aaronnhorvitz Goto Github PK
Name: Aaron Horvitz
Type: User
Name: Aaron Horvitz
Type: User
This is a modification of Scikit-Learn's LASSO for Adaptive LASSO to use for feature selection.
This is the first Python course I wrote for AIA Global's members (Another updated course is available.)
Here is a quick run-through on creating a linear regression model using two popular variable selection/shrinkage methods (LASSO and Elastic-Net), followed by backward stepwise selection to arrive at a parsimonious model.
This tests various classifier models on binary target data to see which one maximizes performance. It then returns all the models, model performance statistics as well the ROC curves and Precision Recall plots, as well performance plots against the number of estimators used.
COVID-19 Forecast With Exogenous Variables
Data and code behind the articles and graphics at FiveThirtyEight
Introductory Course for Data Science Training
FECDataConnect is a project aimed at extracting data from the Federal Election Commission (FEC) and integrating it into a MariaDB database. This ETL pipeline ensures that the data remains fresh and accessible for further analysis.
This is my capstone project. The full presentation can be found in the uploaded PDF file. I created a model that calculates the ROI and predicts individual donations to election campaigns for the US House of Representatives using data reported to the Federal Election Commission (FEC).
How to find stock and commodity price trends using LOWESS (Locally Weighted Scatterplot Smoothing)
Generalized additive model with pairwise interactions
A simple implementation of the LOESS algorithm using numpy
Code for common data analytics projects
This is my capstone project. I created a model that calculates the ROI and predicts individual donations to election campaigns for the US House of Representatives using data reported to the Federal Election Commission (FEC).
This is for anyone who would like to quickly read the COVID-19 time series data into a Pandas dataframe inside a Jupyter Notebook. I posted the Python code on Github in a Jupyter Notebook. The raw data is updated daily by Johns Hopkins University. Hopefully, this helps.
R repo
These are just small pieces of code that may help make your life easier.
This is a simple notebook that will download stock prices for you and display them on a chart.
This code provides a series of diagnostic plots for time series analysis. These include ACF and PACF plots, predicted vs actual, residual plots, differenced residual plots, and many more.
This code provides a series of diagnostic plots for time series analysis. These include ACF and PACF plots, predicted vs actual, residual plots, differenced residual plots, and many more.
This a test for stationarity. It takes the original data, differenced data, plots both and performs a Dickey-Fuller Test
This is just a quick function to produce a lowess smoother.
Code to upsample binary classification data when you have a rare event problem.
Here is a Jupyter Notebook that reads the polling data for the 2020 Presidential election published by 538 on Github, sorts through it, and plots the polling results and trends at the national and state levels. Have fun!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.