American Express App Dev hackathon | Techgig
Requirements:
Please see the jupyter notebook code for understanding how to download the packages and run them.
The jupyter notebook can be easily uploaded on Google Colab and used there for free CPU and analysis. No settings and changes to the code are needed.
Team Name : d2Anubis
Team members : Niharika (1 member only)
Email ID : [email protected]
We have used the following technologies to make the project:
- Twint : To extract data from twitter in large scale
- PySpark : For big data processing of data and data analysis
- Koalas : Its a wrapper on top of pyspark allowing pandas syntax to work with pyspark
- Matplotlib and Seaborn : We used matplotllib and seaborn for plotting plots
- Jupyter notebook : it allows interactive visualization and programming for working on data science projects
- Google Colab : It is provided by Google for working with big datasets allowing high and free RAM and GPU
- NLTK : It is a python package for natural language processing and sentiment analysis
One can run these on his own laptop but we would recommend to use Google Colab as it is fast and free to run the codes there.
Running the code on own laptop might lead to low memory.
Video link can be found in the presentation file. Since the video file was large we have uploaded it on Google drive.
Link to video : https://drive.google.com/drive/folders/11175RZ3wraUAxJq4Jb6MLojvceL4RrY8?usp=sharing