Learn Building Polynomial Regression

Loading File

We load poly.csv and inspect it:


              1234
            
import pandas as pd
file_link = 'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b22d1166-efda-45e8-979e-6c3ecfc566fc/poly.csv'
df = pd.read_csv(file_link)
print(df.head())

Then visualize the relation:


              12345
            
import matplotlib.pyplot as plt
X = df['Feature']
y = df['Target']
plt.scatter(X, y)
plt.show()

A straight line fits poorly, so Polynomial Regression is more suitable.

Building X̃ Matrix

To create X̃, we could add squared features manually:

df['Feature_squared'] = df['Feature'] ** 2

But for higher degrees, PolynomialFeatures is easier. It requires a 2-D structure:

from sklearn.preprocessing import PolynomialFeatures
X = df[['Feature']]
poly = PolynomialFeatures(n)
X_tilde = poly.fit_transform(X)

It also adds the constant column, so no sm.add_constant() needed.

If X is 1-D, convert it:

X = X.reshape(-1, 1)

Building the Polynomial Regression

import statsmodels.api as sm
y = df['Target']
X = df[['Feature']]
X_tilde = PolynomialFeatures(n).fit_transform(X)
model = sm.OLS(y, X_tilde).fit()

Predicting requires transforming new data the same way:

X_new_tilde = PolynomialFeatures(n).fit_transform(X_new)
y_pred = model.predict(X_new_tilde)

Full Example


              123456789101112131415161718
            
import pandas as pd, numpy as np, matplotlib.pyplot as plt
import statsmodels.api as sm
from sklearn.preprocessing import PolynomialFeatures

df = pd.read_csv(file_link)
n = 2
X = df[['Feature']]
y = df['Target']
X_tilde = PolynomialFeatures(n).fit_transform(X)
model = sm.OLS(y, X_tilde).fit()

X_new = np.linspace(-0.1, 1.5, 80).reshape(-1,1)
X_new_tilde = PolynomialFeatures(n).fit_transform(X_new)
y_pred = model.predict(X_new_tilde)

plt.scatter(X, y)
plt.plot(X_new, y_pred)
plt.show()

Try different n values to see how the curve changes and how predictions behave outside the original feature range—this leads into the next chapter.

Everything was clear?

Thanks for your feedback!

Section 3. Chapter 3

Ask AI

Ask anything or try one of the suggested questions to begin our chat

Suggested prompts:

What does the `PolynomialFeatures` class do in this context?

How do I choose the best degree `n` for my polynomial regression?

Can you explain why a straight line fits poorly in this example?

Awesome!

Completion rate improved to 5.26

Swipe to show menu