Merge branch 'master' into two_unique_numbers

Author: RamachandraBhardwaj

.github/workflows/build.yml

@@ -9,13 +9,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - run:
-          sudo apt-get update && sudo apt-get install -y libtiff5-dev libjpeg8-dev libopenjp2-7-dev
-          zlib1g-dev libfreetype6-dev liblcms2-dev libwebp-dev tcl8.6-dev tk8.6-dev python3-tk
-          libharfbuzz-dev libfribidi-dev libxcb1-dev
-          libxml2-dev libxslt-dev
-          libhdf5-dev
-          libopenblas-dev
+      - run: sudo apt-get update && sudo apt-get install -y libhdf5-dev
       - uses: actions/checkout@v5
       - uses: astral-sh/setup-uv@v7
         with:
@@ -32,6 +26,7 @@ jobs:
           --ignore=computer_vision/cnn_classification.py
           --ignore=docs/conf.py
           --ignore=dynamic_programming/k_means_clustering_tensorflow.py
+          --ignore=machine_learning/local_weighted_learning/local_weighted_learning.py
           --ignore=machine_learning/lstm/lstm_prediction.py
           --ignore=neural_network/input_data.py
           --ignore=project_euler/

CONTRIBUTING.md

@@ -99,7 +99,7 @@ We want your work to be readable by others; therefore, we encourage you to note
   ruff check
   ```
 
-- Original code submission require docstrings or comments to describe your work.
+- Original code submissions require docstrings or comments to describe your work.
 
 - More on docstrings and comments:
 

DIRECTORY.md

@@ -624,6 +624,7 @@
   * [Sequential Minimum Optimization](machine_learning/sequential_minimum_optimization.py)
   * [Similarity Search](machine_learning/similarity_search.py)
   * [Support Vector Machines](machine_learning/support_vector_machines.py)
+  * [T Stochastic Neighbour Embedding](machine_learning/t_stochastic_neighbour_embedding.py)
   * [Word Frequency Functions](machine_learning/word_frequency_functions.py)
   * [Xgboost Classifier](machine_learning/xgboost_classifier.py)
   * [Xgboost Regressor](machine_learning/xgboost_regressor.py)

data_structures/queues/circular_queue.py

@@ -17,7 +17,7 @@ def __len__(self) -> int:
         >>> len(cq)
         0
         >>> cq.enqueue("A")  # doctest: +ELLIPSIS
-        <data_structures.queues.circular_queue.CircularQueue object at ...
+        <data_structures.queues.circular_queue.CircularQueue object at ...>
         >>> cq.array
         ['A', None, None, None, None]
         >>> len(cq)
@@ -51,17 +51,24 @@ def enqueue(self, data):
         """
         This function inserts an element at the end of the queue using self.rear value
         as an index.
+
         >>> cq = CircularQueue(5)
         >>> cq.enqueue("A")  # doctest: +ELLIPSIS
-        <data_structures.queues.circular_queue.CircularQueue object at ...
+        <data_structures.queues.circular_queue.CircularQueue object at ...>
         >>> (cq.size, cq.first())
         (1, 'A')
         >>> cq.enqueue("B")  # doctest: +ELLIPSIS
-        <data_structures.queues.circular_queue.CircularQueue object at ...
+        <data_structures.queues.circular_queue.CircularQueue object at ...>
         >>> cq.array
         ['A', 'B', None, None, None]
         >>> (cq.size, cq.first())
         (2, 'A')
+        >>> cq.enqueue("C").enqueue("D").enqueue("E")  # doctest: +ELLIPSIS
+        <data_structures.queues.circular_queue.CircularQueue object at ...>
+        >>> cq.enqueue("F")
+        Traceback (most recent call last):
+           ...
+        Exception: QUEUE IS FULL
         """
         if self.size >= self.n:
             raise Exception("QUEUE IS FULL")
@@ -75,6 +82,7 @@ def dequeue(self):
         """
         This function removes an element from the queue using on self.front value as an
         index and returns it
+
         >>> cq = CircularQueue(5)
         >>> cq.dequeue()
         Traceback (most recent call last):

graphs/graph_adjacency_list.py

@@ -61,6 +61,15 @@ def add_vertex(self, vertex: T) -> None:
         """
         Adds a vertex to the graph. If the given vertex already exists,
         a ValueError will be thrown.
+
+        >>> g = GraphAdjacencyList(vertices=[], edges=[], directed=False)
+        >>> g.add_vertex("A")
+        >>> g.adj_list
+        {'A': []}
+        >>> g.add_vertex("A")
+        Traceback (most recent call last):
+        ...
+        ValueError: Incorrect input: A is already in the graph.
         """
         if self.contains_vertex(vertex):
             msg = f"Incorrect input: {vertex} is already in the graph."

machine_learning/apriori_algorithm.py

@@ -11,6 +11,7 @@
 Examples: https://www.kaggle.com/code/earthian/apriori-association-rules-mining
 """
 
+from collections import Counter
 from itertools import combinations
 
 
@@ -44,11 +45,16 @@ def prune(itemset: list, candidates: list, length: int) -> list:
     >>> prune(itemset, candidates, 3)
     []
     """
+    itemset_counter = Counter(tuple(item) for item in itemset)
     pruned = []
     for candidate in candidates:
         is_subsequence = True
         for item in candidate:
-            if item not in itemset or itemset.count(item) < length - 1:
+            item_tuple = tuple(item)
+            if (
+                item_tuple not in itemset_counter
+                or itemset_counter[item_tuple] < length - 1
+            ):
                 is_subsequence = False
                 break
         if is_subsequence:

machine_learning/decision_tree.py

@@ -146,14 +146,13 @@ def predict(self, x):
         """
         if self.prediction is not None:
             return self.prediction
-        elif self.left or self.right is not None:
+        elif self.left is not None and self.right is not None:
             if x >= self.decision_boundary:
                 return self.right.predict(x)
             else:
                 return self.left.predict(x)
         else:
-            print("Error: Decision tree not yet trained")
-            return None
+            raise ValueError("Decision tree not yet trained")
 
 
 class TestDecisionTree:
@@ -201,4 +200,4 @@ def main():
     main()
     import doctest
 
-    doctest.testmod(name="mean_squarred_error", verbose=True)
+    doctest.testmod(name="mean_squared_error", verbose=True)

maths/factorial.py

@@ -56,7 +56,7 @@ def factorial_recursive(n: int) -> int:
         raise ValueError("factorial() only accepts integral values")
     if n < 0:
         raise ValueError("factorial() not defined for negative values")
-    return 1 if n in {0, 1} else n * factorial(n - 1)
+    return 1 if n in {0, 1} else n * factorial_recursive(n - 1)
 
 
 if __name__ == "__main__":

maths/fibonacci.py

@@ -183,7 +183,7 @@ def fib_memoization(n: int) -> list[int]:
     """
     if n < 0:
         raise ValueError("n is negative")
-    # Cache must be outside recursuive function
+    # Cache must be outside recursive function
     # other it will reset every time it calls itself.
     cache: dict[int, int] = {0: 0, 1: 1, 2: 1}  # Prefilled cache
 

maths/monte_carlo.py

@@ -8,7 +8,7 @@
 from statistics import mean
 
 
-def pi_estimator(iterations: int):
+def pi_estimator(iterations: int) -> None:
     """
     An implementation of the Monte Carlo method used to find pi.
     1. Draw a 2x2 square centred at (0,0).