In dieser Aufgabe erhalten Sie den altbekannten Housing-Datensatz, diesmal jedoch nur mit dem Merkmal `'age'`.

import pandas as pd

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b22d1166-efda-45e8-979e-6c3ecfc566fc/houses_poly.csv')
print(df.head())

Als Nächstes erstellen wir ein Streudiagramm für diese Daten:

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b22d1166-efda-45e8-979e-6c3ecfc566fc/houses_poly.csv')
X = df['age']
y = df['price']
plt.scatter(X, y, alpha=0.4)
plt.show()

Eine Gerade passt hier schlecht: Die Preise steigen sowohl für sehr neue als auch für sehr alte Häuser. Eine Parabel bildet diesen Trend besser ab – genau das werden Sie in dieser Aufgabe erstellen.

import unittest
import numpy as np
import pandas as pd
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression


# Codefinity helper for dynamic names
def _dynamic_test(test_case, condition, ok_msg, fail_msg):
    if condition:
        test_case._testMethodName = ok_msg
        test_case.assertTrue(True)
    else:
        test_case._testMethodName = fail_msg
        test_case.fail(fail_msg)


class TestUserCode(unittest.TestCase):

    # 1. X contains only "age"
    def test_X_contains_age(self):
        import user_code

        cond = False
        try:
            X = user_code.X
            cond = isinstance(X, pd.DataFrame) and list(X.columns) == ["age"]
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X is correctly assigned from the 'age' column.",
            "Expected X = df[['age']]."
        )

    # 2. PolynomialFeatures used correctly
    def test_X_poly_preprocessing(self):
        import user_code

        cond = False
        try:
            X = user_code.X
            n = user_code.n
            X_poly = user_code.X_poly

            # Re-create expected transformation
            poly = PolynomialFeatures(n)
            expected = poly.fit_transform(X)

            cond = (
                isinstance(X_poly, np.ndarray)
                and X_poly.shape == expected.shape
                and np.allclose(X_poly, expected)
            )
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X_poly is correctly generated using PolynomialFeatures.",
            "Expected X_poly = poly.fit_transform(X)."
        )

    # 3. Model is LinearRegression and is fitted
    def test_model_fitted(self):
        import user_code

        cond = False
        try:
            model = user_code.model
            cond = isinstance(model, LinearRegression) and hasattr(model, "coef_")
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "The model is a fitted LinearRegression instance.",
            "Expected model = LinearRegression() and model.fit()."
        )

    # 4. X_new reshaped to 2D array
    def test_X_new_shape(self):
        import user_code

        cond = False
        try:
            X_new = user_code.X_new
            cond = isinstance(X_new, np.ndarray) and len(X_new.shape) == 2 and X_new.shape[1] == 1
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X_new is correctly reshaped to (-1, 1).",
            "Expected X_new = np.linspace(...).reshape(-1, 1)."
        )

    # 5. X_new_poly transformed correctly
    def test_X_new_poly_transform(self):
        import user_code

        cond = False
        try:
            X_new = user_code.X_new
            X_new_poly = user_code.X_new_poly
            poly = user_code.poly

            expected = poly.transform(X_new)

            cond = (
                isinstance(X_new_poly, np.ndarray)
                and np.allclose(X_new_poly, expected)
            )
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X_new_poly is correctly transformed using the fitted poly instance.",
            "Expected X_new_poly = poly.transform(X_new)."
        )

    # 6. Check print statements logic (intercept_ and coef_)
    def test_params_printed(self):
        cond = False
        try:
            with open("user_code.py", "r") as f:
                src = f.read().replace(" ", "")
            cond = "model.intercept_" in src and "model.coef_" in src
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "Model intercept and coefficients are printed.",
            "Expected printing model.intercept_ and model.coef_."
        )


if __name__ == "__main__":
    unittest.main()

test_code.py

Beherrschung der grundlegenden Algorithmen des überwachten Lernens und deren Implementierung mit Scikit-learn. Untersuchung von linearer und polynomialer Regression zur Preisvorhersage sowie Übergang zur Klassifikation mit k-NN, logistischer Regression und Entscheidungsbäumen. Bewertung von Modellen durch Kreuzvalidierung, Steuerung von Overfitting mittels Regularisierung und Optimierung von Hyperparametern. Aufbau robuster prädiktiver Systeme und Definition komplexer Entscheidungsgrenzen für Aufgaben der Mehrklassenklassifikation.

Herausforderung: Bewertung des Modells

Lösung