[mypy] fix small folders 2 (#4293)

* Update perceptron.py

* Update binary_tree_traversals.py

* fix machine_learning

* Update build.yml

* Update perceptron.py

* Update machine_learning/forecasting/run.py

Co-authored-by: Christian Clauss <[email protected]>

Author: algobytewise

Diff for: .github/workflows/build.yml

@@ -38,10 +38,13 @@ jobs:
            genetic_algorithm
            geodesy
            knapsack
+           machine_learning
            networking_flow
+           neural_network
            quantum
            scheduling
            sorts
+           traversals
       - name: Run tests
         run: pytest --doctest-modules --ignore=project_euler/ --ignore=scripts/ --cov-report=term-missing:skip-covered --cov=. .
       - if: ${{ success() }}

Diff for: machine_learning/forecasting/run.py

@@ -29,8 +29,7 @@ def linear_regression_prediction(
     >>> abs(n - 5.0) < 1e-6  # Checking precision because of floating point errors
     True
     """
-    x = [[1, item, train_mtch[i]] for i, item in enumerate(train_dt)]
-    x = np.array(x)
+    x = np.array([[1, item, train_mtch[i]] for i, item in enumerate(train_dt)])
     y = np.array(train_usr)
     beta = np.dot(np.dot(np.linalg.inv(np.dot(x.transpose(), x)), x.transpose()), y)
     return abs(beta[0] + test_dt[0] * beta[1] + test_mtch[0] + beta[2])

Diff for: machine_learning/k_means_clust.py

@@ -200,7 +200,7 @@ def kmeans(
 
 
 def ReportGenerator(
-    df: pd.DataFrame, ClusteringVariables: np.array, FillMissingReport=None
+    df: pd.DataFrame, ClusteringVariables: np.ndarray, FillMissingReport=None
 ) -> pd.DataFrame:
     """
     Function generates easy-erading clustering report. It takes 2 arguments as an input:

Diff for: machine_learning/word_frequency_functions.py

@@ -61,7 +61,7 @@ def term_frequency(term: str, document: str) -> int:
     return len([word for word in tokenize_document if word.lower() == term.lower()])
 
 
-def document_frequency(term: str, corpus: str) -> int:
+def document_frequency(term: str, corpus: str) -> tuple[int, int]:
     """
     Calculate the number of documents in a corpus that contain a
     given term

Diff for: neural_network/perceptron.py

@@ -11,7 +11,14 @@
 
 
 class Perceptron:
-    def __init__(self, sample, target, learning_rate=0.01, epoch_number=1000, bias=-1):
+    def __init__(
+        self,
+        sample: list[list[float]],
+        target: list[int],
+        learning_rate: float = 0.01,
+        epoch_number: int = 1000,
+        bias: float = -1,
+    ) -> None:
         """
         Initializes a Perceptron network for oil analysis
         :param sample: sample dataset of 3 parameters with shape [30,3]
@@ -46,7 +53,7 @@ def __init__(self, sample, target, learning_rate=0.01, epoch_number=1000, bias=-
         self.bias = bias
         self.number_sample = len(sample)
         self.col_sample = len(sample[0])  # number of columns in dataset
-        self.weight = []
+        self.weight: list = []
 
     def training(self) -> None:
         """
@@ -94,7 +101,7 @@ def training(self) -> None:
                 # if epoch_count > self.epoch_number or not error:
                 break
 
-    def sort(self, sample) -> None:
+    def sort(self, sample: list[float]) -> None:
         """
         :param sample: example row to classify as P1 or P2
         :return: None
@@ -221,11 +228,11 @@ def sign(self, u: float) -> int:
     print("Finished training perceptron")
     print("Enter values to predict or q to exit")
     while True:
-        sample = []
+        sample: list = []
         for i in range(len(samples[0])):
-            observation = input("value: ").strip()
-            if observation == "q":
+            user_input = input("value: ").strip()
+            if user_input == "q":
                 break
-            observation = float(observation)
+            observation = float(user_input)
             sample.insert(i, observation)
         network.sort(sample)

Diff for: traversals/binary_tree_traversals.py

@@ -188,7 +188,7 @@ def pre_order_iter(node: TreeNode) -> None:
     """
     if not isinstance(node, TreeNode) or not node:
         return
-    stack: List[TreeNode] = []
+    stack: list[TreeNode] = []
     n = node
     while n or stack:
         while n:  # start from root node, find its left child
@@ -218,7 +218,7 @@ def in_order_iter(node: TreeNode) -> None:
     """
     if not isinstance(node, TreeNode) or not node:
         return
-    stack: List[TreeNode] = []
+    stack: list[TreeNode] = []
     n = node
     while n or stack:
         while n: