import unittest
import importlib
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
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 TestTitanicTransformations(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.user_code = importlib.import_module("user_code")
        cls.df = cls.user_code.transformed_data
        cls.original = sns.load_dataset("titanic")

    def test_missing_values_filled(self):
        """Check missing values in 'age' and 'embarked' were handled."""
        df = self.df
        cond = ("age" in df.columns) and not df["age"].isnull().any()
        _dynamic_test(
            self,
            cond,
            "Missing values in 'age' and 'embarked' successfully filled.",
            "Missing values still exist in 'age' or 'embarked'."
        )

    def test_get_dummies_applied(self):
        """Check that get_dummies() was used for 'sex' and 'embarked'."""
        df = self.df
        cond = any(col.startswith("sex_") for col in df.columns) and any(
            col.startswith("embarked_") for col in df.columns
        )
        _dynamic_test(
            self,
            cond,
            "Categorical columns 'sex' and 'embarked' successfully encoded using get_dummies().",
            "'sex' and 'embarked' were not properly one-hot encoded."
        )

    def test_standard_scaler(self):
        """Check scaling of 'age' and 'fare' with StandardScaler."""
        df = self.df
        cond = (
            abs(df["age_scaled"].mean()) < 1e-6 and
            abs(df["fare_scaled"].mean()) < 1e-6 and
            np.isclose(df["age_scaled"].std(), 1, atol=0.1) and
            np.isclose(df["fare_scaled"].std(), 1, atol=0.1)
        )
        _dynamic_test(
            self,
            cond,
            "'age' and 'fare' successfully standardized (mean≈0, std≈1).",
            "'age_scaled' or 'fare_scaled' not properly standardized."
        )

    def test_family_size(self):
        """Check that 'family_size' column exists and was correctly calculated."""
        df = self.df
        cond = "family_size" in df.columns and (
            df["family_size"] == df["sibsp"] + df["parch"] + 1
        ).all()
        _dynamic_test(
            self,
            cond,
            "'family_size' successfully created and computed.",
            "'family_size' missing or incorrectly computed."
        )

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

test_code.py

Covers essential techniques for preparing raw data for supervised learning. Focuses on handling missing values, encoding categorical features, scaling and transforming numerical data, and creating meaningful features that improve model performance and reliability.


Challenge: Transformation Grid

Solution