Added unsupervised learning classes and Streamlit interactive platform #242
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Created 1D CNN model with transformer. Test loss was around 0.21.
CNN training and evaluation script
Making dataset available for all users
Changed output of method so that it returns axis and figure, rather than directly printing the spectral plot
Created outlier detection model which allows for different types of dimensionality reduction, clustering, and data visualization.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Created an interactive Streamlit website where TelescopeML users can design their outlier detection model for astronomical datasets. Currently, this website only supports the brown dwarf dataset which is part of the tutorial notebooks.
Users can decide whether to use t-SNE or PCA for dimensionality reduction and specify the number of dimensions the data is being reduced to. Then, they can decide whether to use DB-Scan or K-means for clustering, and specify parameters such as how many clusters are allowed.
Then, they can see the spectral distribution of outliers vs. non-outliers for any of the 4 output values in the brown dwarf dataset, while specifying ranges for the other output values for filtering ourposes.
BONUS section: Added a 1D CNN and transformer script and existing Keras model for future use and training.