Randy Suarez Rodes's repositories
HackerRank
My submissions to HackerRank
CI_CD_tools
A collection of CI_CD pipelines and tools for multiple Git Providers
Coin-PredaBot
A discord bot to notify crypto metrics
CS6307Project1
Repo for CS6307 Assignment 1 - Relational Data Model
CS6307Project2
Repo for CS6307 Assignment 2 - Big Data Management and Analytics
CS6307Project3
Repo for CS6307 Assignment 3 - Big Data Management and Analytics
Matricial-Distance-for-Cluster-Analysis-of-Amino-Acids
Cluster analysis for side chains in amino-acids. Use of a custom measure needed in R^mĂ—3 to apply cluster analysis methodology. Comparison of several distances for 3- Dimensional structures. Custom matricial similarity measures are proposed. Pioneer approach, quite different from the usual one in the R^p space. Implementation of custom K-means algorithm in Matlab to handle complex 3 dimensional structures.
March_Madness
March Madness tournament bracket predictions using Spark MLlib and tracking results using MLflow
ML_Algorithms
A collection of machine learning algorithm examples and templates in Python and R
Personal_Projects
A space for personal ideas and projects
Poll-Prediction
During each election year, we are inundated with the results of political preference polls. The media presents the results of these polls with little or no discussion of their accuracy. TV news reports typically present a set of poll percentages as if they were the actual population percentages, while newspapers may include a small-font footnote stating that the results have an error of (3-5)%. Such statements are based on the conservative bound on the s.d. of a sample proportion and ignore several issues that can impact the results significantly. This project is intended to examine some of those issues. Note that the percentages for each candidate are not independent, and so confidence intervals for each percentage would not be independent. Suppose that the poll asks respondents how likely they are to vote and then labels each respondent as either likely to vote or not likely to vote. The final poll report is based only on those who are labeled as likely to vote. There are two types of populations to be examined. The first scenario is the preferences of those who claim they will vote but don't vote and those who vote are the same. Another one is the preferences of those who claim they will vote but don't vote and those who vote are not the same.