9

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import statsmodels.api as sm

# Sample data: Housing Prices and Square Footage

data = {

'sqft': [1500, 1700, 1900, 2000, 2100, 2300, 2500],

'price': [200000, 220000, 240000, 260000, 290000, 320000, 350000]

}

df = pd.DataFrame(data)

# Add the spline feature: (sqft - 2000)+

df['spline'] = np.where(df['sqft'] > 2000, df['sqft'] - 2000, 0)

# Design matrix

X = sm.add_constant(df[['sqft', 'spline']])  # Intercept + sqft + spline term

y = df['price']

# Fit the model

model = sm.OLS(y, X).fit()

# Output the results

print(model.summary())