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

class TestTask(unittest.TestCase):
    def setUp(self):
        self.data = {
            'apple': [1, 0, 1, 0],
            'banana': [1, 1, 0, 0],
            'carrot': [0, 1, 1, 0],
            'donut': [0, 0, 1, 1],
        }
        self.user_item_matrix = pd.DataFrame(self.data, index=['alice', 'bob', 'carol', 'dave'])
        self.module_name = 'user_code'

    def test_returns_list(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.recommend_products(self.user_item_matrix, 'bob', top_n=2)
        _dynamic_test(self, isinstance(result, list), "Function returns a list.", f"Expected list, got {type(result)}.")

    def test_recommendations_are_valid(self):
        import user_code
        importlib.reload(user_code)
        # Bob's vector: [0,1,1,0], most similar is Alice: [1,1,0,0]
        # Alice has apple (1), bob does not (0)
        result = user_code.recommend_products(self.user_item_matrix, 'bob', top_n=2)
        expected = ['apple']
        _dynamic_test(
            self,
            all(item in ['apple'] for item in result),
            "Recommendation is valid and contains only items the similar user has and target does not.",
            f"Recommendation contains unexpected items: {result}"
        )

    def test_top_n_limit(self):
        import user_code
        importlib.reload(user_code)
        # carol: [1,0,1,1], most similar user is alice: [1,1,0,0]
        # Alice has banana (1), carol does not (0)
        result = user_code.recommend_products(self.user_item_matrix, 'carol', top_n=1)
        _dynamic_test(
            self,
            isinstance(result, list) and len(result) <= 1 and (len(result) == 0 or result[0] == 'banana'),
            "Function respects top_n and returns correct recommendation for carol.",
            f"Expected ['banana'] or [], got {result}"
        )

    def test_no_similar_user(self):
        import user_code
        importlib.reload(user_code)
        # Add a new user with all zeros
        df = self.user_item_matrix.copy()
        df.loc['eve'] = [0, 0, 0, 0]
        result = user_code.recommend_products(df, 'eve', top_n=2)
        _dynamic_test(self, result == [], "Returns empty list if no similar user.", f"Expected [], got {result}")

    def test_no_new_items_to_recommend(self):
        import user_code
        importlib.reload(user_code)
        # Bob and dave: dave has only donut, bob has not. But similarity is zero with everyone except alice.
        # Add a user who has all the same items as alice
        df = self.user_item_matrix.copy()
        df.loc['erin'] = [1, 1, 0, 0]
        result = user_code.recommend_products(df, 'erin', top_n=2)
        _dynamic_test(
            self,
            result == [],
            "Returns empty list if most similar user has no new items to recommend.",
            f"Expected [], got {result}"
        )

    def test_handles_different_top_n(self):
        import user_code
        importlib.reload(user_code)
        # alice: [1,1,0,0], most similar user is bob: [0,1,1,0]
        # bob has carrot (1), alice does not (0)
        result = user_code.recommend_products(self.user_item_matrix, 'alice', top_n=5)
        _dynamic_test(
            self,
            result == ['carrot'],
            "Function returns all possible recommendations if top_n > available.",
            f"Expected ['carrot'], 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: Building a User-Based Collaborative Filtering Component

Solution