I denne udfordring får du det velkendte boligdatasæt, men denne gang kun med `'age'`-egenskaben.

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())

Dernæst oprettes et scatterplot for disse data:

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()

En ret linje passer dårligt her: priserne stiger for både meget nye og meget gamle huse. En parabel modellerer denne tendens bedre — det er det, du skal bygge i denne udfordring.

Men før du begynder, skal du huske `PolynomialFeatures`-klassen.

`fit_transform(X)` kræver et 2-D array eller DataFrame. Brug `df[['col']]` eller, for et 1-D array, anvend `.reshape(-1, 1)` for at konvertere det til 2-D.


Opgaven er at opbygge en polynomiel regression af grad 2 ved hjælp af `PolynomialFeatures` og `OLS`.

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


# 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 to create X_tilde
    def test_X_tilde_polynomial_preprocessing(self):
        import user_code

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

            expected = PolynomialFeatures(n).fit_transform(X)

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

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

    # 3. Model is fitted using sm.OLS
    def test_model_fitted(self):
        import user_code
        from statsmodels.regression.linear_model import RegressionResultsWrapper

        cond = isinstance(user_code.model, RegressionResultsWrapper)

        _dynamic_test(
            self,
            cond,
            "The model is correctly fitted using sm.OLS.",
            "Expected model = sm.OLS(y, X_tilde).fit()."
        )

    # 4. X_new reshaped to 2D array via reshape(-1,1)
    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_tilde preprocessed with PolynomialFeatures(n)
    def test_X_new_tilde_polynomial(self):
        import user_code

        cond = False
        try:
            n = user_code.n
            X_new = user_code.X_new
            X_new_tilde = user_code.X_new_tilde

            expected = PolynomialFeatures(n).fit_transform(X_new)

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

        _dynamic_test(
            self,
            cond,
            "X_new_tilde is correctly processed using PolynomialFeatures.",
            "Expected X_new_tilde = PolynomialFeatures(n).fit_transform(X_new)."
        )

    # 6. model.params exists and is printed in student code
    def test_model_params_printed(self):
        cond = False
        try:
            with open("user_code.py", "r") as f:
                src = f.read().replace(" ", "")
            cond = "model.params" in src
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "Model parameters are printed using model.params.",
            "Expected print(model.params)."
        )


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


test_code.py

Lineær regression er et centralt begreb inden for prædiktiv analyse. Det anvendes bredt af dataforskere, dataanalytikere og statistikere, da det er let at opbygge og fortolke, men samtidig kraftfuldt nok til mange opgaver.

Lad os begynde med den simpleste lineære regressionsmodel! Du vil lære idéen bag lineær regression og hvordan man foretager forudsigelser i Python.

De fleste virkelige forudsigelsesopgaver involverer mere end én feature. Du vil lære, hvordan man håndterer lineær regression med flere features.

En ret linje beskriver ikke altid dataene tilstrækkeligt. Lad os lære at opbygge en mere kompleks model til forudsigelse. Det er det, polynomiel regression egner sig til.

Nu hvor du ved, hvordan man opbygger flere lineære regressionsmodeller, har du brug for en metode til at vælge den bedste. Dette kan opnås ved hjælp af metrikker. Dette afsnit forklarer de mest anvendte metrikker og de udfordringer, du kan møde ved brugen af dem.

Udfordring: Evaluering af Modellen

Løsning