Machine Learning with Python : Coursera Quiz Answers 2023

Week 1 Quiz Answers

Practice Quiz

1.

Question 1

Supervised learning deals with unlabeled data, while unsupervised learning deals with labelled data.

1 point

True

False

2.

Question 2

The "Regression" technique in Machine Learning is a group of algorithms that are used for:

1 point

Prediction of class/category of a case; for example, a cell is benign or malignant, or a customer will churn or not.

Finding items/events that often co-occur; for example grocery items that are usually bought together by a customer.

Predicting a continuous value; for example predicting the price of a house based on its characteristics.

3.

Question 3

When comparing Supervised with Unsupervised learning, is this sentence True or False?

In contrast to Supervised learning, Unsupervised learning has more models and more evaluation methods that can be used in order to ensure the outcome of the model is accurate.

1 point

True

False

Graded Quiz

1.

Question 1

In a dataset, what do the columns represent?

1 point

Variable Type

Observations

Features

Independent Variables

2.

Question 2

What is a major benefit of unsupervised learning over supervised learning?

1 point

Being able to produce a prediction based on unlabelled data.

Discover previously unknown information about the dataset.

Better evaluates the performance of a built model.

Explore the relationship between features and the target.

3.

Question 3

What’s the correct order for using a model?

1 point

Clean the data, fit the model on the entire dataset, split the data into training and test sets, evaluate model accuracy.

Split the data into the training and test sets, fit the model on the train set, clean the data, evaluate model accuracy.

Clean the data, split the data into training and test sets, fit the model on the train set, evaluate model accuracy.

Split the data into training and test sets, fit the model on the train set, evaluate model accuracy.

4.

Question 4

Which of the following is suitable for an unsupervised learning?

1 point

Segment customers into groups for discovering similar characteristics between them.

Examine the relationship between academic performance and level of in-class participation using observations that include a feature recording each student’s grade.

Predict house price based on location, house size, and number of rooms.

Classifying benign and malignant tumors using historical data on tumor shape, color, etc.

5.

Question 5

The main purpose of the NumPy library is to:

1 point

Construct machine learning models.

Visualize results in 2D and 3D plots.

Perform computations on arrays efficiently.

Achieve scientific computations.

Week 2 Quiz Answers

Practice Quiz

1.

Question 1

Which of the following is the meaning of "Out of Sample Accuracy" in the context of evaluation of models?

1 point

"Out of Sample Accuracy" is the percentage of correct predictions that the model makes on data that the model has NOT been trained on.

“Out of Sample Accuracy” is the percentage of correct predictions that the model makes using the test dataset.

"Out of Sample Accuracy" is the accuracy of an overly trained model (which may capture noise and produced a non-generalized model)

“Out of Sample Accuracy” is the accuracy of a model on all the data available.

2.

Question 2

When should we use Multiple Linear Regression? (Select two)

1 point

When there are multiple dependent variables

When we would like to predict impacts of changes in independent variables on a dependent variable.

When we would like to identify the strength of the effect that the independent variables have on a dependent variable.

When we would like to examine the relationship between multiple variables.

3.

Question 3

Which sentence is TRUE about linear regression?

1 point

A linear relationship is necessary between the independent and dependent variables as well as in between independent variables.

Multiple linear regression requires a linear relationship between the predictors and the response, but simple linear regression does not.

Simple linear regression requires a linear relationship between the predictor and the response, but multiple linear regression does not.

A linear relationship is necessary between the independent variables and the dependent variable.

Graded Quiz

1.

Question 1

What are the requirements for independent and dependent variables in regression?

1 point

Independent and dependent variables must be continuous.

Independent and dependent variables can be either categorical or continuous.

Independent variables must be continuous. Dependent variables can be either categorical or continuous.

Independent variables can be either categorical or continuous. Dependent variables must be continuous.

2.

Question 2

The key difference between simple and multiple regression is:

1 point

Simple regression assumes a linear relationship between variables, whereas this assumption is not necessary for multiple regression.

To estimate a single dependent variable, simple regression uses one independent variable whereas multiple regression uses multiple.

Simple linear regression compresses multidimensional space into one dimension.

Multiple linear regression introduces polynomial features.

3.

Question 3

Recall that we tried to predict CO2 emission with car information. Say that now we can describe the relationship as: CO2_emission = 130 - 2.4*cylinders + 8.3*fuel_consumption

What is TRUE of this relationship?

1 point

When “cylinders” decreases by 1 while fuel_consumption remains constant, CO2_emission increases by 2.4 units.

When “cylinders” increases by 1 while fuel_consumption remains constant, CO2_emission increases by 2.4 units.

Since the coefficient for “fuel_consumption” is greater than that for “cylinders”, “fuel_consumption” has higher impact on CO2_emission.

When both “cylinders” and “fuel_consumption” increase by 1 unit, CO2_emission decreases.

