STA 141B Final Project

Analyzing Steam game reviews to determine if there exists a relationship between a game's price and the percentage of positive reviews it receives.

Instructions For Reproduction

Please make sure every file exists in the same folder, otherwise issues may come up.

1. Download this Kaggle dataset and save it as games.csv
2. Run get_appids.py. Make sure to input your Steam API Key here.
3. Run get_reviews.py. Note that this file will take a while to run.
4. Run data_merging_cleaning.py
5. Run levene.py. This file will produce the results obtained in sections 2.2 and 2.3.2 of the paper.
6. Run Price vs. Player Satisfaction.py. This produces Figure 1.
7. Run anova_and_boxplot.py. This produces Figure 2, as well as the results obtained in section 3.2 of the paper.
8. Run free_vs_paid.py. This produced Figure 3.
9. Run tukey.py. This produces Table 4.
   

Alternatively,

1. Download this Kaggle dataset and save it as games.csv
2. Download finalproject.ipynb and run the code there.

Note that the results and figures may not align with the results discussed in the paper due to the fact that the data will update with each API call. The datasets used in the analysis can be found in the Output folder.