Movie Data Analysis
This repo holds the code for analyzing a Dataset as part of the IBM Hackchallenge 2018. The same project has been awarded the "The Jury Award" in the competition.
A command line based interface using Python-3 which is capable of asking the query from user in text format or even in Image format and get the answer from the dataset. We’ve used Natural Language Processing and Image processing libraries to achieve this. We have also analyzed the emotions of the film in each year and then could predict the year given the rate of emotion. The solution contains different types of graphs and text outputs to give a holistic comprehensibility to the end user.
Libraries required
- Pytesseract
- Open-cv
- tensorflow
- Pandas
- Numpy
- Matplotlib
- Seaborn
- SciKit-Learn
Note: The file "libraries.exe" which is available in the file "Libraries" from the repository can be used to install all these libraries provided you have "pip" working in your system.
Steps to follow:
- Download the zip file.
- Execute the file "libraries.exe" to install and the required libraries for the Python Code. (Make sure pip is installed in your system.)
- Run the python code without changing the path of datasets.
Once the above steps are done you are good to go.
Cheers :)