4.

Question 4

What could be the cause of a model yielding high training accuracy and low out-of-sample accuracy?

1 point

The model is training on the entire dataset, so it is overfitting.

The model is training on a small training set, so it is overfitting.

The model is training on the entire dataset, so it is underfitting.

The model is training on a small training set, so it is underfitting.

5.

Question 5

Multiple Linear Regression is appropriate for:

1 point

Predicting whether a drug is effective for a patient based on her characteristics.

Predicting tomorrow’s rainfall amount based on the wind speed and temperature.

Predicting the sales amount based on month.

Week 3 Quiz Answers

Practice Quiz

1.

Question 1

Which one is TRUE about the kNN algorithm?

1 point

kNN is a classification algorithm that takes a bunch of unlabelled points and uses them to learn how to label other points.

The most similar point in kNN is the one with the smallest distance averaged across all normalized features.

kNN calculates similarity by measuring how close the two data points’ response values are.

kNN algorithm can be used to estimate values for a continuous target.

2.

Question 2

If the information gain of the tree by using attribute A is 0.3, what can we infer?

1 point

The entropy of a tree before split minus weighted entropy after split by attribute A is 0.3.

Entropy in the decision tree increases by 0.3 if we make this split.

Compared to attribute B with 0.65 information gain, attribute A should be selected first for splitting.

By making this split, we increase the randomness in each child node by 0.3.

3.

Question 3

When we have a value of K for KNN that’s too small, what will the model most likely look like?

1 point

The model will have high out-of-sample accuracy.

The model will have high accuracy on the test set.

The model will be highly complex and captures too much noise.

The model will be overly simple and does not capture enough noise.

Graded Quiz

1.

Question 1

What can we infer about our kNN model when the value of K is too big?

1 point

The training accuracy will be high, while the out-of-sample accuracy will be low.

The model will capture a lot of noise as a result of overfitting.

The model will be too complex and not interpretable.

The model is overly generalized and underfitted to the data.

2.

Question 2

When splitting data into branches for a decision tree, what kind of feature is favored and chosen first?

1 point

The feature that increases entropy in the tree nodes.

The feature with the greatest number of categories.

The feature that splits the data equally into groups.

The feature that increases purity in the tree nodes.

3.

Question 3

What is the relationship between entropy and information gain?

1 point

When information gain increases, entropy decreases.

High entropy and high information gain is desired.

When information gain decreases, entropy decreases.

High entropy and low information gain is desired.

4.

Question 4

Predicting whether a customer responds to a particular advertising campaign or not is an example of what?

1 point

Classification problem

Machine learning

Regression

None of the above

5.

Question 5

For a new observation, how do we predict its response value (categorical) using a KNN model with k=5?

1 point

Form 5 clusters and assign the new observation to the most similar cluster, taking the mean value as prediction.

Take majority vote among 5 points whose features are closest to the new observation.

Take the majority vote among 5 points who are the most similar to each other.

Take the average among 5 points whose features are closest to the new observation.

Week 4 Quiz Answers

Practice Quiz

1.

2.

3.

Graded Quiz

1.

Question 1

Which option lists the steps of training a logistic regression model in the correct order?

1. Use the cost function on the training set.

2. Update weights with new parameter values.

3. Calculate cost function gradient.

4. Initialize the parameters.

5. Repeat until specified cost or iterations reached.

1 point

1, 4, 3, 2, 5

4, 1, 3, 2, 5

4, 3, 2, 5, 1

3, 2, 5, 4, 1

2.

Question 2

What is the objective of SVM in terms of hyperplanes?

1 point

Choose the hyperplane that represents the largest margin between the two classes.

Minimize the distance between hyperplane and the support vectors.

Choose the hyperplane that’s closest to one of the two classes.

Find the hyperplane of the lowest dimension.

3.

Question 3

Logistic regression is used to predict the probability of a:

1 point

Categorical dependent variable

Numerical independent variable

­Categorical independent variable

Numerical dependent variable

4.

Question 4

In which cases would we want to consider using SVM?

1 point

When we want multiple decision boundaries with varying weights.

When mapping the data to a higher dimensional feature space can better separate classes.

When we desire efficiency when using large datasets.

When we desire probability estimates for each class.

5.

Question 5

What is a disadvantage of one-vs-all classification?

1 point

It cannot output probability estimates of classes.

There’s an ambiguous region where multiple classes are valid outputs.

It requires more models to be created compared to one-vs-one.

It does not handle two-class classification well.

Week 5 Quiz Answers

Practice Quiz

1.

Question 1

Which of the following is an application of clustering?

1 point

Customer segmentation

Sales prediction

Price estimation

Customer churn prediction

2.

Question 2

Which approach can be used to calculate dissimilarity of objects in clustering?

1 point

Cosine similarity

Minkowski distance

Euclidian distance

All of the above

3.

