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

class TestTask(unittest.TestCase):
    def setUp(self):
        # Initializing local mock dataset using exact un-renamed raw file schemas
        # FIX: Changed pl.F64 to pl.Float64 to match proper Polars type syntax
        self.df = pl.DataFrame({
            "Name": ["Half-Life 2", "Unreleased Indie Game", "Portal", "Free Beta Test"],
            "Price": [9.99, None, 19.99, None]  # None acts as Null in Polars constructors
        }, schema={"Name": pl.String, "Price": pl.Float64})

    def test_price_column_exists_and_unnamed(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "handle_missing_prices", None)
        _dynamic_test(
            self,
            callable(func),
            "handle_missing_prices function exists and is callable.",
            "handle_missing_prices function is missing or not callable."
        )
        result = func(self.df)
        _dynamic_test(
            self,
            result is not None and "Price" in result.columns,
            "Returned DataFrame retains original raw column name 'Price'.",
            "Returned DataFrame is missing the required raw column 'Price'. Did you accidentally rename it?"
        )

    def test_null_values_filled_correctly(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "handle_missing_prices", None)
        result = func(self.df)
        
        # Expected outputs: None values should map to 0.0, actual numbers must remain unaltered
        expected_prices = [9.99, 0.0, 19.99, 0.0]
        
        if result is not None and "Price" in result.columns:
            actual_prices = result["Price"].to_list()
            _dynamic_test(
                self,
                actual_prices == expected_prices,
                "Null values successfully targeted and replaced with fallback float values.",
                f"Null replacement logic failed. Expected: {expected_prices}, Got: {actual_prices}"
            )
        else:
            _dynamic_test(self, False, "", "Sanitation evaluation halted due to column tracking schema faults.")

    def test_other_attributes_preserved(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "handle_missing_prices", None)
        result = func(self.df)
        if result is not None:
            _dynamic_test(
                self,
                "Name" in result.columns,
                "Context validation passed: Text identifier column 'Name' remains unchanged.",
                "Context validation failed: Primary data structural columns were altered or dropped."
            )
        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

Een praktijkgerichte, intermediaire cursus voor Python-ontwikkelaars om data wrangling te beheersen met Polars, aan de hand van echte Steam-gamegegevenssets. Leer het kolomgebaseerde paradigma van Polars, selectie, aggregatie, joinen, herschikken en essentiële bewerkingen op strings, datums en ontbrekende gegevens.

Ontdek de belangrijkste verschillen tussen Polars en traditionele rij-gebaseerde DataFrames, met de nadruk op kolomgebaseerde bewerkingen, selectie en conditionele logica met behulp van de Steam-gamesdataset.

Krijg een grondig begrip van de parallelle group-by-, aggregatie-, join- en herstructureringsmogelijkheden van Polars met behulp van de Steam-games- en spy insights-datasets.

Verken de basisprincipes van data cleaning: tekstnormalisatie, datumparsing en robuuste verwerking van ontbrekende waarden in Polars.

Uitdaging: Omgaan met Nullen

Oplossing