n",
+    "   :caption: register_example_file.py\n",
+    "```"
    ]
   },
   {
@@ -81,7 +82,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Pull the registered dataset, apply a transformation, and register the result"
+    "## Open a dataset, subset it, and register the result"
    ]
   },
   {
@@ -159,8 +160,8 @@
    },
    "outputs": [],
    "source": [
-    "cell_types = artifact.cell_types.all().lookup(return_field=\"name\")\n",
-    "diseases = artifact.diseases.all().lookup(return_field=\"name\")"
+    "cell_types = artifact.cell_types.all().distinct().lookup(return_field=\"name\")\n",
+    "diseases = artifact.diseases.all().distinct().lookup(return_field=\"name\")"
    ]
   },
   {
@@ -241,7 +242,6 @@
     "    },\n",
     "    organism=\"human\",\n",
     ")\n",
-    "\n",
     "curate.validate()"
    ]
   },
@@ -255,19 +255,7 @@
    },
    "outputs": [],
    "source": [
-    "artifact = curate.save_artifact(description=\"anndata with obs subset\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "hide-output"
-    ]
-   },
-   "outputs": [],
-   "source": [
+    "artifact = curate.save_artifact(description=\"anndata with obs subset\")\n",
     "artifact.describe()"
    ]
   },
@@ -276,7 +264,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Examine data flow"
+    "## Examine data lineage"
    ]
   },
   {
@@ -342,20 +330,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(\"--> What is the history of this artifact?\\n\")\n",
+    "print(\"--> What is the lineage of this artifact?\\n\")\n",
     "artifact.view_lineage()\n",
     "\n",
     "print(\"\\n\\n--> Which features and labels are associated with it?\\n\")\n",
-    "logger.print(artifact.features)\n",
-    "logger.print(artifact.labels)\n",
+    "print(artifact.features)\n",
+    "print(artifact.labels)\n",
     "\n",
-    "print(\"\\n\\n--> Which notebook analyzed and registered this artifact\\n\")\n",
-    "logger.print(artifact.transform)\n",
+    "print(\"\\n\\n--> Which notebook analyzed and saved this artifact\\n\")\n",
+    "print(artifact.transform)\n",
     "\n",
-    "print(\"\\n\\n--> By whom\\n\")\n",
-    "logger.print(artifact.created_by)\n",
+    "print(\"\\n\\n--> Who save this artifact?\\n\")\n",
+    "print(artifact.created_by)\n",
     "\n",
-    "print(\"\\n\\n--> And which artifact is its parent\\n\")\n",
+    "print(\"\\n\\n--> Which artifacts were inputs?\\n\")\n",
     "display(artifact.run.input_artifacts.df())"
    ]
   },
@@ -369,8 +357,8 @@
    },
    "outputs": [],
    "source": [
-    "!rm -r ./analysis-usecase\n",
-    "!lamin delete --force analysis-usecase"
+    "!rm -r ./analysis-flow\n",
+    "!lamin delete --force analysis-flow"
    ]
   }
  ],
@@ -393,7 +381,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.10.13"
   },
   "nbproject": {
    "id": "eNef4Arw8nNM",