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

class TestTask(unittest.TestCase):
    def setUp(self):
        # Updated to match the exact column names expected by your solution
        self.df = pl.DataFrame({
            "Name": ["Portal 2", "Counter-Strike", "Dota 2"],
            "Positive": [90, 80, 50],
            "Negative": [10, 20, 50]
        })

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

    def test_positive_ratio_values_correct(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "calculate_positive_ratio", None)
        result = func(self.df)
        
        # Expected ratios: 90/100 = 0.9, 80/100 = 0.8, 50/100 = 0.5
        expected = [0.9, 0.8, 0.5]
        if result is not None and "Positive Ratio" in result.columns:
            actual = result["Positive Ratio"].to_list()
            # Checking with tolerance for floating-point values
            is_correct = all(abs(a - b) < 1e-5 for a, b in zip(actual, expected))
            _dynamic_test(
                self,
                is_correct,
                "'Positive Ratio' column contains correct proportional values.",
                f"'Positive Ratio' values incorrect. Expected: {expected}, Got: {actual}"
            )
        else:
            _dynamic_test(self, False, "", "Result missing 'Positive Ratio' column.")

    def test_context_behavior_preserves_columns(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "calculate_positive_ratio", None)
        result = func(self.df)
        if result is not None:
            # Enforce that it used with_columns (keeps everything) rather than select (drops unmentioned columns)
            # Updated to match your expected input column names
            for col in ["Name", "Positive", "Negative"]:
                _dynamic_test(
                    self,
                    col in result.columns,
                    f"Context verification passed: Column '{col}' was preserved.",
                    f"Context verification failed: Column '{col}' is missing. Did you accidentally use .select() instead of .with_columns()?"
                )
        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__":
    # verbosity=2 ensures dynamic names are printed to standard output
    unittest.main(verbosity=2)

test_main.py

Un cours pratique de niveau intermédiaire destiné aux développeurs Python pour maîtriser la manipulation de données avec Polars, en utilisant des jeux de données réels issus de Steam. Approfondissement du paradigme en colonnes de Polars, de la sélection, de l’agrégation, des jointures, de la restructuration, ainsi que des opérations essentielles sur les chaînes de caractères, les dates et les données manquantes.

Explorez les principales différences entre Polars et les DataFrames traditionnels basés sur les lignes, en mettant l'accent sur les opérations en colonnes, la sélection et la logique conditionnelle à l'aide du jeu de données Steam games.

Acquérir une compréhension approfondie des capacités de groupement parallèle, d'agrégation, de jointure et de restructuration de Polars en utilisant les jeux de données Steam games et spy insights.

Explorez les éléments essentiels du nettoyage des données : normalisation du texte, analyse des dates et gestion robuste des valeurs manquantes dans Polars.

Challenge: Contextes Principaux Select vs With_Columns

Solution