From 47b97ee187f8616172d9d5283cdc8ce6bdfcc5e1 Mon Sep 17 00:00:00 2001
From: Dani Bodor <d.bodor@esciencecenter.nl>
Date: Tue, 31 Oct 2023 16:00:02 +0100
Subject: [PATCH] add internal attributes of `QueryCollection` to its init and
 comment in docstring.

also fix docstring typos in process method
---
 deeprank2/query.py | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/deeprank2/query.py b/deeprank2/query.py
index 566a8f7b0..bcc089114 100644
--- a/deeprank2/query.py
+++ b/deeprank2/query.py
@@ -377,15 +377,29 @@ def _build_helper(self) -> Graph:
 
 
 class QueryCollection:
-    """Represents the collection of data queries.
+    """Represents the collection of data queries that will be processed.
 
+    The class attributes are set either while adding queries to the
+    collection (`_queries` and `_ids_count`), or when processing the collection
+    (`_cpu_count`, `_prefix`, and `_grid_settings`).
+
+    Attributes:
+        _queries (list[:class:`Query`]): The `Query` objects in the collection.
+        _ids_count (dict[str, int]): The original `query_id` and the repeat number for this id.
+            This is used to rename the `query_id` to ensure that there are no duplicate ids.
+        _prefix, _cpu_count, and _grid_settings: See docstring for `QueryCollection.process`.
+
+    Note:
         Queries can be saved as a dictionary to easily navigate through their data,
         using `QueryCollection.export_dict()`.
     """
 
     def __init__(self):
-        self._queries = []
-        self._ids_count = {}
+        self._queries: list[Query] = []
+        self._ids_count: dict[str, int] = {}
+        self._prefix: str | None = None
+        self._cpu_count: int | None = None
+        self._grid_settings: GridSettings | None = None
 
     def add(
         self,
@@ -475,8 +489,8 @@ def process( # pylint: disable=too-many-arguments, too-many-locals, dangerous-de
         """Render queries into graphs (and optionally grids).
 
         Args:
-            prefix (str None, optional): prefix for naming the output files. Defaults to "processed-queries".
-            feature_modules (list[ModuleType] | list[str] | Literal ['all'], optional): feature module or list of feature modules
+            prefix (str | None, optional): Prefix for naming the output files. Defaults to "processed-queries".
+            feature_modules (list[ModuleType] | list[str] | Literal ['all'], optional): Feature module or list of feature modules
                 used to generate features (given as string or as an imported module).
                 Each module must implement the :py:func:`add_features` function, and all feature modules must exist inside `deeprank2.features` folder.
                 If set to 'all', all available modules in `deeprank2.features` are used to generate the features.
@@ -485,7 +499,7 @@ def process( # pylint: disable=too-many-arguments, too-many-locals, dangerous-de
                 the number of CPUs available to the system.
                 Defaults to None, which takes all available cpu cores.
             combine_output (bool, optional):
-                if `True` (default): all processes are combined into a single HDF5 file.
+                If `True` (default): all processes are combined into a single HDF5 file.
                 If `False`: separate HDF5 files are created for each process (i.e. for each CPU used).
             grid_settings (:class:`GridSettings` | None, optional): If valid together with `grid_map_method`, the grid data will be stored as well.
                 Defaults to None.