For this challenge, you will build the same Polynomial Regression of degree 2 as in the previous challenge. However, you will need to split the set into a training set and a test set to calculate RMSE for both those sets. This is required to judge whether the model overfits/underfits or not.  
Here is the reminder of the `train_test_split()` function you'll want to use.

And also reminder of the `mean_squared_error()` function with `np.sqrt()` needed to calculate RMSE:
```python
rmse = np.sqrt(mean_squared_error(y_true, y_predicted))
```

import unittest
import numpy as np
import pandas as pd
import statsmodels.api as sm
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import mean_squared_error


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


class TestUserCode(unittest.TestCase):

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

        try:
            X = user_code.X
            condition = list(X.columns) == ["age"]
        except:
            condition = False

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

    # 2 — PolynomialFeatures applied
    def test_polynomial_features(self):
        import user_code

        try:
            n = user_code.n
            X = user_code.X
            expected = PolynomialFeatures(n).fit_transform(X)
            condition = np.allclose(user_code.X_tilde, expected)
        except:
            condition = False

        _dynamic_test(
            self,
            condition,
            "PolynomialFeatures applied correctly to X.",
            "Expected X_tilde = PolynomialFeatures(n).fit_transform(X)."
        )

    # 3 — split correctness
    def test_split(self):
        import user_code

        try:
            total = len(user_code.X_tilde)
            condition = (
                len(user_code.X_tilde_train) + len(user_code.X_tilde_test) == total
            )
        except:
            condition = False

        _dynamic_test(
            self,
            condition,
            "Dataset split correctly.",
            "Expected train_test_split(X_tilde, y, test_size=0.3, random_state=0)."
        )

    # 4 — model is fitted
    def test_model_fitted(self):
        import user_code
        from statsmodels.regression.linear_model import RegressionResultsWrapper

        condition = isinstance(user_code.model, RegressionResultsWrapper)

        _dynamic_test(
            self,
            condition,
            "Model is fitted correctly using OLS.",
            "Expected model = sm.OLS(y_train, X_tilde_train).fit()."
        )

    # 5 — predictions for train and test exist & correct shape
    def test_predictions(self):
        import user_code

        try:
            cond1 = isinstance(user_code.y_train_pred, np.ndarray)
            cond2 = isinstance(user_code.y_test_pred, np.ndarray)
            cond3 = len(user_code.y_train_pred) == len(user_code.y_train)
            cond4 = len(user_code.y_test_pred) == len(user_code.y_test)

            condition = cond1 and cond2 and cond3 and cond4
        except:
            condition = False

        _dynamic_test(
            self,
            condition,
            "Predictions for train and test sets computed correctly.",
            "Expected model.predict(X_tilde_train/test)."
        )

    # 6 — RMSE computed manually with sqrt(MSE)
    def test_rmse_correct(self):
        import user_code

        try:
            train_expected = np.sqrt(
                mean_squared_error(user_code.y_train, user_code.y_train_pred)
            )
            test_expected = np.sqrt(
                mean_squared_error(user_code.y_test, user_code.y_test_pred)
            )

            condition = (
                np.isclose(train_expected, user_code.train_rmse)
                and np.isclose(test_expected, user_code.test_rmse)
            )
        except:
            condition = False

        _dynamic_test(
            self,
            condition,
            "RMSE is computed using sqrt(MSE).",
            "Expected RMSE = np.sqrt(mean_squared_error(...))."
        )

    # 7 — summary must be printed
    def test_summary_called(self):
        condition = False
        try:
            with open("user_code.py", "r") as f:
                contents = f.read().replace(" ", "")
            condition = "model.summary()" in contents
        except:
            condition = False

        _dynamic_test(
            self,
            condition,
            "model.summary() is printed.",
            "Expected print(model.summary())."
        )


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


test_code.py

When you complete the task, you will notice that the test RMSE is even lower than the training RMSE. Usually, models do not show better results on unseen instances. Here, the difference is tiny and caused by chance. Our dataset is relatively small, and while splitting, the test set received a bit better(easier to predict) data points.

Lineare Regression ist ein zentrales Konzept in der prädiktiven Analytik. Sie wird von Data Scientists, Datenanalysten und Statistikern häufig verwendet, da sie einfach zu erstellen und zu interpretieren ist, aber dennoch für viele Aufgaben ausreichend leistungsfähig bleibt.

Beginnen wir mit dem einfachsten Modell der linearen Regression. Sie lernen das Konzept der linearen Regression kennen und erfahren, wie Vorhersagen in Python getroffen werden.

Die meisten Vorhersageaufgaben in der Praxis beinhalten mehr als ein Merkmal. Sie lernen, wie man lineare Regression mit mehreren Merkmalen anwendet.

Eine Gerade beschreibt die Daten nicht immer ausreichend. Lernen Sie, wie ein komplexeres Modell für Vorhersagen erstellt werden kann. Dafür eignet sich die polynomiale Regression.

Nachdem Sie nun wissen, wie man verschiedene lineare Regressionsmodelle erstellt, benötigen Sie eine Methode, um das beste auszuwählen. Dies ist mithilfe von Metriken möglich. In diesem Abschnitt werden die am häufigsten verwendeten Metriken sowie die Herausforderungen bei deren Anwendung erläutert.

Challenge: Predicting Prices Using Polynomial Regression

Lösung