Building Features from Nominal and Numeric Data in Microsoft Azure

Question 1

A distrubtion of data refers to which of the following?

The skewness of that data

The density of the data

The shape it is in when you graph it

The mean value of that dataset

Answer 1

The shape it is in when you graph it

Question 2

Much of the field of statistics is predicated on understanding what distribution?

Gaussian

Bernoulli

Exponential

Poisson

Answer 2

Gaussian

Question 3

The measure of the thickness of the tails of a distribution is known as what?

Mesokurtic

Platykurtic

Kurtosis

Leptokurtic

Answer 3

Kurtosis

Question 4

There are four core steps in the machine learning process. What are they and what is the order of that process?

Model, Source, Wrangle, Production

Source, Model, Wrangle, Production

Wrangle, Source, Model, Production

Source, Wrangle, Model, Production

Answer 4

Source, Wrangle, Model, Production

Question 5

A rare chance of occurrence within a dataset is often referred to as what?

Imputation

Outlier

Kurtosis

Platykurtic

Answer 5

Outlier

Question 6

In Python, missing values often have which entry?

EMPTY

SAN

NAN

NULL

Answer 6

NAN

Question 7

If the distribution is not Gaussian or the standard deviation is very small, which common scaler might be your best option?

Robust Scaler

Normalizer

Standard Scaler

Min-Max Scaler

Answer 7

Min-Max Scaler

Question 8

The process of binning manually based on your own personal insight of the data and setting ranges we would like to bin our data into is referred to as what?

Fixed-Width Binning

Detailed Binning

Binning by Instinct

Quantile Binning

Answer 8

Binning by Instinct

Question 9

Whole numbers that can’t be divided are known as what?

Discrete

Diminished

Qualitative

Continous

Answer 9

Discrete

Question 10

Which type of scale is used for labeling data?

Ratio

Nominal

Numeric

Discrete

Answer 10

Nominal