more refences to documentation

settylab · Aug 30, 2023 · 99bb40f · 99bb40f
1 parent 56434e2
commit 99bb40f
Show file tree

Hide file tree

Showing 3 changed files with 116 additions and 8 deletions.
diff --git a/docs/source/serialization.rst b/docs/source/serialization.rst
@@ -52,7 +52,7 @@ density, refer to our
 Deserialization from AnnData
 ----------------------------
 
-The function `mellon.Predictor.from_dict` can deserialize the
+The function :meth:`mellon.Predictor.from_dict` can deserialize the
 :class:`mellon.Predictor` and any sub class.
 
 .. code-block:: python
@@ -69,9 +69,10 @@ The function `mellon.Predictor.from_dict` can deserialize the
 Serialization to File
 ---------------------
 
-Mellon supports serialization to a human-readable JSON file and compressed file formats such as .gz (gzip) and .bz2 (bzip2).
+Mellon supports serialization to a human-readable JSON file and compressed file
+formats such as .gz (gzip) and .bz2 (bzip2).
 
-The function `mellon.Predictor.from_json` can deserialize the
+The function :meth:`mellon.Predictor.from_json` can deserialize the
 :class:`mellon.Predictor` and any sub class.
 
 .. code-block:: python
@@ -88,7 +89,8 @@ The function `mellon.Predictor.from_json` can deserialize the
 Deserialization from File
 -------------------------
 
-Mellon supports deserialization from JSON and compressed file formats. The compression method can be inferred from the file extension.
+Mellon supports deserialization from JSON and compressed file formats. The
+compression method can be inferred from the file extension.
 
 .. code-block:: python
 

diff --git a/notebooks/time-series_tutorial.ipynb b/notebooks/time-series_tutorial.ipynb
@@ -370,7 +370,9 @@
    "source": [
     "## Step 4: Density Evaluation and Plotting\n",
     "\n",
-    "The cell-state density can be evaluated for any time point. For instance, we can evaluate the\n",
+    "The `density_predictor` is a subclass of the\n",
+    "[mellon.base_predictor.PredictorTime](https://mellon.readthedocs.io/en/latest/predictor.html#mellon.base_predictor.PredictorTime).\n",
+    "Thus the cell-state density can be evaluated for any time point. For instance, we can evaluate the\n",
     "density for all cell states at stage E7.10 wich is notably not covered by a sample."
    ]
   },
@@ -723,7 +725,11 @@
     "\n",
     "## Step 7: Saving the Predictor\n",
     "\n",
-    "The density predictor can be serialized and saved for future use. It can be stored in the AnnData `uns` attribute, and the AnnData can be saved with the `write` method. The predictor can be reconstructed using the `from_dict` method of `mellon.Predictor`."
+    "The density predictor can be serialized and saved for future use.\n",
+    "It can be stored in the AnnData `uns` attribute, and the AnnData can be saved with the `write` method.\n",
+    "The predictor can be reconstructed using the\n",
+    "[from_dict](https://mellon.readthedocs.io/en/latest/predictor.html#mellon.Predictor.from_dict)\n",
+    "method of [mellon.Predictor](https://mellon.readthedocs.io/en/latest/predictor.html#mellon.Predictor)."
    ]
   },
   {
@@ -830,7 +836,105 @@
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {
-    "state": {},
+    "state": {
+     "009d4a832bc547eda98b7134b8bfa189": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "0956b753c5db4344907cbdc9934269bd": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "1b675b44738948378acc3e81a5a190e1": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "children": [
+        "IPY_MODEL_339b3c18a5a249ba93043baf40ec7e4f",
+        "IPY_MODEL_22e8e9adc7de4f88bdaae6afa680dc7c",
+        "IPY_MODEL_6ccb85f98c8e4378b7a9dc92691a001c"
+       ],
+       "layout": "IPY_MODEL_7b4c74dd7d054a5c821a9a25958b1258"
+      }
+     },
+     "22e8e9adc7de4f88bdaae6afa680dc7c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "bar_style": "success",
+       "layout": "IPY_MODEL_009d4a832bc547eda98b7134b8bfa189",
+       "max": 18684354899,
+       "style": "IPY_MODEL_fe530b4f59bb414796f46b1e5716f344",
+       "value": 18684354899
+      }
+     },
+     "339b3c18a5a249ba93043baf40ec7e4f": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_ee6bc90a82fb468c9cb840306406f599",
+       "style": "IPY_MODEL_0956b753c5db4344907cbdc9934269bd",
+       "value": "100%"
+      }
+     },
+     "604ee0f3c5c542c2a39e2d2ba52aa852": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "6ccb85f98c8e4378b7a9dc92691a001c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_e0bae8abaf084635bc297e90a0330ad9",
+       "style": "IPY_MODEL_604ee0f3c5c542c2a39e2d2ba52aa852",
+       "value": " 17.4G/17.4G [16:58&lt;00:00, 20.3MB/s]"
+      }
+     },
+     "7b4c74dd7d054a5c821a9a25958b1258": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "e0bae8abaf084635bc297e90a0330ad9": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "ee6bc90a82fb468c9cb840306406f599": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "fe530b4f59bb414796f46b1e5716f344": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     }
+    },
     "version_major": 2,
     "version_minor": 0
    }

diff --git a/notebooks/trajectory-trends_tutorial.ipynb b/notebooks/trajectory-trends_tutorial.ipynb
@@ -293,7 +293,9 @@
    "id": "8129bf9a",
    "metadata": {},
    "source": [
-    "Palantir also offers a wrapper for the `mellon.FunctionEstimator` to run the trend computation on all branches simultaneously and store them in `ad.varm[\"gene_trends_<fate>\"]`:"
+    "Palantir also offers a wrapper for the\n",
+    "[`mellon.FunctionEstimator`](https://mellon.readthedocs.io/en/uncertainty/model.html#mellon.model.FunctionEstimator)\n",
+    "to run the trend computation on all branches simultaneously and store them in `ad.varm[\"gene_trends_<fate>\"]`:"
    ]
   },
   {