Misc fixes across multiple algorithms (#6912)

Source: Snyk code quality
Add scikit-fuzzy to requirements

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Dhruv Manilawala <dhruvmanila@gmail.com>

compression/huffman.py

@@ -31,7 +31,7 @@ def parse_file(file_path: str) -> list[Letter]:
             c = f.read(1)
             if not c:
                 break
-            chars[c] = chars[c] + 1 if c in chars.keys() else 1
+            chars[c] = chars[c] + 1 if c in chars else 1
     return sorted((Letter(c, f) for c, f in chars.items()), key=lambda l: l.freq)
 
 

data_structures/linked_list/is_palindrome.py

@@ -55,7 +55,7 @@ def is_palindrome_dict(head):
     d = {}
     pos = 0
     while head:
-        if head.val in d.keys():
+        if head.val in d:
             d[head.val].append(pos)
         else:
             d[head.val] = [pos]

digital_image_processing/filters/local_binary_pattern.py

@@ -60,7 +60,7 @@ def local_binary_value(image: np.ndarray, x_coordinate: int, y_coordinate: int)
     )
 
 
-if __name__ == "main":
+if __name__ == "__main__":
 
     # Reading the image and converting it to grayscale.
     image = cv2.imread(

fuzzy_logic/fuzzy_operations.py

@@ -8,11 +8,7 @@ Python:
   - 3.5
 """
 import numpy as np
-
-try:
-    import skfuzzy as fuzz
-except ImportError:
-    fuzz = None
+import skfuzzy as fuzz
 
 if __name__ == "__main__":
     # Create universe of discourse in Python using linspace ()

graphs/dijkstra_algorithm.py

@@ -89,13 +89,13 @@ class Graph:
         #  Edge going from node u to v and v to u with weight w
         # u (w)-> v, v (w) -> u
         # Check if u already in graph
-        if u in self.adjList.keys():
+        if u in self.adjList:
             self.adjList[u].append((v, w))
         else:
             self.adjList[u] = [(v, w)]
 
         # Assuming undirected graph
-        if v in self.adjList.keys():
+        if v in self.adjList:
             self.adjList[v].append((u, w))
         else:
             self.adjList[v] = [(u, w)]

graphs/directed_and_undirected_(weighted)_graph.py

@@ -226,9 +226,6 @@ class DirectedGraph:
                                 break
                             else:
                                 return True
-                                # TODO:The following code is unreachable.
-                                anticipating_nodes.add(stack[len_stack_minus_one])
-                                len_stack_minus_one -= 1
                     if visited.count(node[1]) < 1:
                         stack.append(node[1])
                         visited.append(node[1])
@@ -454,10 +451,6 @@ class Graph:
                                 break
                             else:
                                 return True
-                                # TODO: the following code is unreachable
-                                # is this meant to be called in the else ?
-                                anticipating_nodes.add(stack[len_stack_minus_one])
-                                len_stack_minus_one -= 1
                     if visited.count(node[1]) < 1:
                         stack.append(node[1])
                         visited.append(node[1])

hashes/hamming_code.py

@@ -79,8 +79,7 @@ def emitter_converter(size_par, data):
     ['1', '1', '1', '1', '0', '1', '0', '0', '1', '0', '1', '1', '1', '1', '1', '1']
     """
     if size_par + len(data) <= 2**size_par - (len(data) - 1):
-        print("ERROR - size of parity don't match with size of data")
-        exit(0)
+        raise ValueError("size of parity don't match with size of data")
 
     data_out = []
     parity = []

linear_algebra/src/test_linear_algebra.py

@@ -89,7 +89,7 @@ class Test(unittest.TestCase):
         """
         test for global function zero_vector()
         """
-        self.assertTrue(str(zero_vector(10)).count("0") == 10)
+        self.assertEqual(str(zero_vector(10)).count("0"), 10)
 
     def test_unit_basis_vector(self) -> None:
         """

maths/extended_euclidean_algorithm.py

@@ -75,11 +75,12 @@ def main():
     """Call Extended Euclidean Algorithm."""
     if len(sys.argv) < 3:
         print("2 integer arguments required")
-        exit(1)
+        return 1
     a = int(sys.argv[1])
     b = int(sys.argv[2])
     print(extended_euclidean_algorithm(a, b))
+    return 0
 
 
 if __name__ == "__main__":
-    main()
+    raise SystemExit(main())

maths/jaccard_similarity.py

@@ -14,7 +14,7 @@ Jaccard similarity is widely used with MinHashing.
 """
 
 
-def jaccard_similariy(set_a, set_b, alternative_union=False):
+def jaccard_similarity(set_a, set_b, alternative_union=False):
     """
     Finds the jaccard similarity between two sets.
     Essentially, its intersection over union.
@@ -35,18 +35,18 @@ def jaccard_similariy(set_a, set_b, alternative_union=False):
     Examples:
     >>> set_a = {'a', 'b', 'c', 'd', 'e'}
     >>> set_b = {'c', 'd', 'e', 'f', 'h', 'i'}
-    >>> jaccard_similariy(set_a, set_b)
+    >>> jaccard_similarity(set_a, set_b)
     0.375
 
