Project: Wikidata, Movies, and Success
The datasets was gathered from CMPT 353 cluster and The Movie Database.
Overview: For this project, we wanted to do data exploration relating to movies, its success and trends. The data we gathered were pulled from various sources such as the CMPT 353 cluster and the Movie Database, which was cleaned and refined to tackle our problem. We used statistical tests, machine learning and data visualization techniques learned from the course. There were a lot of lessons learned throughout this project as we discovered that some conclusions were inconclusive or limited. Lastly, there were limitations with our datasets.
Libraries:
- Scikit Learn
- Pandas
- NumPy
- Matplotlib
- Scipy
- Rest of the libraries came with Anaconda
Order of Execution:
- ETL.ipynb
- Movie_Success_Correlation.ipynb
- trends.ipynb
- EDA_ML.ipynb
Expected Ouput: Since we used jupyter notebook, all of the expected outputs are there. The notebooks contains ouputs and do output some ETL'd csv files