SKlearn

Question 1

What is independent variable called in SKlearn

Answer 1

Feature

Question 2

What is dependent variable called?

Answer 2

Output, Target

Question 3

Find the R-squared in sklearn

Answer 3

reg.score(x_matrix,y)

Notice x has been reshaped to a 2d vector

Question 4

Find the coefficients in sklearn

Answer 4

reg.coef_

Result is an array containing all coefficients

Question 5

Find the intercept in sklearn

Answer 5

reg.intercept_

–> Leads to a float

Question 6

Making predictions in sklearn

Answer 6

reg.predict(input)

Leads to array not a float, because predict method can take more than 1 value

Question 7

What is the ML word for observation?

Answer 7

Sample

Each row in the dataset is a sample

Question 8

How to calculate Adjusted R-squared in Python?

Answer 8

Set cell to markdown

Put the formula in Python –> Look up formula
r2 = reg.score(x,y)
n = x.shape[0]
p = x.shape[1]

Notice that x does not need to be reshaped because it already contains 2 variables. Then fill in these variables into formula.

Remember: Adjusted R-squared steps on the R-squared and adjusts for the nr of variables included in the model

Question 9

What is the advantage of feature selection?

Answer 9

Simplifies models

Improves speed and prevents a series of unwanted issues arising from having too many features

Question 10

What can you do with the F-statistic?

Answer 10

Test whether model has merit

Null Hypothesis is that all betas are equal to 0 –> H0: ß1 = ß2 = ß3 = 0

If all Beta’s are 0 than the model is useless

Question 11

What is an F-Statistic?

Answer 11

Similar to a T statistic from a T-test

T-test will tell you if a single variable is statistically significant

F-test will tell you if a group of variables are jointly significant

Based on hypothesis that all betas are equal to 0 –> H0: ß1 = ß2 = ß3 = 0

Question 12

How to interpret the P-value in the results table?

Answer 12

A low P-value (< 0.05) means that the coefficient is likely not to equal zero.

A high P-value (> 0.05) means that we cannot conclude that the explanatory variable affects the dependent variable (here: if Average_Pulse affects Calorie_Burnage).

A high P-value is also called an insignificant P-value.

Question 13

How is the P-value denoted in the results table?

Answer 13

P>|t|

Question 14

How to interpret the F-statistic? And the P-value change?

Answer 14

Compare F-statistic without or without variable –> Lower F-statistic means closer to a non-significant model

Prob(F-statistic) can still be significant but notice the change –> If it’s higher then drop the variable

Question 15

What will this return?

from sklearn.feature_selection import f_regression

f_regression(x,y)

Answer 15

2 Arrays
1 with the F-statistics
1 with the according p-values –> Prob(F-statistic)

Question 16

What does feature_selection.f_regression do?

Answer 16

It creates simple linear regressions of each feature and the dependent variable

Question 17

from sklearn.feature_selection import f_regression
f_regression(x,y)

How to extract the p-values from regression results?

Answer 17

p_values is f_regression(x,y)[1]

Since first array are the F-statistics

Question 18

Do p-values reflect the interconnection of the features in our multiple linear regression?

Answer 18

No

Question 19

Why is Feature Scaling / Standardization needed?

Answer 19

Common problem when working with numerical data is difference in magnitude

It is transforming the data into a standard scale so all numbers are of the same magnitude

Question 20

What is feature scaling also called?

Answer 20

Standardization / Normalization

Question 21

What are coefficients and intercept called in Machine Learning

Answer 21

Weights and Bias

Question 22

What is the reason SKlearn does not really support p-values?

Answer 22

Most ML practisioners perform some kind of feature scaling so what the (very small) weights off the variable become apparent.

Question 23

What would you need to do after standardizing the dataset?

Answer 23

After standardizing the dataset, the input for predict must be standardized as well

Input must be standarized in the same way

Question 24

x_simple_matrix = x_scaled[:,0].reshape(-1,1)

What happens here?

Answer 24

You are taking the first column out of x_scaled