Question 3

How is a center point (centroid) picked for each cluster in k-means upon initialization? (select two)

1 point

We can randomly choose some observations out of the data set and use these observations as the initial means.

We select the k points closest to the mean/median of the entire dataset.

We can create some random points as centroids of the clusters.

We can select it through correlation analysis.

Graded Quiz

Give Me Answers If You have

1.

Question 1

The objective of k-means clustering is:

1 point

Maximize the number of correctly classified data points

Separate dissimilar samples and group similar ones

Minimize the cost function via gradient descent

Yield the highest out of sample accuracy

4.

Question 4

When the parameter K for k-means clustering increases, what happens to the error?

1 point

It will decrease because the data points are less possible to be in the wrong cluster.

It will decrease because distance between data points and centroid will decrease.

It might increase or decrease depending on if data points are closer to the centroid.

It will increase because incorrectly classified points are further from the correct centroid.

Week 6 Quiz Answers

Practice Quiz

1.

Question 1

Which of the following is not true about Machine Learning?

1 / 1 point

Machine Learning models help us in tasks such as object recognition, summarization, and recommendation.

Machine learning gives computers the ability to make decision by writing down rules and methods and being explicitly programmed.

Machine Learning models iteratively learn from data and allow computers to find hidden insights.

Machine Learning was inspired by the learning process of human beings.

Correct

Correct! Machine learning can learn without explicitly being programmed to do so.

3.

Question 3

In which of the following would you use Multiple Linear Regression?

1 / 1 point

Predicting the production of apples in an orchard based on temperature and rainfall.

Predict whether a customer is likely to repay a loan based on age and income.

Predict CO2 emission of a car based on engine size.

Recommend products to customers based on their demographic characteristics.

Correct

Correct! We use multiple linear regression when there is more than one independent variable for predicting a continuous variable.

1.

Question 1

Which of the following is not true about Machine Learning?

1 / 1 point

Machine Learning was inspired by the learning process of human beings.

Machine learning gives computers the ability to make decision by writing down rules and methods and being explicitly programmed.

Machine Learning models iteratively learn from data and allow computers to find hidden insights.

Machine Learning models help us in tasks such as object recognition, summarization, and recommendation.

Correct

Correct! Machine learning can learn without explicitly being programmed to do so.

2.

Question 2

Which of the following is not a Machine Learning technique?

1 / 1 point

Associations

Regression/Estimation

Clustering

Heuristics

Correct

Correct! The common machine learning techniques are regression/estimation, classification, clustering, association, anomaly detection, sequence mining, and recommendation systems.

3.

Question 3

Which of the following is true for Multiple Linear Regression?

1 / 1 point

Multiple independent variables are used to predict a dependent variable.

The relationship between the independent variable x and the dependent variable y is modeled as an nth degree polynomial in x.

One independent variable is used to predict a dependent variable.

Observational data are modeled by a function which is a nonlinear combination of the model parameters and depends on one or more independent variables.

Correct

Correct! This contrasts simple linear regression, which only uses one independent variable.

4.

Question 4

Which of the below is an example of classification problem?

1 / 1 point

Predicting whether an email is spam or not.

Predicting whether a customer will purchase a particular item based on an advertising campaign.

Predicting whether a customer would purchase an associated product based on previous purchases.

All of the above.

Correct

Correct! All of these can be phrased as a classification task.

5.

Question 5

Which of the following statements are TRUEabout Logistic Regression? (select two)

0 / 1 point

Logistic regression can be used both for binary classification and multi-class classification.

Logistic regression finds a regression line through the data to predict the probability of a point belonging to a class.

This should not be selected

Incorrect. Logistic regression applies the sigmoid function that always returns a value between 0 and 1.

Logistic regression is analogous to linear regression but takes a categorical/discrete target field instead of a numeric one.

Correct

Almost correct! There are other true statements about Logistic Regression.

In logistic regression, the dependent variable is always binary.

6.

Question 6

Which of the following statements is true for k-means clustering?

1 / 1 point

Is one of the simplest unsupervised learning algorithms that solve well known clustering problems.

k-means divides the data into non-overlapping clusters without any cluster-interval structure.

The object of k-means is to form clusters in such a way that similar samples go into a cluster, and dissimilar samples fall into different clusters.

All of the above.

Correct

Correct! All statements are true about k-Means clustering.

8.

Question 8

What are some advantages of logistic regression over SVM?

1 / 1 point

It focuses on finding the best margin to separate classes in one iteration.

It focuses on attaining the right probability for each output class.

It can be used for linearly separable data.

It works well with high-dimensional data, such as text or image.

Correct

Correct! SVM is unable to provide probability estimates of each class.

9.

Question 9

Suppose you’d like to determine how a model performs on predicting the minimum and maximum temperature for a given day. Which metric is the most appropriate to use?

