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

class TestTask(unittest.TestCase):
    def setUp(self):
        # Mock dataset designed to test boundaries: Free, Budget (exact 10.0), Premium, and invalid Positive values
        self.df = pl.DataFrame({
            "Name": ["Freebie", "Cheap Game", "Exact Ten", "Expensive", "No Reviews", "Negative Reviews"],
            "Price": [0.0, 4.99, 10.0, 14.99, 0.0, 5.0],
            "Positive": [100, 50, 25, 200, 0, -5]
        })

    def test_function_and_columns_exist(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "filter_and_tier_games", None)
        
        _dynamic_test(
            self,
            callable(func),
            "filter_and_tier_games function exists and is callable.",
            "filter_and_tier_games function is missing or not callable."
        )
        
        result = func(self.df)
        _dynamic_test(
            self,
            result is not None and "Price Tier" in result.columns,
            "Returned DataFrame contains 'Price Tier' column.",
            "Returned DataFrame is missing 'Price Tier' column."
        )

    def test_filtering_logic_correct(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "filter_and_tier_games", None)
        result = func(self.df)
        
        # 'No Reviews' (0) and 'Negative Reviews' (-5) should be filtered out
        expected_names = ["Freebie", "Cheap Game", "Exact Ten", "Expensive"]
        
        if result is not None:
            actual_names = result["Name"].to_list()
            _dynamic_test(
                self,
                actual_names == expected_names,
                "Filtering logic correctly retains only games with Positive > 0.",
                f"Filtering logic failed. Expected games: {expected_names}, Got: {actual_names}"
            )
        else:
            _dynamic_test(self, False, "", "Returned DataFrame is None.")

    def test_price_tier_values_correct(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "filter_and_tier_games", None)
        result = func(self.df)
        
        # Expected tiers corresponding to the filtered games
        expected_tiers = ["Free", "Budget", "Budget", "Premium"]
        
        if result is not None and "Price Tier" in result.columns:
            actual_tiers = result["Price Tier"].to_list()
            _dynamic_test(
                self,
                actual_tiers == expected_tiers,
                "'Price Tier' column contains correct classifications (Free, Budget, Premium).",
                f"'Price Tier' values incorrect. Expected: {expected_tiers}, Got: {actual_tiers}"
            )
        else:
            _dynamic_test(self, False, "", "Result missing 'Price Tier' column.")

    def test_original_columns_preserved(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "filter_and_tier_games", None)
        result = func(self.df)
        
        if result is not None:
            for col in ["Name", "Price", "Positive"]:
                _dynamic_test(
                    self,
                    col in result.columns,
                    f"Context verification passed: Column '{col}' was preserved.",
                    f"Context verification failed: Column '{col}' is missing."
                )
        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(verbosity=2)

test_main.py

Ein praxisorientierter, mittlerer Kurs für Python-Entwickler zur Beherrschung des Data Wrangling mit Polars anhand von realen Steam-Spieldatensätzen. Vermittelt wird das spaltenorientierte Paradigma von Polars, Selektion, Aggregation, Verknüpfung, Umformung sowie grundlegende Operationen mit Zeichenketten, Datumswerten und fehlenden Daten.

Untersuchung der grundlegenden Unterschiede zwischen Polars und traditionellen zeilenbasierten DataFrames mit Schwerpunkt auf spaltenbasierten Operationen, Selektion und bedingter Logik anhand des Steam-Games-Datensatzes.

Erwerben Sie ein fundiertes Verständnis der parallelen Group-by-, Aggregations-, Join- und Umformungsfunktionen von Polars anhand der Steam-Spiele- und Spy-Insights-Datensätze.

Erkunden Sie die Grundlagen der Datenbereinigung: Textnormalisierung, Datumsanalyse und robuste Behandlung fehlender Werte in Polars.

Herausforderung: Filtern & Bedingte Logik

Lösung