In deze uitdaging oefen je met het omgaan met klasse-ongelijkheid in een grote dataset door **oversampling** toe te passen. Je krijgt een `pandas` DataFrame met een doeldkolom waarin de klassen ongelijk verdeeld zijn. Het doel is om een nieuwe DataFrame te maken waarin de minderheidsklasse wordt overbemonsterd, zodat beide klassen evenveel rijen bevatten. Deze techniek is nuttig in situaties waarin je wilt voorkomen dat modellen bevooroordeeld raken richting de meerderheidklasse.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import pandas as pd
import importlib

class TestTask(unittest.TestCase):
    def setUp(self):
        self.user_code = importlib.import_module("user_code")
        self.data = {
            "feature1": [1, 2, 3, 4, 5, 6],
            "feature2": [10, 20, 30, 40, 50, 60],
            "target": ["A", "A", "A", "B", "B", "B"]
        }
        self.df = pd.DataFrame(self.data).iloc[:-1]  # Remove one B

    def test_columns_preserved(self):
        importlib.reload(self.user_code)
        balanced_df = self.user_code.oversample_minority(self.df, "target")
        _dynamic_test(
            self,
            set(balanced_df.columns) == set(self.df.columns),
            "Returned DataFrame contains the same columns as input DataFrame.",
            f"Returned DataFrame columns {balanced_df.columns.tolist()} do not match input columns {self.df.columns.tolist()}"
        )

    def test_balanced_class_counts(self):
        importlib.reload(self.user_code)
        balanced_df = self.user_code.oversample_minority(self.df, "target")
        counts = balanced_df["target"].value_counts()
        _dynamic_test(
            self,
            len(set(counts.values)) == 1 and counts["A"] == counts["B"],
            "Each class in the target column is balanced (equal row counts).",
            f"Class counts are not balanced: {counts.to_dict()}"
        )

    def test_total_row_count(self):
        importlib.reload(self.user_code)
        majority_count = self.df["target"].value_counts().max()
        balanced_df = self.user_code.oversample_minority(self.df, "target")
        expected_total = 2 * majority_count
        _dynamic_test(
            self,
            balanced_df.shape[0] == expected_total,
            "Total number of rows is twice the original majority class count.",
            f"Expected {expected_total} rows, got {balanced_df.shape[0]}"
        )

    def test_no_column_alteration(self):
        importlib.reload(self.user_code)
        balanced_df = self.user_code.oversample_minority(self.df, "target")
        _dynamic_test(
            self,
            all(col in balanced_df.columns for col in self.df.columns) and all(col in self.df.columns for col in balanced_df.columns),
            "No columns were dropped or altered in the returned DataFrame.",
            f"Returned columns: {balanced_df.columns.tolist()}, original columns: {self.df.columns.tolist()}"
        )

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.

Challenge: Toepassen van Oversampling

Oplossing