For this challenge, the same housing dataset will be used. However, now it has two features: age and area of the house (columns `'age'` and `'square_feet'`).

import pandas as pd

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

Your task is to build a Multiple Linear Regression model using the `OLS` class. Also, you will print the summary table to look at the p-values of each feature.

import unittest
import numpy as np
import pandas as pd
import statsmodels.api as sm


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


class TestUserCode(unittest.TestCase):

    # 1. Test that X contains the correct columns
    def test_X_contains_correct_columns(self):
        import user_code

        cond = False
        try:
            X = user_code.X
            cond = list(X.columns) == ["age", "square_feet"]
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X correctly contains ['age', 'square_feet'].",
            "Expected X to contain columns: ['age', 'square_feet']."
        )

    # 2. Test preprocessing with sm.add_constant
    def test_X_tilde_add_constant(self):
        import user_code

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

            cond = (
                isinstance(X_tilde, pd.DataFrame)
                and "const" in X_tilde.columns
                and X_tilde.shape[1] == X.shape[1] + 1
            )
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X_tilde correctly includes a constant column.",
            "Expected X_tilde to be created using sm.add_constant(X)."
        )

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

        cond = isinstance(user_code.model, RegressionResultsWrapper)

        _dynamic_test(
            self,
            cond,
            "model is a fitted OLS RegressionResultsWrapper.",
            "Expected model = sm.OLS(y, X_tilde).fit()"
        )

    # 4. Test X_new_tilde construction
    def test_X_new_tilde(self):
        import user_code
        import numpy as np

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

            expected_shape = (3, 3)  # const + 2 features

            cond = (
                isinstance(X_new_tilde, np.ndarray)
                and X_new_tilde.shape == expected_shape
                and np.allclose(X_new_tilde[:, 1:], X_new)
            )
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "X_new_tilde correctly created with sm.add_constant(X_new).",
            "Expected X_new_tilde to include constant column and match X_new values."
        )

    # 5. Test predictions
    def test_predictions(self):
        import user_code
        import numpy as np

        cond = False
        try:
            y_pred = user_code.y_pred
            cond = (
                isinstance(y_pred, np.ndarray)
                and y_pred.shape == (3,)
            )
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "y_pred is a NumPy array with correct shape (3,).",
            "Expected y_pred = model.predict(X_new_tilde) to have shape (3,)."
        )

    # 6. Test summary call (using code inspection)
    def test_model_summary_called(self):
        cond = False
        try:
            with open("user_code.py", "r") as f:
                src = f.read()
            cond = "model.summary()" in src.replace(" ", "")
        except Exception:
            cond = False

        _dynamic_test(
            self,
            cond,
            "model.summary() is called.",
            "Expected model.summary() to be printed."
        )


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


test_code.py

If you did everything right, you got the p-values close to zero. That means all our features are significant for the model.

Explores regression techniques for modeling and predicting continuous outcomes using Python. Builds on linear regression foundations to analyze relationships between variables, interpret model coefficients, and evaluate predictive performance on real-world datasets.


Challenge: Predicting Prices Using Two Features

Ratkaisu

Challenge: Predicting Prices Using Two Features

Ratkaisu