add mddoclink to data tutorial

Author: voorhs

docs/source/docs_utils/apiref.py

@@ -98,8 +98,8 @@ class DocumentationLink(ReplacePattern):
     @staticmethod
     def link_to_doc_page(
         page_type: Literal["api", "tutorial", "guide"],
-        page: str,
-        anchor: str | None = None,
+        dotpath: str,
+        obj: str | None = None,
     ) -> str:
         """
         Create a link to a documentation page.
@@ -111,18 +111,18 @@ def link_to_doc_page(
                 - "tutorial" -- Tutorials
                 - "guide" -- User guides
 
-        :param page:
-            Name of the page without the common prefix.
+        :param dotpath:
+            Path to the index page in unix style.
 
-            So, to link to keywords, pass "script.core.keywords" as page (omitting the "chatsky" prefix).
+            So, to link Dataset, pass "context" as page (omitting the "autointent" prefix).
 
             To link to the basic script tutorial, pass "script.core.1_basics" (without the "tutorials" prefix).
 
             To link to the basic concepts guide, pass "basic_conceptions".
 
             API index pages are also supported.
             Passing "index_pipeline" will link to the "apiref/index_pipeline.html" page.
-        :param anchor:
+        :param obj:
             An anchor on the page. (optional)
 
             For the "api" type, use only the last part of the linked object.
@@ -134,12 +134,14 @@ def link_to_doc_page(
             A link to the corresponding documentation part.
         """
         if page_type == "api":
-            prefix = "" if page.startswith("index") else "chatsky."
-            return f"../apiref/{prefix}{page}.rst" + (f"#{prefix}{page}.{anchor}" if anchor is not None else "")
-        if page_type == "tutorial":
-            return f"../tutorials/tutorials.{page}.py" + (f"#{anchor}" if anchor is not None else "")
-        if page_type == "guide":
-            return f"../user_guides/{page}.rst" + (f"#{anchor}" if anchor is not None else "")
+            path = "/".join(dotpath.split("."))
+            return f"../autoapi/autointent/{path}/index.rst" + (
+                f"#autointent.{dotpath}.{obj}" if obj is not None else ""
+            )
+        # if page_type == "tutorial":
+        #     return f"../tutorials/tutorials.{page}.py" + (f"#{anchor}" if anchor is not None else "")
+        # if page_type == "guide":
+        #     return f"../guides/{page}.rst" + (f"#{anchor}" if anchor is not None else "")
         msg = "Unexpected page type"
         raise ValueError(msg)
 

docs/source/docs_utils/notebook.py

@@ -11,7 +11,7 @@
 from autointent.context.data_handler import Dataset
 
 # %%
-datasets.logging.disable_progress_bar() # disable tqdm outputs
+datasets.logging.disable_progress_bar()  # disable tqdm outputs
 
 # %% [markdown]
 """
@@ -101,9 +101,9 @@
 ```
 
 - `name`: A human-readable representation of the intent.
-- `tags`: Used in multilabel scenarios to predict the most probable class listed in a specific tag.
-- `regexp_partial_match` and `regexp_full_match`: Used by the `RegExp` module to predict intents based on provided patterns.
-- `description`: Used by the `DescriptionScorer` to calculate scores based on the similarity between an utterance and intent descriptions.
+- `tags`: Used in multilabel scenarios to predict the most probable class listed in a specific %mddoclink(api,context.data_handler,Tag).
+- `regexp_partial_match` and `regexp_full_match`: Used by the %mddoclink(api,modules,RegExp) module to predict intents based on provided patterns.
+- `description`: Used by the %mddoclink(api,modules.scoring,DescriptionScorer) to calculate scores based on the similarity between an utterance and intent descriptions.
 
 All fields in the `intents` list are optional except for `id`.
 """
@@ -122,6 +122,8 @@
 # %% [markdown]
 """
 ### Creating a dataset from a Python dictionary
+
+One can load data into Python using our %mddoclink(api,context.data_handler,Dataset) object.
 """
 
 # %%
@@ -203,7 +205,7 @@
 
 # %% [markdown]
 """
-The `Dataset` class organizes your data as a dictionary of splits (`str: datasets.Dataset`).
+The %mddoclink(api,context.data_handler,Dataset) class organizes your data as a dictionary of [datasets.Dataset](https://huggingface.co/docs/datasets/v2.1.0/en/package_reference/main_classes#datasets.Dataset).
 For example, after initialization, an `oos` key may be added if OOS samples are provided.
 In the case of the `banking77` dataset, only the `train` split is available, which you can access as shown below:
 """
@@ -215,7 +217,7 @@
 """
 ### Working with dataset splits
 
-Each split in the `Dataset` class is an instance of [datasets.Dataset](https://huggingface.co/docs/datasets/en/package_reference/main_classes#datasets.Dataset),
+Each split in the %mddoclink(api,context.data_handler,Dataset) class is an instance of [datasets.Dataset](https://huggingface.co/docs/datasets/en/package_reference/main_classes#datasets.Dataset),
 so you can work with them accordingly.
 """
 
@@ -230,7 +232,7 @@
 """
 
 # %%
-dataset.intents[0] # get intent (id=0)
+dataset.intents[0]  # get intent (id=0)
 
 # %% [markdown]
 """