Đề Thi FE AID301c - SP26 - FE

[adminadmin is verified member.]

Học kỳ

SP2026

Thời Gian

9/5/26

Loại tài liệu

FE

AID301c SP26 FE

1. (Choose 1 answer)
What is the purpose of the classification_report in sklearn?
A. To visualize data
B. To summarize model performance
C. To preprocess data
D. To train a model

2. (Choose 1 answer)
In the script example-spark-submit.sh, what does the #!/bin/bash line indicate?
A. It specifies the script's name
B. It indicates the script is written in Python
C. It tells the system to use the Bash shell to execute the script
D. It is a comment and has no effect

3. (Choose 1 answer)
In the context of NLP, what does sentiment analysis refer to?
A. Analyzing the structure of sentences
B. Determining the emotional tone behind a series of words
C. Translating text from one language to another
D. Summarizing large documents

4. (Choose 3 answers)
Thinking with the lens of the scientific process, what would your next steps be if you wanted to decide where to open the next store for your sled business?
A. Start pulling sales and other data to create a business viability assessment for Vermont
B. Gather more data and repeat the snowfall experiment
C. Gather different data say snowfall by county and repeat the experiment
D. Start a business viability assessment for all three states

5. (Choose 1 answer)
Processing the corpus with the provided lemmatize_document reduces the total number of tokens to what percentage of the original?
A. 10-15%
B. 20-35%
C. 45-50%
D. 70-75%
E. 85-95%

6. (Choose 1 answer)
What is the first step in setting up the Watson Developer Cloud Python SDK?
A. Install the SDK
B. Create an IBM Cloud account
C. Create a resource for Natural Language Understanding
D. Download the tutorial files

7. (Choose 1 answer)
When you worked on model deployment case study, which modification to the ALS algorithm had the largest effect on model performance?
A. The explicit training vs implicit training comparison
B. The lambda or regularization parameter
C. The epsilon or scale parameter
D. The l1 vs l2 comparison

8. (Choose 1 answer)
When you compiled the JSON files into a single DataFrame or NumPy array, about how many days did the entire range of dates span?
A. 400
B. 450
C. 500
D. 600
E. 650

9. (Choose 1 answer)
Which library in Python is commonly used for reading and writing CSV files?
A. NumPy
B. Matplotlib
C. Pandas
D. SciPy

10. (Choose 1 answer)
What is a poisoning attack?
A. An attack that occurs during model deployment
B. An attack that injects malicious data into the training set
C. An attack that modifies the model's architecture
D. An attack that occurs only at test time

11. (Choose 1 answer)
Which Python package can be used to estimate test coverage?
A. unittest
B. coverage
C. pytest
D. flask

12. (Choose 1 answer)
What is the primary purpose of documenting your data before starting a project?
A. To impress stakeholders
B. To streamline the modeling process and ensure data quality
C. To increase project costs
D. To avoid using Python

13. (Choose 1 answer)
What is a common issue with using accuracy as a metric for imbalanced classes?
A. It is always accurate.
B. It can be misleading.
C. It is the only metric available.
D. It does not consider false positives.

14. (Choose 1 answer)
The decision tree base models in random forests individually have high bias and low variance.
A. True
B. False

15. (Choose 1 answer)
Which country had the most total revenue when you summed across all purchases?
A. Singapore
B. United Kingdom
C. USA
D. EIRE
E. Germany

16. (Choose 1 answer)
Which of the following is NOT a component of the confusion matrix?
A. True Negatives (TN)
B. False Positives (FP)
C. True Positives (TP)
D. Average Score (AS)
E. False Negatives (FN)

17. (Choose 1 answer)
Docker containers run a private file system that is isolated from the host and other containers. What is the suggested way to access notebooks and scripts from within the container?
A. tmpfs mount
B. use a named pipe
C. bind mounts
D. GitHub
E. volumes

