Evaluate the Model

In this challenge, you are given the good old housing dataset, but this time only with the 'age' feature.

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())


              1234
            
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())

Let's build a scatterplot of this 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()


              12345678
            
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()

Fitting a straight line to this data may not be a great choice. The price gets higher for either brand-new or really old houses. Fitting a parabola looks like a better choice. And that's what you will do in this challenge.

But before you start, recall the PolynomialFeatures class.

The fit_transform(X) method requires X to be a 2-D array (or a DataFrame).
Using X = df[['column_name']] will get your X suited for fit_transform().
And if you have a 1-D array, use .reshape(-1, 1) to make a 2-D array with the same contents.

The task is to build a Polynomial Regression of degree 2 using PolynomialFeatures and OLS.

Tarea

Swipe to start coding

Assign the X variable to a DataFrame containing column 'age'.
Create an X_tilde matrix using the PolynomialFeatures class.
Build and train a Polynomial Regression model.
Reshape X_new to be a 2-D array.
Preprocess X_new the same way as X.
Print the model's parameters.

Solución

import pandas as pd

import numpy as np

import statsmodels.api as sm

import matplotlib.pyplot as plt

from sklearn.preprocessing import PolynomialFeatures

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

# Assign the variables

X = df[['age']]

y = df['price']

n = 2 # A degree of Polynomial Regression

# Preprocess X

X_tilde = PolynomialFeatures(n).fit_transform(X)

# Build and train the model

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

# Create and preprocess X_new

X_new = np.linspace(0, 125, 200).reshape(-1, 1)

X_new_tilde = PolynomialFeatures(n).fit_transform(X_new)

# Predict the target for X_new

y_pred = model.predict(X_new_tilde)

# Visualize the result

plt.scatter(X, y, alpha=0.4)

plt.plot(X_new, y_pred, color='orange')

plt.show()

# Print the model's parameters

print(model.params)

¿Todo estuvo claro?

¡Gracias por tus comentarios!

Sección 3. Capítulo 5

single

import pandas as pd

import numpy as np

import statsmodels.api as sm

import matplotlib.pyplot as plt

from sklearn.preprocessing import PolynomialFeatures

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

# Assign the variables

X = df[['___']]

y = df['price']

n = 2 # A degree of Polynomial Regression

# Preprocess X

X_tilde = PolynomialFeatures(n).___(X)

# Build and train the model

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

# Create and preprocess X_new

X_new = np.linspace(0, 125, 200).___(-1, 1)

X_new_tilde = ___(n).fit_transform(___)

# Predict the target for X_new

y_pred = model.predict(X_new_tilde)

# Visualize the result

plt.scatter(X, y, alpha=0.4)

plt.plot(X_new, y_pred, color='orange')

plt.show()

# Print the model's parameters

print(model.___)

Pregunte a AI

Pregunte lo que quiera o pruebe una de las preguntas sugeridas para comenzar nuestra charla