Python

Programming with Python Final Project 2021 Dr. Kamesam

1

1. Conduct your analysis in a notebook. Submit your notebook with all the code and output.

2. Start with a cell of markdown and include your name. Notebook filename must have your name.

3. Make your work look professional. All variable names should be meaningful, charts have titles etc.

4. Write down your answer (in markdown) to questions where results display is not sufficient.

You may use more than one tool/chart to answer a question.

games.csv has reviews of several computer games. Two important columns in each review are the score,

and the score_phrase (rating) given by the user/reviewer. Your analysis is to summarize these two

columns and relate them to the other attributes of the game. The reviews are from users in the USA as

well as abroad (location)

1. Read and inspect the data carefully to make sure you understand the data.

2. Are there any missing values? Explain your answer.

3. Rename columns such that the column names are short, have no spaces in the name, and are all

in the same case. In particular, rename score_phrase as rating , and editor choice as ed_choice

4. How many reviews are there?

5. How many games were reviewed?

6. How many of the games that are reviewed won editor choice award?

7. What is the title (game) that got the maximum number of reviews?

8. Calculate and show how many games are of each genre.

9. What is the distribution of the score given by reviewers? Create a visual (chart), draw your

conclusions and write them down.

10. Create a table and a chart to show the distribution of rating by the reviewers. Draw your

conclusions and write them down.

11. What is the average score in each rating? What are your observations?

12. Create a visual to show the relation between editor's choice and score received by the game.

What are your observations?

13. Is there any relation between rating by reviewers, and ed_choice? Explain your answer.

14. Some of the reviews rated the game as a masterpiece. What is the genre (of games) that got the

maximum number of masterpiece ratings?

15. Within each rating, is the score all over the place, or is there a clear pattern?

16. Determine if there is a significant difference in the scores by location (USA vs abroad). Create a

table to show the average score within each rating and location. What is your conclusion?

17. Over the years, has the average score stayed steady, or is there a trend? Create a visual to

answer the question.

Include the following lines of code in the last cell of your notebook and execute before you submit.