18. (Choose 1 answer)
When you use Watson Services like Watson Natural Language Understanding via the Python SDK, what are the three items that need to be saved? These items are generally saved on a local machine and included in scripts and notebooks as imported variables.
A. service version, service API key, service JSON map
B. service URL, service JSON map, service API key
C. service API key, service version, service URL
D. service version, service IAMAuthenticator, service URL
E. service API key, service URL, service IAMAuthenticator

19. (Choose 1 answer)
For given input lists: a,b,c and 1,2,3 Create a dictionary from two input lists
A. def make_dict(lst1,lst2): res = {} for key,value in zip(lst1,lst2): res[key]= value return res
B. def make_dict(lst1,lst2): res = {} res[lst1]= lst2 return res
C. def make_dict(lst1,lst2): res = {} for key,value in (lst1,lst2): res[key]= value return res
D. def make_dict(lst1,lst2): res = [] for key,value in zip(lst1,lst2): res[key]= value return res

20. (Choose 1 answer)
What is the purpose of kubectl in kubernetes?
A. Automatic logging of requests and responses
B. A tool that makes it easy to run a single-node cluster locally
C. The primary node agent on each node, responsible for the processes running on that machine
D. The CLI for communicating with the kubernetes cluster

21. (Choose 1 answer)
Which of the following is the least valid statement when it comes to dashboards?
A. Dashboards are an easy way to share summaries and findings
B. Dashboards have interactive functionality that helps create a rich experience for the user
C. Dashboards are generally used after serveral iterations of the AI workflow
D. Dashboards are quick way to create portable simple plots
E. Dashboards can be used to tell the story of investigative visualizations

22. (Choose 1 answer)
What is the first stage of the design thinking process?
A. Ideate
B. Empathize
C. Prototype
D. Test

23. (Choose 1 answer)
Which of the following is NOT a factor that affects the time spent on data cleaning?
A. Team experience
B. Data quality
C. Project requirements
D. Company size

24. (Choose 1 answer)
What is the community package of the Docker Engine called?
A. docker-io
B. docker-ce
C. docker-compose
D. docker-toolbox

25. (Choose 2 answers)
Sparse matrices can be useful as a target destination for ETL, but what are the main caveats (choose one or more)?
A. You cannot convert directly from a numpy array to any of the scipy sparse matrices
B. NumPy linear algebra functions generally cannot be called directly
C. Saving to disk is not possible directly from a scipy sparse format
D. The train test splits need to be performed by hand with scipy sparse matrices
E. It is difficult to print to screen scipy sparse matrices directly

26. (Choose 1 answer)
There are many ways to carry out statistical inference. Which one method of the following is NOT used to compute estimates in the context of statistical inference.
A. Null Hypothesis Significance Testing (NHST)
B. Maximum Likelihood Estimation (MLE)
C. Markov Chain Monte Carlo (MCMC)
D. Expectation Maximization (EM)
E. Simulation via Permutations

27. (Choose 1 answer)
What does the term "trunk" refer to in the context of Continuous Integration?
A. A type of software bug
B. The main branch of code where all changes are merged
C. A deployment strategy
D. A testing framework

28. (Choose 1 answer)
Why is granular data preferred over summary level data?
A. It is easier to collect
B. It allows for more detailed analysis
C. It takes less time to process
D. It is more visually appealing

29. (Choose 1 answer)
When embarking on a data science project, why do you ultimately want to format your data so that it can be housed in something like a Pandas DataFrame or NumPy Array?
A. DataFrames/Arrays most closely resemble tables in relational databases.
B. DataFrames/Arrays are the only structures in Python capable of holding significant amounts of data.
C. Nearly all modeling algorithms take input data in a tabular format analogous to format of DataFrames/Arrays.
D. All of the answers

30. (Choose 1 answer)
Which process model is known for its open standard and has been around since 1996?
A. OSEMN
B. CRISP-DM
C. Design Thinking
D. Agile

31. (Choose 1 answer)
What is a key principle of design thinking mentioned in the course?
A. Data collection
B. Observation and Reflection
C. Rapid prototyping
D. User testing

32. (Choose 1 answer)
Which method is recommended for handling missing values in numerical data?
A. Convert missing values to a flag
B. Use imputation techniques
C. Delete the entire dataset
D. Replace with a random value

