Technical Area:
- Knowing about different classification models
- Understand about loading data into CSV and JSON files in order to be formatted for ML algorithms
- Understand about web scraping/crawling and how that data can be used with different metrics
Tools:
- Google Colab
- VSCode
- Numpy/Pandas
- Scikitlearn
Soft skills:
- Learned how to collaborate with teammates and come to a cohesive decision
- Learned a lot through reading articles and watching videos to further understand the material
Highlights:
- Was able to clean my data successfully
- Able to load data into a .csv file and .json
- Learned about some of the classification modules
- Came more comfortable understanding VSCode’s lightweight platform
Tasks:
- Cleaned data correctly
- Understood Bag of Words
- Understood the cosine similarity and the distance metric which was early exposed in the first module
Hurdles/Problem Faced:
- Small bugs and errors that may have taken more time then I’d like
- Steepness of material to get through. Learned from Colin that our own implementation is better and more useful especially in the long run, rather than copying/learning from a template
- Need to work on categorizing and formatting the data to get ready for the recommender system