Page 247 - Ai Book - 10

4. What type of file extension is commonly used for datasets in tabular form?

a. .txt b. .csv
c. .zip d. .sql
5. What is the primary use of the ‘Why’ canvas in the AI project cycle?

a. Identifying stakeholders

b. Understanding the purpose and value of the project
c. Visualizing data
d. Creating regression models

6. Which type of analysis focuses on understanding the underlying structure of the data?
a. Descriptive Analysis b. Predictive Analysis

c. Diagnostic Analysis d. Exploratory Data Analysis

B. Fill in the blanks.
1. ________________ is the stage where we identify the stakeholders or team working on an AI project.

2. The goal of stakeholders in the Mess scenario is to predict the quantity of food estimation to reduce the
considerable amount of ________________.

3. Data Acquisition is crucial, and the data acquired should be ________________, reliable, and correct to
avoid conflicts in the project.
4. ________________ is a necessary step before training or modeling a system.
5. In the modeling stage, a regression model is used, which is a supervised learning model that works on
________________ data.
6. The evaluation phase in the AI project life cycle involves feeding data into the trained model, model
functioning, prediction, testing, and checking accuracy before moving to the ________________ stage.

7. ________________ is an archive file format used to collect multiple data files together into a single file,
compressing them to use less storage space.

8. In Python for Data Science, ________________ is the fundamental package for scientific computing,
featuring a powerful N-dimensional array object and useful linear algebra capabilities.

C. State ‘T’ for True or ‘F’ for False statements.
1. The “Who” block in the 4 W’s canvas helps identify stakeholders or teams involved in an AI project.

2. Data Acquisition is an unimportant stage in the AI project life cycle.
3. The goal of stakeholders in the Mess scenario is to increase the quantity of leftover food.

4. Regression is a supervised learning model that works with categorical data.
5. In the modeling stage, the dataset is divided into a 30:70 ratio for training and testing, respectively.

6. CSV is an acronym for Comma Separated Variables, which allows data to be saved in a
tabular format.
7. Pandas is a Python package for data science that offers only one main structure, either
Series or DataFrame.

8. Matplotlib is a popular Python package used for data visualization, written in Java.

121
121