33. (Choose 1 answer)
Which of the following is a key aspect of applying data transformations?
A. Data collection
B. Iteration
C. Data visualization
D. Data storage

34. (Choose 1 answer)
What will the management team want to know after the sales data is released?
A. The number of products sold
B. If the teams are well-optimized based on historical sales data
C. The marketing budget for each team
D. The demographics of the customers

35. (Choose 1 answer)
What is the primary purpose of dimensionality reduction in data science?
A. To increase the number of features
B. To simplify models and reduce computation time
C. To eliminate all data points
D. To create more complex models

36. (Choose 1 answer)
In the context of the AI workflow presented in these materials which of the following is not an example of a valid feedback loop?
A. Trying different data transformations on a given model
B. Returning to the data collection stage from transformations to reduce the number of transforms
C. Performing EDA on the data after a model has been deployed and data have been logged
D. Moving from the business opportunity and data collection to model iteration
E. Returning to discuss the business opportunity after a model has been deployed

37. (Choose 1 answer)
What is a key reason for using existing NLP APIs instead of building models from scratch?
A. They are always more accurate
B. They require less time and resources
C. They are easier to understand
D. They eliminate the need for data

38. (Choose 1 answer)
Which of the following is a common challenge when optimizing code for machine learning models?
A. Lack of available data
B. Difficulty in improving training time for large models
C. Inability to use multiple GPUs
D. Limited programming languages available

39. (Choose 1 answer)
If you have data with a large number of features and you are sure that it will take some time to train and tune the model, which approach is LEAST likely to result in a speed improvement during grid-searching?
A. In your pipeline use variance thresholding to limit the number of features
B. Use the Shuffle and split form of cross-validation
C. Use a randomized grid search form of cross validation
D. Randomly subset the data
E. Use PCA to reduce the dimensionality of the data before training

40. (Choose 1 answer)
Which Python package supports spawning processes for code optimization?
A. threading
B. subprocess
C. multiprocessing
D. numpy

41. (Choose 1 answer)
Which of the following neural network architectures are most-commonly used for time-series analysis?
A. Multi-layer perceptron
B. Recurrent neural networks
C. Transfer learning
D. Convolutional neural network
E. Autoencoders

42. (Choose 1 answer)
A decision tree classifier is useful as a model for the AAVAIL subscriber churn data.
A. True
B. False

43. (Choose 1 answer)
What is the purpose of profiling in code optimization?
A. To write new algorithms from scratch
B. To identify which parts of the code are bottlenecks
C. To increase the number of processor cores
D. To reduce the amount of data used

44. (Choose 1 answer)
What type of data structures are used as standardized input to the interfaces in scikit-learn?
A. Lists and dictionaries
B. DataFrames and Series
C. NumPy arrays and SciPy sparse matrices
D. Strings and tuples

45. (Choose 1 answer)
Which command-line tool is used to interact with the Kubernetes API?
A. Kubelet
B. Kube CTL
C. Docker
D. Helm

46. (Choose 1 answer)
A Kubernetes pod can contain multiple kubernetes deployments
A. True
B. False

47. (Choose 1 answer)
Docker images are the basis of containers. It is possible to pull an image from the registry and ask the Docker client to run a container based on that image. Some images are official while many others are user defined
A. True
B. False

48. (Choose 1 answer)
Which of the following classifiers is inherently designed for multiclass classification?
A. Linear Regression
B. Naive Bayes
C. K-Means Clustering
D. Decision Trees (in binary mode)

49. (Choose 1 answer)
The.fit_transform method corresponds to which scikit-learn interface(s)?
A. Transformer, Estimator, Predictor
B. Transformer, Estimator
C. Estimator, Predictor
D. Transformer
E. Transformer, Predictor

50. (Choose 1 answer)
Which command is used to install the Watson Developer Cloud Python SDK?
A. pip install ibm-watson
B. pip install --upgrade ibm-watson
C. install ibm-watson
D. upgrade ibm-watson