This repo contains:
- Description of the project in a PDF
- Three python starter files
- Three test files
- A starter jupyter notebook
- Our csv data combined with API and scaped data as OMDB.csv
- The notebooks to be evaluated are "Greg_notebook_essential" and "Grace_notebook". These will be updated into one for Friday.
We are using OMDB (API) & IMDB (csv) to compare information on movies & TV shows based on their rankings. These are our hypotheses:
- Can actor/actress "x" significantly improve the rating of this movie? (Taking the mean rating of films with actor "x" compared to films of the same genre for the past 5 years without said actor/actress) - z-test
- Do drama films garner a higher rating? - z-test V
- Do the ratings vary between rating platforms? Which one will dictate most what people watch? If statistically different then find out how much by. - ANOVA, z-test
- Are films more popular if released in Winter? As indoor activity! - Number of votes if we can't get revenue/budget (ROI).