Clever Classification

Inspiration: Learning new things

What it does: Part 1 (AaronMathewsSimilarity.py) finds similar news articles for each mystery article. Part 2(food review classifier) finds keywords for a given food review from the Amazon Fine Foods dataset.

How we built it: We experimented with different distance functions to calculate similarity between an object and a number of other objects. We then grouped similar objects.

Challenges we ran into: General Debugging, trying to find the best distance function

Accomplishments that we're proud of: Building something

What we learned: K-Nearest Neighbors, API's, Various Distance Functions in Scipy, Basics of dealing with JSON and CSV files

What's next for Clever Classification: Using more sophisticated classification techniques

Built With

bloombergembeddingapi
python
scipy

Updates

Clayton Dumay posted an update — Oct 09, 2022 01:59 PM EDT

Our Guesses:

1- Finances. This article is likely discussing money, the market, and stocks.

2- Financial issues. This article probably deals with some sort of recession. This could be the great recession or the current recession.

3- Diseases. This article is likely discussing the Covid pandemic. This article is likely discussing covid, the vaccine, and the consequences of covid.

4- Political Unrest, War. This article probably deals with some sort of war, possibly something in Africa.

5- Natural Disasters, Climate Change. This article probably deals with climate change and natural disasters associated with it. This article may be discussing forest fires.

Log in or sign up for Devpost to join the conversation.

Aaron Mathews posted an update — Oct 09, 2022 11:42 AM EDT

Our Guesses: 1- Travel. This article probably deals with travelling to certain locations on vacation. 2- Financial issues. This article probably deals with some sort of recession. This could be the great recession or the current recession. 3- Diseases, Flu. This article probably deals with a deadly disease and vaccinations that prevent them. This could be discussing the Covid pandemic. 4- Political Unrest, War. This article probably deals with some sort of war, possibly the Russia-Ukraine conflict. 5- Natural Disasters, Climate Change. This article probably deals with climate change and natural disasters associated with it.

Log in or sign up for Devpost to join the conversation.

Aaron Mathews posted an update — Oct 09, 2022 11:30 AM EDT

The Amazon Fine Food Reviews Dataset is not included due to file size. This can be downloaded from: 'https://www.kaggle.com/datasets/snap/amazon-fine-food-reviews?resource=download' and should be saved as 'Reviews.csv' in the same directory as the rest of the files.

Log in or sign up for Devpost to join the conversation.

Aaron Mathews started this project — Oct 09, 2022 11:28 AM EDT

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.