-    >>> jaccard_similariy(set_a, set_a)
+    >>> jaccard_similarity(set_a, set_a)
     1.0
 
-    >>> jaccard_similariy(set_a, set_a, True)
+    >>> jaccard_similarity(set_a, set_a, True)
     0.5
 
     >>> set_a = ['a', 'b', 'c', 'd', 'e']
     >>> set_b = ('c', 'd', 'e', 'f', 'h', 'i')
-    >>> jaccard_similariy(set_a, set_b)
+    >>> jaccard_similarity(set_a, set_b)
     0.375
     """
 
@@ -67,14 +67,15 @@ def jaccard_similariy(set_a, set_b, alternative_union=False):
 
         if alternative_union:
             union = len(set_a) + len(set_b)
+            return len(intersection) / union
         else:
             union = set_a + [element for element in set_b if element not in set_a]
+            return len(intersection) / len(union)
 
         return len(intersection) / len(union)
 
 
 if __name__ == "__main__":
-
     set_a = {"a", "b", "c", "d", "e"}
     set_b = {"c", "d", "e", "f", "h", "i"}
-    print(jaccard_similariy(set_a, set_b))
+    print(jaccard_similarity(set_a, set_b))

matrix/matrix_class.py

@@ -286,7 +286,7 @@ class Matrix:
     # MATRIX OPERATIONS
     def __eq__(self, other: object) -> bool:
         if not isinstance(other, Matrix):
-            raise TypeError("A Matrix can only be compared with another Matrix")
+            return NotImplemented
         return self.rows == other.rows
 
     def __ne__(self, other: object) -> bool:

project_euler/problem_001/sol7.py

@@ -26,9 +26,7 @@ def solution(n: int = 1000) -> int:
 
     result = 0
     for i in range(n):
-        if i % 3 == 0:
-            result += i
-        elif i % 5 == 0:
+        if i % 3 == 0 or i % 5 == 0:
             result += i
     return result
 

project_euler/problem_042/solution42.py

@@ -34,12 +34,11 @@ def solution():
         words = f.readline()
 
     words = [word.strip('"') for word in words.strip("\r\n").split(",")]
-    words = list(
-        filter(
-            lambda word: word in TRIANGULAR_NUMBERS,
-            (sum(ord(x) - 64 for x in word) for word in words),
-        )
-    )
+    words = [
+        word
+        for word in [sum(ord(x) - 64 for x in word) for word in words]
+        if word in TRIANGULAR_NUMBERS
+    ]
     return len(words)
 
 

project_euler/problem_067/sol1.py

@@ -28,8 +28,12 @@ def solution():
     with open(triangle) as f:
         triangle = f.readlines()
 
-    a = (x.rstrip("\r\n").split(" ") for x in triangle)
-    a = [list(map(int, x)) for x in a]
+    a = []
+    for line in triangle:
+        numbers_from_line = []
+        for number in line.strip().split(" "):
+            numbers_from_line.append(int(number))
+        a.append(numbers_from_line)
 
     for i in range(1, len(a)):
         for j in range(len(a[i])):

project_euler/problem_089/sol1.py

@@ -125,8 +125,9 @@ def solution(roman_numerals_filename: str = "/p089_roman.txt") -> int:
 
     savings = 0
 
-    file1 = open(os.path.dirname(__file__) + roman_numerals_filename)
-    lines = file1.readlines()
+    with open(os.path.dirname(__file__) + roman_numerals_filename) as file1:
+        lines = file1.readlines()
+
     for line in lines:
         original = line.strip()
         num = parse_roman_numerals(original)

requirements.txt

@@ -9,7 +9,7 @@ pandas
 pillow
 qiskit
 requests
-# scikit-fuzzy  # Causing broken builds
+scikit-fuzzy
 sklearn
 statsmodels
 sympy

scheduling/first_come_first_served.py

@@ -79,7 +79,7 @@ if __name__ == "__main__":
     # ensure that we actually have processes
     if len(processes) == 0:
         print("Zero amount of processes")
-        exit()
+        raise SystemExit(0)
 
     # duration time of all processes
     duration_times = [19, 8, 9]
@@ -87,7 +87,7 @@ if __name__ == "__main__":
     # ensure we can match each id to a duration time
     if len(duration_times) != len(processes):
         print("Unable to match all id's with their duration time")
-        exit()
+        raise SystemExit(0)
 
     # get the waiting times and the turnaround times
     waiting_times = calculate_waiting_times(duration_times)

scheduling/multi_level_feedback_queue.py

@@ -276,7 +276,7 @@ if __name__ == "__main__":
     queue = deque([P1, P2, P3, P4])
 
     if len(time_slices) != number_of_queues - 1:
-        exit()
+        raise SystemExit(0)
 
     doctest.testmod(extraglobs={"queue": deque([P1, P2, P3, P4])})
 

web_programming/emails_from_url.py

@@ -93,7 +93,7 @@ def emails_from_url(url: str = "https://github.com") -> list[str]:
             except ValueError:
                 pass
     except ValueError:
-        exit(-1)
+        raise SystemExit(1)
 
     # Finally return a sorted list of email addresses with no duplicates.
     return sorted(valid_emails)