Regression models

Practicing Statistics Interview Questions in Python

Conor Dewey

Data Scientist, Squarespace

Getting started

Correlated scatter plot

¹ Wikimedia

Assumptions

Linear relationship
Errors are normally distributed
Homoscedasticity
Independent observations

Linear regression

Linear fit

¹ Wikipedia

Linear regression

Linear regression formula

Example: linear regression

from sklearn.linear_model import LinearRegression 
lm = LinearRegression()
lm.fit(X_train, y_train)

LinearRegression(copy_X=True, fit_intercept=True, 
                    n_jobs=None, normalize=False)

Example: linear regression

coef = lm.coef_
print(coef)

[0.79086669]

Logistic regression

Logistic regression visualized

¹ Wikimedia

Logistic regression

Sigmoid function

Example: logistic regression

from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(solver='lbfgs')
clf.fit(X_train, y_train)

LogisticRegression(C=1.0, class_weight=None, 
                   dual=False, fit_intercept=True, 
                   intercept_scaling=1,
                   max_iter=100, multi_class='warn',
                   n_jobs=None, penalty='l2',
                   random_state=None, solver='lbfgs',
                   tol=0.0001, verbose=0, 
                   warm_start=False)

Example: logistic regression

coefs = clf.coef_
print(coefs)

[[0.4015177  3.85056451]]

accuracy = clf.score(X_test, y_test)
print(accuracy)

0.8583333333333333

Summary

Review
Assumptions
Linear regression
Logistic regression

Let's prepare for the interview!

Practicing Statistics Interview Questions in Python