Predict Prices Using Two Features

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())


              1234
            
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.

Oppgave

Swipe to start coding

Assign the 'age' and 'square_feet' columns of df to X.
Preprocess the X for the OLS's class constructor.
Build and train the model using the OLS class.
Preprocess the X_new array the same as X.
Predict the target for X_new.
Print the model's summary table.

Løsning

import pandas as pd

import numpy as np

import statsmodels.api as sm

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

# Assign the variables

X = df[['age', 'square_feet']]

y = df['price']

# Preprocess X

X_tilde = sm.add_constant(X)

# Build and train the model

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

# Create and preprocess X_new

X_new = np.array([[4, 10000], [30, 14000], [70, 16000]])

X_new_tilde = sm.add_constant(X_new)

# Predict instances from X_new and print them

y_pred = model.predict(X_new_tilde)

print('Prediction:', np.floor(y_pred)) # np.floor() keeps only the whole part of the numbers

# Print the summary table

print(model.summary())

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

Alt var klart?

Takk for tilbakemeldingene dine!

Seksjon 2. Kapittel 5

import pandas as pd

import numpy as np

import statsmodels.api as sm

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

# Assign the variables

X = df[['___', 'square_feet']]

y = df['price']

# Preprocess X

X_tilde = sm.___(X)

# Build and train the model

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

# Create and preprocess X_new

X_new = np.array([[4, 10000], [30, 14000], [70, 16000]])

X_new_tilde = ___.___(X_new)

# Predict instances from X_new and print them

y_pred = ___.predict(___)

print('Prediction:', np.floor(y_pred)) # np.floor() keeps only the whole part of the numbers

# Print the summary table

print(model.___())