In the files that can be found along with this Readme you can find information about wether it is possible to predict the next "Big-Hit" genre for video games using statistical analysis.
There are four important places:
-
The first 2 important files are the "data" folder containing the original datasets and the SDA-Gen-Data.ipynb, which is needed to format the two (vgsales.csv and Video_games_Sales_as_at_22_Dec_2016.csv) different data-sets) into one csv file.
-
After this we executed some general analysis over the newly generated data to get an indication of how we could use this data. This can be found in the Overview_of_the_data.ipynb file.
-
Secondly the main file that utilizes this generated data is SDA-BigHits.ipynb. This file contains all the analyses about the data and the several ways in which we implemented statistical analysis methods to try to predict the next big hit genre.
-
Finally there are two folders left "Documenten" and "Picture plots" and one file "Extra-Info.ipynb".
- "Documenten" contains the files about our project plan and our presentation about the project.
- "Picture plots" contains pictures of several important plots, which were used in the presentation.
- "Extra-Info.ipynb" contains some additional plots that weren't added to the BigHits notebook that didn't lead to a huge conclusion and it contains some duplicate plots from the BigHits notebook.
- First run everything in the SDA-Gen-Data.ipynb notebook.
- Secondly run everything in the Overview_of_the_data.ipynb and Extra-Info.ipynb. These notebooks contain more information, which could lead to a more accurate/broad view. Also generates Overview_of_the_data.ipynb files which are used in the main file.
- Lastly run everything in the SDA-BigHits.ipynb notebook, which will then generate all our plots and our analyses, with our most important findings with respect to our main question.