Ship
Pending review
SO its been a very long time since I wrote a devlog…..I finished my app abt a month and a half ago. So I implemented my ML into the App, fixed a bunch of GUI bugs, and I worked on a gif that animated your simulated asteroids. After that, I tweaked some more GUI bugs, made sure everything was okay and presentable, and then I made my streamlit app public. You can find it on my github.
Devlog 6: Before I used UMAP to reduce dimensions, but when I was unpickling it from joblib into my normal .py scripts, it started to crash my app and scripts because UMAP is not compatible with python 3.13.2 for some reason. I did not want to downgrade my python, so I switched to PCA, which is another dimension reducer mechanism. PCA is fast, linear, and it preserves global variance. After, I start working on integrating my GUI with it. As you know, the plan is to get a current NEO asteroid and input it through the model to see what group it is, so I created that specific script to do that. Based on the means of the cluster groups, I figured out their characteristics, which was needed in order to tell the user what the asteroid group means. I also created a class that plots the new point into the existing PLT plot, which will be shown in the streamlit app. After all this, I thought I was done, but I realized I made a very big mistake. I didn’t analyze my dataset too much, until I started to work on a script that gets the top 5 most similar asteroids. I noticed the 5 asteroids were all the same. When I looked at my dataset, I saw that I had a bunch of duplicate asteroid names, but with different approach dates, so in reality, I only had about 20 unique asteroids. Thus, to mitigate this, I found a new dataset that has over 300k entries, and 30k+ unique asteroids. I made sure I did everything correct when training the unsupervised model. Finally, I once again, integrated the model to my GUI. Now everything looks nice and clean.
#Develog #5….its been a while since my last Devlog. To fix my machine learning model, I used UMAP, which reduces dimensions (features) of my data, which is put it through a K-Means model. K-Means is an unsupervised ML model, meaning it comes up with patterns itself. In this project, it is used to find the different groups of NEOs. After, I began on implementing the model to the recent NEOs. Essentially, when a user clicks on an asteroid in the table, all the relevant data of that NEO will be put into the UMAP, and then predicted by my K-Means.
Devlog #4 -> Working on a machine learning model for website. The model is trying to characterize and group historical NEOs based on their features. It will be used to find which NEOs are closest to the current NEO. Thus far, the model has not being doing good, as it can’t group the asteroids in the desired way.
Devlog 3: I had to debug the issue with .txt file, as it wasn’t updating after I clicked an asteroid name. I ended up reverting to a previous commit.
Develog #2: Working on fixing GUI and makign code more efficient.
Working on fixing gui
