Mid-Term Exam

Question 1

List and describe four levels of measurements.

Answer 1

Nominal
Ordinal
Interval
Ratio

Question 2

Python includes built in data types for lists, sets, and dicts?

Answer 2

True

Question 3

The median of a set of numbers is defined as …

Answer 3

The middle value.
Put the numbers in order
If 2 numbers are in the middle compute the mean.

It is good at finding the center distribution.

Question 4

All data are quantitative?

Answer 4

False

Question 5

Ordinal values allow us to measure distances

Answer 5

False

Question 6

Nominal values allow us to order different data points

Answer 6

False

Question 7

Python includes built in data types for lists, sets, and dicts

Answer 7

True

Question 8

Explain the difference between list and dict values in python.

Answer 8

Python lists are ordered variable-length arrays, rather than linked lists

Python dictionaries unordered unique resizable hash tables.

Question 9

if statements in python can include additional clauses using the elseif keyword.

Answer 9

False

Question 10

What does lamda do in python?

Answer 10

lamda is a way to create a temporary function

It can be used when performing a map(lambda x: x, x+2)

Question 11

Data formats are used as a way to share data between systems?

Answer 11

True

Question 12

Data are measurements of a phenomenon

Answer 12

True

Question 13

Data are the same as the thing being measured

Answer 13

False

Question 14

Systems store formatted data

Answer 14

True

Question 15

CSV files are like a tab from a spreadsheet

Answer 15

True

Question 16

numpy arrays have no data type

Answer 16

False

Array is a dimensional vector

Question 17

NumPy arrays have a .all() method that returns true if any of the elements are true

Answer 17

false

Question 18

What does the argmax function do in numpy?

Answer 18

Returns the indices of the maximum values along an axis

Question 19

Explain the relationship between a Series and a DataFrame in pandas?

Answer 19

Series is the datastructure for a single column of a DataFrame

The data in a DataFrame is actually stored in memory as a collection of Series

Question 20

What is an “index” on a pandas dataframe?

Answer 20

An index is the reference to the series in dataframe

Question 21

You can see the first several rows of a dataframe using

df.first()

Answer 21

False

Question 22

Given two series, a and b, does a == b return true if they’re equivalent and false otherwise? If not, what does it produce instead?

Answer 22

The == operator compares by checking for equality

It would return ‘both a and b are equal’

Question 23

Compare and contrast supervised and unsupervised machine learning

Answer 23

Supervised learning is machine learning that we have the answer for (labeled data)

Unsupervised learning is ML for which we are uncertain as to the answer or have no labeled data.

Question 24

Compare and contrast regression and classification

Answer 24

Regression is the process of trying to make a prediction based on a previous data set.

Classification is where we are attempting to determine if something is part of a class.

Question 25

The line separating the positive class and negative class is called the

Answer 25

decision boundary

Question 26

In order to apply machine learning, we must first convert our data into a numeric format

Answer 26

True

Question 27

Define precision and recall.

Answer 27

Precision is true positive / (true positive + true negative)

Recall is true positive / (true positive + false negative)

Question 28

What does a confusion matrix display?

Answer 28

A confusion matrix displays possible answers you get when classifying data

                           Was positive          was negative 

Condition positive | True positive | true negative
(type 1 error)

Condition negative | false positive
(type 2 error) | false negative

Question 29

F1-score is a combination of which of the following metrics:

Answer 29

precision and recall

Question 30

What is the visual effect of modifying the cluster_std when using make_blobs() to generate synthetic classification data?

Answer 30

By modifying the cluster_std to the dataset we would bring the data closer (or further apart) from the median.

Question 31

How is the cost function used during the training process?

Answer 31

A cost function is something you want to minimize. For example, your cost function might be the sum of squared errors over your training set. Gradient descent is a method for finding the minimum of a function of multiple variables. So you can use gradient descent to minimize your cost function.

Question 32

During training of a linear regressor, the user must specify the bias parameter in advance.

Answer 32

False

Question 33

What is a residual in linear regression?

Answer 33

Is the difference between the optimal solution and the proposed guess.

Question 34

How is the residual sum of squares (RSS) cost function for linear regression defined?

Answer 34

Sum of the squared of the residuals. It is a measure of the discrepancy between the data and an estimation model.

Question 35

In linear regression, our regressor learns a decision boundary that’s shaped like a bowl (or upside-down dome).

Answer 35

False

Question 36

What is the role of the logistic function in logistic regression?

Answer 36

To classify between the 0 and 1 boundary

Question 37

What is the name of the cost function we learned for logistic regression?

Answer 37

Cross Entropy Function

Question 38

The cost function for logistic regression penalizes all wrong answers equally

Answer 38

False

Question 39

Define the basic algorithm for kNN classification.

Answer 39

For an unlabeled shape we can look at the closest nearby labelled samples to determine what the class of s should be.

1) Find the k nearest known training point
2) Average the values for the point
3) Assign the class

Question 40

What parameter performs regularization in kNN classification? If you want to increase variance in a kNN classifier, should this parameter get larger or smaller? Why?

Answer 40

K is the parameter that performs regularization

To increase the variance in then you should reduce K.

Increasing k acts like a regularizer and tends towards more biased smoother model.

Question 41

Explain cross-validation. Why do we use cross-validation?

Answer 41

We may have a limited data set so we could apply cross validation to break the training data up so as to limit the possibility of the model over learning (or memorizing) with available dataset

Question 42

In class we discussed that there are three basic contributors to model error. What are they?

Answer 42

Overfitting
Underfitting
Not enough data

Question 43

What is the purpose of regularization in machine learning?

Answer 43

The purpose of regularization is to encourage a simpler model.

Question 44

What part of the learning process is modified when we apply regularization to a logistic or linear regression model?

Answer 44

We modify the weights in the cost function to to find the optimal solution.

Question 45

L1 regularization is the sum of the square roots of the weights in your model

Answer 45

False

Question 46

L2 regularization is the sum of the squares of the weights of your model

Answer 46

True

Question 47

L1 regularization will result in sparser models

Answer 47

True

Question 48

Sparser models means that there are fewer training samples used during the learning process

Answer 48

False

Question 49

Hyperparameters are asjusted outside the training procedure of the model

Answer 49

True