import unittest
import importlib
import pandas as pd
import seaborn as sns

def _dynamic_test(test_case, condition, success_msg, failure_msg):
    if condition:
        test_case._testMethodName = success_msg
        test_case.assertTrue(True, success_msg)
    else:
        test_case._testMethodName = failure_msg
        test_case.fail(failure_msg)

class TestTitanicCleaning(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        """Import user's solution and prepare reference data for testing."""
        cls.user_code = importlib.import_module("user_code")
        cls.cleaned = cls.user_code.cleaned_data

        # Load base dataset to compute IQR bounds for reference
        base = sns.load_dataset("titanic")
        base["age"].fillna(base["age"].mean(), inplace=True)
        base["embarked"].fillna(base["embarked"].mode()[0], inplace=True)
        base.drop_duplicates(inplace=True)

        Q1 = base["fare"].quantile(0.25)
        Q3 = base["fare"].quantile(0.75)
        IQR = Q3 - Q1
        cls.lower_bound = Q1 - 1.5 * IQR
        cls.upper_bound = Q3 + 1.5 * IQR

    def test_no_missing_values(self):
        """Ensure missing values in 'age' and 'embarked' are handled."""
        df = self.cleaned
        condition = (
            not df["age"].isnull().any() and
            not df["embarked"].isnull().any()
        )
        _dynamic_test(
            self,
            condition,
            "No missing values remain in 'age' or 'embarked'.",
            "Missing values still exist in 'age' or 'embarked'."
        )

    def test_no_duplicates(self):
        """Ensure duplicate rows are removed."""
        df = self.cleaned
        condition = len(df) == len(df.drop_duplicates())
        _dynamic_test(
            self,
            condition,
            "Duplicate rows successfully removed.",
            "Duplicate rows still exist in the dataset."
        )

    def test_outlier_removal(self):
        """Verify that outliers in 'fare' were filtered using IQR."""
        df = self.cleaned.copy()
        fares = df["fare"].dropna()
        eps = 1e-6
        within = fares.between(self.lower_bound - eps, self.upper_bound + eps)
        condition = within.all()
        _dynamic_test(
            self,
            condition,
            "Outliers in 'fare' handled correctly using IQR.",
            "Some extreme 'fare' values were not properly filtered."
        )

    def test_columns_exist(self):
        """Ensure required columns exist in the cleaned dataset."""
        required = {"age", "embarked", "fare"}
        df_cols = set(self.cleaned.columns)
        condition = required.issubset(df_cols)
        _dynamic_test(
            self,
            condition,
            "Cleaned dataset includes essential columns.",
            "One or more essential columns are missing in the cleaned dataset."
        )

if __name__ == "__main__":
    unittest.main(argv=["first-arg-is-ignored"], exit=False)


test_code.py

Leer praktische technieken om data te schonen, transformeren en te engineeren voor machine learning met Python. Deze cursus behandelt essentiële stappen in preprocessing, featurecreatie en praktijkgerichte uitdagingen om data voor modellering voor te bereiden.

Beheers de fundamentele stappen voor het opschonen en voorbereiden van ruwe gegevens voor analyse en machine learning.

Ruwe gegevens omzetten in bruikbare kenmerken voor machine learning-modellen.

Kenmerken ontwikkelen en selecteren om de modelprestaties en de interpreteerbaarheid te verbeteren.

Uitdaging: Gegevensopschoning

Oplossing

Awesome!

Uitdaging: Gegevensopschoning

Oplossing