From 77312535e643e4c8fecd7c20b3381996808dea11 Mon Sep 17 00:00:00 2001
From: Muriithi Frederick Muriuki
Date: Thu, 29 Jul 2021 14:09:49 +0300
Subject: Add partial type annotations for slink module

Issue:
https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi

* Add some type annotations for the `nearest` function.
* Leave some comments regarding the issues experienced when trying to add some
  typing annotations to the function to help with future endeavours of the
  same.
---
 gn3/computations/slink.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'gn3/computations/slink.py')

diff --git a/gn3/computations/slink.py b/gn3/computations/slink.py
index 4aac6b3..23d3d88 100644
--- a/gn3/computations/slink.py
+++ b/gn3/computations/slink.py
@@ -7,6 +7,10 @@ slink:
     TODO: Describe what the function does...
 """
 import logging
+from typing import List, Tuple, Union, Sequence
+
+NumType = Union[int, float]
+SeqOfNums = Sequence[NumType]
 
 class LengthError(BaseException):
     """Raised whenever child lists/tuples are not the same length as the parent
@@ -73,7 +77,10 @@ raise an exception."""
 def __flatten_list_of_lists(parent):
     return [item for child in parent for item in child]
 
-def nearest(lists, i, j):
+# i and j are Union[SeqOfNums, NumType], but that leads to errors where the
+# values of i or j are indexed, since the NumType type is not indexable.
+# I don't know how to type this so that it does not fail on running `mypy .`
+def nearest(lists: Sequence[SeqOfNums], i, j) -> NumType:
     """
     Computes shortest distance between member(s) in `i` and member(s) in `j`.
 
@@ -126,6 +133,10 @@ def nearest(lists, i, j):
 
     raise ValueError("member values (i or j) should be lists/tuples of integers or integers")
 
+# `lists` here could be Sequence[SeqOfNums], but that leads to errors I do not
+# understand down the line
+# Might have to re-implement the function especially since the errors are thrown
+# where `listindexcopy` is involved
 def slink(lists):
     """
     DESCRIPTION:
-- 
cgit v1.2.3


From f712da630c1a3642cb44b62c4b2b857373cd78d7 Mon Sep 17 00:00:00 2001
From: Muriithi Frederick Muriuki
Date: Wed, 4 Aug 2021 11:30:44 +0300
Subject: Fix issues caught by pylint

* gn3/computations/slink.py: remove unused imports
* gn3/db/traits.py: remove unnecessary `else` clauses
* tests/unit/db/test_traits.py: add docstrings for functions
---
 gn3/computations/slink.py    | 2 +-
 gn3/db/traits.py             | 6 +++---
 tests/unit/db/test_traits.py | 3 +++
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'gn3/computations/slink.py')

diff --git a/gn3/computations/slink.py b/gn3/computations/slink.py
index 23d3d88..5953e6b 100644
--- a/gn3/computations/slink.py
+++ b/gn3/computations/slink.py
@@ -7,7 +7,7 @@ slink:
     TODO: Describe what the function does...
 """
 import logging
-from typing import List, Tuple, Union, Sequence
+from typing import Union, Sequence
 
 NumType = Union[int, float]
 SeqOfNums = Sequence[NumType]
diff --git a/gn3/db/traits.py b/gn3/db/traits.py
index ea35d7e..29c91a6 100644
--- a/gn3/db/traits.py
+++ b/gn3/db/traits.py
@@ -166,8 +166,7 @@ def set_confidential_field(trait_info):
             "confidential": 1 if (
                 trait_info.get("pre_publication_description", None)
                 and not trait_info.get("pubmed_id", None)) else 0}
-    else:
-        return trait_info
+    return trait_info
 
 def retrieve_probeset_trait_info(trait_data_source: Dict[str, Any], conn: Any):
     """Retrieve trait information for type `ProbeSet` traits.
@@ -344,13 +343,14 @@ def set_riset_fields(trait_info, conn):
 
 def retrieve_trait_info(
         trait_type: str, trait_name: str, trait_dataset_id: int,
-        trait_dataset_name: str, conn: Any, QTL=None):
+        trait_dataset_name: str, conn: Any, qtl=None):
     """Retrieves the trait information.
 
     https://github.com/genenetwork/genenetwork1/blob/master/web/webqtl/base/webqtlTrait.py#L397-L456
 
     This function, or the dependent functions, might be incomplete as they are
     currently."""
+    # pylint: disable=[R0913]
     trait_info_function_table = {
         "Publish": retrieve_publish_trait_info,
         "ProbeSet": retrieve_probeset_trait_info,
diff --git a/tests/unit/db/test_traits.py b/tests/unit/db/test_traits.py
index 2445d26..1c481a2 100644
--- a/tests/unit/db/test_traits.py
+++ b/tests/unit/db/test_traits.py
@@ -207,6 +207,7 @@ class TestTraitsDBFunctions(TestCase):
             )
 
     def test_set_haveinfo_field(self):
+        """Test that the `haveinfo` field is set up correctly"""
         for trait_info, expected in [
                 [{}, {"haveinfo": 0}],
                 [{"k1": "v1"}, {"k1": "v1", "haveinfo": 1}]]:
@@ -214,6 +215,7 @@ class TestTraitsDBFunctions(TestCase):
                 self.assertEqual(set_haveinfo_field(trait_info), expected)
 
     def test_set_homologene_id_field(self):
+        """Test that the `homologene_id` field is set up correctly"""
         for trait_info, expected in [
                 [{"type": "Publish"},
                  {"type": "Publish", "homologeneid": None}],
@@ -229,6 +231,7 @@ class TestTraitsDBFunctions(TestCase):
                         set_homologene_id_field(trait_info, db_mock), expected)
 
     def test_set_confidential_field(self):
+        """Test that the `confidential` field is set up correctly"""
         for trait_info, expected in [
                 [{"type": "Publish"}, {"type": "Publish", "confidential": 0}],
                 [{"type": "ProbeSet"}, {"type": "ProbeSet"}],
-- 
cgit v1.2.3