In deze uitdaging gebruik je **polars** om efficiënt data-aggregatie uit te voeren op grote datasets. Je krijgt de opdracht om een grote DataFrame te groeperen op basis van één kolom en het gemiddelde van een andere kolom voor elke groep te berekenen. Dit is een veelvoorkomende bewerking in data-analyse, vooral bij het werken met big data, omdat het je in staat stelt om samenvattingen en inzichten uit deelverzamelingen van je data te halen zonder alles tegelijk in het geheugen te laden.

import unittest
import sys
import subprocess
import importlib
import ast
import re
import polars as pl

class TestTask(unittest.TestCase):
    def setUp(self):
        self.module = importlib.import_module("user_code")

    def test_returns_dataframe_with_one_row_per_group(self):
        df = pl.DataFrame({
            "group": ["X", "Y", "X", "Z", "Y", "Z", "X"],
            "score": [5, 10, 15, 20, 30, 40, 25]
        })
        result = self.module.groupby_mean(df, "group", "score")
        _dynamic_test(
            self,
            isinstance(result, pl.DataFrame),
            "Returned object is a polars DataFrame",
            f"Returned object is not a polars DataFrame: {type(result)}"
        )
        unique_groups = set(df["group"].to_list())
        _dynamic_test(
            self,
            result.height == len(unique_groups),
            "Returned DataFrame has one row per unique group value",
            f"Expected {len(unique_groups)} groups, got {result.height} rows"
        )

    def test_correct_mean_computation(self):
        df = pl.DataFrame({
            "team": ["A", "B", "A", "B", "A"],
            "points": [10, 20, 30, 40, 50]
        })
        result = self.module.groupby_mean(df, "team", "points")
        expected = {
            "A": (10 + 30 + 50) / 3,
            "B": (20 + 40) / 2
        }
        for row in result.iter_rows(named=True):
            group = row["team"]
            mean_val = row.get("mean_points")
            _dynamic_test(
                self,
                group in expected and abs(mean_val - expected[group]) < 1e-6,
                f"Mean for group {group} is correct",
                f"Expected mean {expected[group]} for group {group}, got {mean_val}"
            )

    def test_column_naming(self):
        df = pl.DataFrame({
            "cat": ["a", "b", "a"],
            "val": [1, 2, 3]
        })
        result = self.module.groupby_mean(df, "cat", "val")
        _dynamic_test(
            self,
            "mean_val" in result.columns,
            "Returned DataFrame column is named correctly as 'mean_val'",
            f"Returned DataFrame columns: {result.columns}"
        )

    def test_works_with_any_dataframe(self):
        df = pl.DataFrame({
            "city": ["NY", "LA", "NY", "SF"],
            "temp": [70, 80, 60, 65],
            "humidity": [30, 40, 50, 60]
        })
        # Test grouping by city, mean of temp
        result = self.module.groupby_mean(df, "city", "temp")
        expected = {
            "NY": (70 + 60) / 2,
            "LA": 80,
            "SF": 65
        }
        for row in result.iter_rows(named=True):
            group = row["city"]
            mean_val = row.get("mean_temp")
            _dynamic_test(
                self,
                group in expected and abs(mean_val - expected[group]) < 1e-6,
                f"Mean for city {group} is correct",
                f"Expected mean {expected[group]} for city {group}, got {mean_val}"
            )

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
    # Collect all assignment nodes to modify
    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 nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    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 praktische, hands-on cursus voor aspirant-data scientists die klaar zijn om echte uitdagingen met grote datasets aan te gaan. Leer efficiënt grote datasets verwerken, samplen en analyseren met Python en essentiële libraries. Elke sectie bevat boeiende video-uitleg en interactieve uitdagingen om je expertise op te bouwen.

Leer fundamentele strategieën voor het omgaan met datasets die te groot zijn om in het geheugen te passen, waaronder chunking- en streamingtechnieken.

Ontdek methoden om grote datasets te balanceren en te bemonsteren, waaronder oversampling en undersampling.

Leer hoe u de polars-bibliotheek gebruikt voor snelle, geheugen-efficiënte gegevensverwerking.

Uitdaging: Polars Data-aggregatie

Oplossing