import unittest
import user_code
import ast
import re   
import importlib
import csv
import polars as pl

class TestTask(unittest.TestCase):
    def setUp(self):
        # Build local mock dataframe using exact un-renamed file schemas
        self.df = pl.DataFrame({
            "Name": ["  cyberpunk 2077  ", "Terraria", "   portal 2 ", "half-life"],
            "Price": [59.99, 9.99, 19.99, 9.99]
        })

    def test_name_column_exists_and_unrenamed(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "clean_game_titles", None)
        _dynamic_test(
            self,
            callable(func),
            "clean_game_titles function exists and is callable.",
            "clean_game_titles function is missing or not callable."
        )
        result = func(self.df)
        _dynamic_test(
            self,
            result is not None and "Name" in result.columns,
            "Returned DataFrame successfully preserves the raw casing header 'Name'.",
            "Returned DataFrame is missing the required raw column 'Name'. Ensure column names are not altered."
        )

    def test_string_transformations_are_accurate(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "clean_game_titles", None)
        result = func(self.df)
        
        # Expected outputs: stripped of whitespace and fully converted to uppercase
        expected_names = ["CYBERPUNK 2077", "TERRARIA", "PORTAL 2", "HALF-LIFE"]
        
        if result is not None and "Name" in result.columns:
            actual_names = result["Name"].to_list()
            _dynamic_test(
                self,
                actual_names == expected_names,
                "String engine successfully stripped outer spacing and normalized text variables to uppercase.",
                f"String processing calculations failed. Expected: {expected_names}, Got: {actual_names}"
            )
        else:
            _dynamic_test(self, False, "", "Text cleaning evaluation halted due to missing schema definitions.")

    def test_other_columns_intact(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "clean_game_titles", None)
        result = func(self.df)
        if result is not None:
            _dynamic_test(
                self,
                "Price" in result.columns,
                "Context validation passed: Non-targeted metric columns like 'Price' remain safe.",
                "Context validation failed: Unrelated columns were dropped during string operations."
            )
        else:
            _dynamic_test(self, False, "", "Returned DataFrame is None.")

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
    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 not assign_nodes:
        return code

    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

Dive into the fundamentals of data wrangling with Polars, using real-world Steam game datasets. Learn Polars' columnar paradigm, selection, aggregation, joining, reshaping, and essential string, date, and missing data operations.

Explore the core differences between Polars and traditional row-based DataFrames, focusing on columnar operations, selection, and conditional logic using the Steam games dataset.

Gain a solid understanding of Polars' parallel group-by, aggregation, joining, and reshaping capabilities using the Steam games and spy insights datasets.

Explore the essentials of data cleaning: text normalization, date parsing, and robust handling of missing values in Polars.

Challenge: Text Cleaning

Solution