From ee778128bdf8d4d6d386cfdc500f3b3173f56c06 Mon Sep 17 00:00:00 2001
From: Maxim Smolskiy <mithridatus@mail.ru>
Date: Thu, 2 Mar 2023 07:57:07 +0300
Subject: [PATCH] Reduce the complexity of other/scoring_algorithm.py (#8045)

* Increase the --max-complexity threshold in the file .flake8
---
 other/scoring_algorithm.py | 57 ++++++++++++++++++++++++++++----------
 1 file changed, 43 insertions(+), 14 deletions(-)

diff --git a/other/scoring_algorithm.py b/other/scoring_algorithm.py
index 00d87cfc0..8e04a8f30 100644
--- a/other/scoring_algorithm.py
+++ b/other/scoring_algorithm.py
@@ -23,29 +23,29 @@ Thus the weights for each column are as follows:
 """
 
 
-def procentual_proximity(
-    source_data: list[list[float]], weights: list[int]
-) -> list[list[float]]:
+def get_data(source_data: list[list[float]]) -> list[list[float]]:
     """
-    weights - int list
-    possible values - 0 / 1
-    0 if lower values have higher weight in the data set
-    1 if higher values have higher weight in the data set
-
-    >>> procentual_proximity([[20, 60, 2012],[23, 90, 2015],[22, 50, 2011]], [0, 0, 1])
-    [[20, 60, 2012, 2.0], [23, 90, 2015, 1.0], [22, 50, 2011, 1.3333333333333335]]
+    >>> get_data([[20, 60, 2012],[23, 90, 2015],[22, 50, 2011]])
+    [[20.0, 23.0, 22.0], [60.0, 90.0, 50.0], [2012.0, 2015.0, 2011.0]]
     """
-
-    # getting data
     data_lists: list[list[float]] = []
     for data in source_data:
         for i, el in enumerate(data):
             if len(data_lists) < i + 1:
                 data_lists.append([])
             data_lists[i].append(float(el))
+    return data_lists
 
+
+def calculate_each_score(
+    data_lists: list[list[float]], weights: list[int]
+) -> list[list[float]]:
+    """
+    >>> calculate_each_score([[20, 23, 22], [60, 90, 50], [2012, 2015, 2011]],
+    ...                      [0, 0, 1])
+    [[1.0, 0.0, 0.33333333333333337], [0.75, 0.0, 1.0], [0.25, 1.0, 0.0]]
+    """
     score_lists: list[list[float]] = []
-    # calculating each score
     for dlist, weight in zip(data_lists, weights):
         mind = min(dlist)
         maxd = max(dlist)
@@ -72,14 +72,43 @@ def procentual_proximity(
 
         score_lists.append(score)
 
+    return score_lists
+
+
+def generate_final_scores(score_lists: list[list[float]]) -> list[float]:
+    """
+    >>> generate_final_scores([[1.0, 0.0, 0.33333333333333337],
+    ...                        [0.75, 0.0, 1.0],
+    ...                        [0.25, 1.0, 0.0]])
+    [2.0, 1.0, 1.3333333333333335]
+    """
     # initialize final scores
     final_scores: list[float] = [0 for i in range(len(score_lists[0]))]
 
-    # generate final scores
     for slist in score_lists:
         for j, ele in enumerate(slist):
             final_scores[j] = final_scores[j] + ele
 
+    return final_scores
+
+
+def procentual_proximity(
+    source_data: list[list[float]], weights: list[int]
+) -> list[list[float]]:
+    """
+    weights - int list
+    possible values - 0 / 1
+    0 if lower values have higher weight in the data set
+    1 if higher values have higher weight in the data set
+
+    >>> procentual_proximity([[20, 60, 2012],[23, 90, 2015],[22, 50, 2011]], [0, 0, 1])
+    [[20, 60, 2012, 2.0], [23, 90, 2015, 1.0], [22, 50, 2011, 1.3333333333333335]]
+    """
+
+    data_lists = get_data(source_data)
+    score_lists = calculate_each_score(data_lists, weights)
+    final_scores = generate_final_scores(score_lists)
+
     # append scores to source data
     for i, ele in enumerate(final_scores):
         source_data[i].append(ele)