1 / 1 point

F1 Score

False positives

Root Mean Squared Error

Log Loss

Correct

Correct! Root mean squared error is in the same units as the response vector, so it’s easier to relate information for the regression problem.

1.

Question 1

What is the subfield of computer science that gives "computers the ability to learn without being explicitly programmed"?

1 / 1 point

Information management

Graphics and visual computing

Computational science

Machine learning

Correct

Correct!

2.

Question 2

Which of the following groups are not Machine Learning techniques?

1 / 1 point

Anomaly Detection and Recommendation Systems

Classification and Clustering

Numpy, Scipy, and Scikit-Learn

Correct

Correct! These are Python packages that we use to write machine learning algorithms rather than techniques.

3.

Question 3

When would you use Multiple Linear Regression?

1 / 1 point

When we would like to predict the impacts that weather and temperature have on crop yield.

Predict whether or not a customer switches to another brand based on income, education, etc.

Group genetic markers to identify family ties.

None of the above.

Correct

Correct! We want to predict the impacts of changes in weather and temperature on a continuous target variable.

4.

Question 4

Which of the below is an example of a classification problem?

1 / 1 point

To predict the category to which a customer belongs to.

To predict whether a customer switches to another provider/brand.

To predict whether a customer responds to a particular advertising campaign or not.

All of the above.

Correct

Correct! All of the above can be phrased as a classification problem.

5.

Question 5

Which of the following is an example of Logistic Regression?

1 / 1 point

The odds of a particular individual having a heart attack based on how much they exercise and how much they weigh.

The probability of a borrower defaulting on their mortgage based upon their credit score and age.

The probability of a person purchasing life insurance based on age and income.

All of the above.

Correct

Correct! All of these are examples of logistic regression as they try to predict the probability of a binary response.

9.

Question 9

Suppose you’d like to determine how a model performs on predicting the minimum and maximum temperature for a given day. Which metric is the most appropriate to use?

1 / 1 point

Log Loss

Root Mean Squared Error

F1 Score

False positives

Correct

Correct! Root mean squared error is in the same units as the response vector, so it’s easier to relate information for the regression problem.

1.

Question 1

Which of the following is an example of Machine Learning?

1 / 1 point

Streaming service viewing suggestions.

Websites recommending items to purchase.

Telecommunication companies predicting subscriber retention.

All of the above.

Correct

Correct! All of these are valid examples of tasks that can be accomplished with machine learning.

2.

Question 2

Which of the following is a Machine Learning technique?

1 / 1 point

Clustering

Classification

Regression/Estimation

All of the above

Correct

Correct! All of the above are considered machine learning techniques along with association, anomaly detection, sequence mining, and recommendation systems.

3.

Question 3

In which of the following would you use Multiple Linear Regression?

1 / 1 point

Recommend products to customers based on their demographic characteristics.

Predict whether a customer is likely to repay a loan based on age and income.

Predicting the production of apples in an orchard based on temperature and rainfall.

Predict CO2 emission of a car based on engine size.

Correct

Correct! We use multiple linear regression when there is more than one independent variable for predicting a continuous variable.

4.

Question 4

Which one is not an example of a classification problem?

1 / 1 point

To predict the category to which a customer belongs to.

To predict the amount of money a customer will spend in one year.

To predict whether a customer switches to another provider/brand.

To predict whether a customer responds to a particular advertising campaign or not.

Correct

Correct! The amount of money spent is not a categorical target variable.

5.

Question 5

Which of the following is an example of Logistic Regression?

1 / 1 point

The odds of a particular individual having a heart attack based on how much they exercise and how much they weigh.

The probability of a borrower defaulting on their mortgage based upon their credit score and age.

The probability of a person purchasing life insurance based on age and income.

All of the above.

Correct

Correct! All of these are examples of logistic regression as they try to predict the probability of a binary response.

6.

Question 6

What type of clustering divides the data into non-overlapping subsets without any cluster-internal structure?

1 / 1 point

k-mean clustering

Hierarchical clustering

DBSCAN

None of the above

Correct

Correct! Other algorithms divide data into clusters of varying shapes.

8.

Question 8

What are some advantages of logistic regression over SVM?

1 / 1 point

It can be used for linearly separable data.

It focuses on finding the best margin to separate classes in one iteration.

It focuses on attaining the right probability for each output class.

It works well with high-dimensional data, such as text or image.

Correct

Correct! SVM is unable to provide probability estimates of each class.

10.

Question 10

When do we use regression trees instead of decision trees?

1 / 1 point

When the response is categorical instead of continuous

When the response is continuous instead of categorical

When some of the independent variables are continuous

When all of the independent variables are continuous

Correct

Correct! Regression trees split the data based on features like in decision trees, but the prediction is an average across the data points in that node.

 Final Project Assignment

Upload A File: