
import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import pandas as pd

class TestTask(unittest.TestCase):
    def setUp(self):
        self.transactions = pd.DataFrame({
            "user_id": [1, 2, 1, 3, 2, 3, 4, 4, 1],
            "item_id": ["apple", "banana", "banana", "apple", "carrot", "carrot", "apple", "banana", "carrot"]
        })
        self.user_code = importlib.import_module("user_code")

    def test_returns_list_of_length_top_n(self):
        importlib.reload(self.user_code)
        result = self.user_code.customers_also_bought(self.transactions, "apple", top_n=2)
        _dynamic_test(
            self,
            isinstance(result, list) and len(result) == 2,
            "Returns a list of length equal to top_n.",
            f"Returned value is not a list of length 2: {result}"
        )

    def test_does_not_include_self(self):
        importlib.reload(self.user_code)
        result = self.user_code.customers_also_bought(self.transactions, "banana", top_n=2)
        _dynamic_test(
            self,
            "banana" not in result,
            "Does not include the provided item_id in recommendations.",
            f"Recommendations include the provided item_id: {result}"
        )

    def test_similarity_order(self):
        importlib.reload(self.user_code)
        # For 'banana', 'carrot' is most similar, then 'apple'
        result = self.user_code.customers_also_bought(self.transactions, "banana", top_n=2)
        expected_order = ["carrot", "apple"]
        _dynamic_test(
            self,
            result == expected_order,
            "Recommendations are based on highest cosine similarity.",
            f"Expected order {expected_order}, got {result}"
        )

    def test_multiple_occurrences(self):
        importlib.reload(self.user_code)
        # 'apple' appears multiple times; should still recommend correct items
        result = self.user_code.customers_also_bought(self.transactions, "apple", top_n=2)
        _dynamic_test(
            self,
            set(result) == {"banana", "carrot"},
            "Handles cases where the item appears multiple times.",
            f"Expected recommendations {{'banana', 'carrot'}}, got {result}"
        )

    def test_fewer_than_top_n(self):
        importlib.reload(self.user_code)
        # Only two items in this mini-dataset
        df = pd.DataFrame({"user_id": [1, 2, 1, 2], "item_id": ["x", "y", "y", "x"]})
        result = self.user_code.customers_also_bought(df, "x", top_n=5)
        _dynamic_test(
            self,
            isinstance(result, list) and len(result) == 1 and result[0] == "y",
            "Handles cases with fewer than top_n other items.",
            f"Expected ['y'], got {result}"
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()


test_main.py

Master the skills needed to design, implement, and scale modern recommendation engines and transactional association models. Go from analyzing raw retail checkouts using classic algorithmic principles like Apriori and FP-Growth to building advanced personalization systems via collaborative filtering and matrix factorization. Learn how to engineer data pipelines that power modern digital storefront discovery layers and drive user engagement metrics.

Discover how to find hidden relationships within massive transactional data structures. Learn the core mathematical frameworks retail giants use to optimize shelf placement, inventory structures, and product bundling strategies.

What is the main difference between user-based and item-based collaborative filtering?

**Which metric is best for measuring similarity between user rating vectors?**

How does item-based filtering improve scalability?

When would you use Pearson correlation over cosine similarity?

What is a neighborhood in collaborative filtering?

Take your algorithmic knowledge to the next level by handling heavy corporate transaction data without memory crashes. Master high-performance compressed trees and discover how to eliminate commercial noise from rule patterns.

Get hands-on experience building the recommendation engines that power modern digital platforms. Learn how to look past product groupings to map historical user behaviors, ratings, and shared consumer habits.

Dive into the mathematical fundamentals of advanced machine learning models for sparse datasets. Learn how to uncover latent features hidden inside multi-dimensional user feedback data to accurately predict missing interactions.

Challenge: Generating Customers Also Bought Recommendations

Solution