KO
|
EN
gitlite — search
Search
#javascript
#python
#hacktoberfest
#react
#ai
#typescript
#llm
#go
#golang
#android
#machine-learning
#rust
#deep-learning
#linux
betas
★ 8
Open GitHub ↗
UW Data 515 Spring 2019 - Final Project
Download README (.md)
Explore Similar Repositories
awesome-BTC-embedded
:
A list of projects using Bitcoin on embedded devices.
spring-cloud-example
:
Example for Spring cloud (netflix OSS, spring cloud)
sign_xcorr
:
audio signal cross correlation using FFT
akaza
:
A cool Whitespace language implementation in Ruby.
jobs
:
people who want typescript jobs, companies that want typescript devs
// repository documentation
Was this content helpful?
★ 0
(0 ratings)
Select Rating:
★
★
★
★
★
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
betas
?
Download (.md)
 ### [](https://travis-ci.org/betas-org/betas) [](https://coveralls.io/github/betas-org/betas?branch=master)      ## Background Our project aims to create a simple and convenient visualization tool, Betas, for data scientists and data analysts to analyze model performance with visualizations in Python. Users can simply run a single line of code to generate custom plots for analyzing a linear regression model with assumptions diagnostics, computing model scores in binary classification, and for evaluating the performance of principal component analysis (PCA) and clustering algorithms. This tool also helps users to fit machine learning models to datasets without a detailed understanding of how the models work. Betas package is pip installable and easy to use by following our example IPython notebooks, in which we are using the Spam dataset and College dataset as demonstration. In addition, we have two interactive web dashboards designed for model diagnostics in linear regression and binary classification. ## Team Members Joel Stremmel Yiming Liu Cathy Jia Mengying Bi Arjun Singh ## Data Data Set 1: The Spam data ([Source](https://web.stanford.edu/~hastie/ElemStatLearn/)) Data Set 2: The Breast Cancer data ([Source](https://github.com/scikit-learn/scikit-learn/tree/master/sklearn/datasets/data)) Data Set 3: The College data ([Source](http://www-bcf.usc.edu/~gareth/ISL/)) Data Set 4: The Auto data ([Source](http://www-bcf.usc.edu/~gareth/ISL/)) ## Software **Programming Languages** [Python](https://www.python.org) **Python Packages** [numpy](http://www.numpy.org) >= 1.13.1 [pandas](https://pandas.pydata.org) >= 0.23.1 [matplotlib](https://matplotlib.org) >= 2.0.2 [seaborn](https://seaborn.pydata.org) >= 0.9.0 [scipy](http://scipy.github.io/devdocs/) <= 1.2.0 [scikit-learn](https://scikit-learn.org) >= 0.20.2 [statsmodels](https://www.statsmodels.org) >= 0.9.0 [dash](https://dash.plot.ly) >= 0.43.0 [bokeh](https://bokeh.pydata.org) >= 1.0.4 ## Structure This package has the following structure. See betas library [documentation](https://github.com/betas-org/betas/blob/master/betas/README.md) for details. ``` betas/ |- betas/ |- README.md |- __init__.py |- binary_score_diagnostics.py |- binary_score_plot.py |- clustering_evaluate.py |- download.js |- pca_evaluate.py |- regression_analysis_plot.py |- regression_diagnostics.py |- setup.cfg |- test_analysis_plot.py |- test_binary_score_plot.py |- test_clustering_evaluate.py |- test_pca_evaluate.py |- data/ |- college.csv |- spam.data.txt |- spam.traintest.txt |- spam_score_label.csv |- dist/ |- betas-v1.3.tar.gz |- docs/ |- Component_Specification.pdf |- Final_Presentation.pdf |- Functional_Specification.pdf |- Project_Summary.pdf |- Technology_Review.pdf |- logo_black.png |- logo_white.png |- examples/ |- demo_regression_analysis_plot.ipynb |- demo_binary_score_plot.ipynb |- demo_clustering_evaluate.ipynb |- demo_pca_evaluate.ipynb |- LICENSE.txt |- README.md |- environment.yml |- requirements.txt |- setup.py ``` ## Installation `pip install betas` ## License Information [MIT License](https://github.com/betas-org/betas/blob/master/LICENSE.txt)
