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

class TestTask(unittest.TestCase):
    def setUp(self):
        # Setup mock primary dataframe matching raw specifications
        self.df = pl.DataFrame({
            "Name": ["Portal", "Half-Life", "Left 4 Dead"],
            "Price": [9.99, 9.99, 19.99]
        })
        
        # Setup mock insights dataframe using string keys
        self.insights_df = pl.DataFrame({
            "Name": ["Portal", "Left 4 Dead", "Dota 2"], # Half-Life is missing, Dota 2 is unmapped
            "Marketing_Tier": ["Gold", "Silver", "Bronze"],
            "Ad_Budget": [5000, 2000, 1500]
        })

    def test_join_columns_exist_and_unaltered(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "merge_marketing_by_name", None)
        _dynamic_test(
            self,
            callable(func),
            "merge_marketing_by_name function exists and is callable.",
            "merge_marketing_by_name function is missing or not callable."
        )
        result = func(self.df, self.insights_df)
        
        _dynamic_test(
            self,
            result is not None and "Name" in result.columns,
            "Returned DataFrame retains original key tracking column 'Name'.",
            "Returned DataFrame is missing 'Name'. Ensure exact casing is used."
        )
        for col in ["Price", "Marketing_Tier", "Ad_Budget"]:
            _dynamic_test(
                self,
                col in result.columns,
                f"Merged column layout includes variable '{col}'.",
                f"Missing expected attribute column '{col}' after running the join."
            )

    def test_left_join_logic_and_null_fill(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, "merge_marketing_by_name", None)
        result = func(self.df, self.insights_df)
        
        if result is not None and "Marketing_Tier" in result.columns:
            _dynamic_test(
                self,
                len(result) == 3,
                "Left join operation successfully maintained primary dataset row lengths.",
                f"Row counts altered. Expected 3 rows, but received {len(result)} rows."
            )
            
            # Aligned key evaluation (Name: "Portal")
            portal_row = result.filter(pl.col("Name") == "Portal")
            _dynamic_test(
                self,
                portal_row["Marketing_Tier"][0] == "Gold",
                "Successfully matched and merged attributes using string keys.",
                f"Incorrect tier mapping for Portal. Expected 'Gold', Got: {portal_row['Marketing_Tier'][0]}"
            )
            
            # Unaligned key verification (Name: "Half-Life" -> missing from right table)
            halflife_row = result.filter(pl.col("Name") == "Half-Life")
            _dynamic_test(
                self,
                halflife_row["Marketing_Tier"][0] is None and halflife_row["Ad_Budget"][0] is None,
                "Left join rules validated: missing right values successfully defaulted to Null.",
                f"Error on missing key values. Expected Null assignments, Got: {halflife_row['Marketing_Tier'][0]}"
            )
        else:
            _dynamic_test(self, False, "", "Join verification halted due to schema structural sorting errors.")

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: Gegevens Samenvoegen

Oplossing