ML Checkpoint 2

A data scientist wants to visualize the correlation between features in their dataset. What tool(s) can they use to visualize a heatmap for a correlation matrix?

• Pandas

• Numpy

• Scikitlearn

• Seaborn

You are preprocessing a dataset that includes categorical features. You want to determine which categories of particular features are most common in your dataset. Which basic descriptive statistic could you use?

• Mode

• Median

• Standard Deviation

• Mean

You've plotted the correlation matrix of your dataset's features and realized that two of the features present a high negative correlation (-0.95). What should you do?

• Do nothing because correlated features won't affect the model performance

• Do nothing as the correlation is not positive

• Remove both features

• Remove one of the features

You are in charge of preprocessing the data your publishing company wants to use for a new ML model they’re building, which aims to predict the influence an academic journal will have in its field. The preprocessing step is necessary to prepare the data for model training.

What type of issue with the data might you encounter during this preprocessing phase. (Select TWO.)

• Outliers

• Overfit data

• Missing values

• Residuals

• Insufficient batch size

A Machine Learning Engineer is creating and preparing data for a linear regression model. However, while preparing the data, the Engineer notices that about 20% of the numerical data contains missing values in the same two columns. The shape of the data is 500 rows by 4 columns, including the target column.

How can the Engineer handle the missing values in the data? (Select TWO.)

• Remove the rows containing the missing values

• Remove the columns containing the missing values

• Fill the missing values with mean of the column

• Impute the missing values using regression

• Add regularization to the model

A Data Scientist created a correlation matrix between nine variables and the target variable. The correlation coefficient between two of the numerical variables, variable 1 and variable 5, is -0.95. How should the Data Scientist interpret the correlation coefficient?

• As variable 1 increases, variable 5 increases

• As variable 1 increases, variable 5 decreases

• Variable 1 does not have any influence on variable 5

• The data is not sufficient to make a well-informed interpretation

An advertising and analytics company uses machine learning to predict user response to online advertisements using a custom XGBoost model. The company wants to improve its ML pipeline by porting its training and inference code, to Amazon SageMaker, and do so with minimal changes to the existing code.

How should the company set up this new pipeline?

• Use the Amazon pre-built R container option and port the existing code over to the container. Register the container in Amazon Elastic Container Registry (Amazon ECR). Finally, run the training and inference jobs using this container.

• Use Amazon in-built algorithms to run their training and inference jobs.

• Use the Build Your Own Container (BYOC) Amazon SageMaker option. Create a new Docker container with the existing code. Register the container in Amazon Elastic Container Registry (ECR). Finally, run the training and inference jobs using this container.

• Create a new Amazon SageMaker notebook instance. Copy the existing code into an Amazon SageMaker notebook. Then, run the pipeline from this notebook.

An ML engineer at a text analytics startup wants to develop a text classification model. The engineer collected large amounts of data to develop a supervised text classification model. The engineer is getting 99% accuracy on the dataset but when the model is deployed to production, it performs significantly worse.

What is the most likely cause of this?

• The engineer did not correctly deploy the model to production

• The engineer did not split the data to validate the model on unseen data

• The engineer did not use the right machine learning algorithm for this use case

• The engineer did not scale the data before training

For a classification problem, what does the loss function measure?

• A loss function measures the steps you need to take to reach the optimal point

• A loss function measures how accurate your prediction is with respect to the true values

• A loss function calculates the iterations that you will take to reach your goal

• A loss function calculates the gradients of the weights for a particular iteration

Gradient Descent is an important optimization method. Which one of the following is TRUE about the gradient descent method? (Select THREE)

• It can involve multiple iterations

• It uses learning rate to multiply the effect of gradients

• It uses a batch of training data points to calculate its next step

• It is more computationally efficient to use for large data sets

• It tries to find the minimum of a loss function