ASSIGNMENT 13 - NUMERICAL INTEGRATION AND DIFFERENTIATION

Using cross validation in estimating mpg given 4 variables

Metro-Hastings Sampler

Exploring Google's Page Rank

Proving the Central Limit Theorem through Simulation

Using R to perform basic matrix procedures and creating a function to solve a system of equations without the aid of tools in R

Using 100 simulations of an exponential distribution of sample size 30, the distribution of the means and minimums are discussed.

A regression analysis of GNI ~ population growth using data from the World Bank.

A presentation on Problem 7.37 from OpenIntro Statistics

As an example of this process, the `flights` database is used for the migration. R connects to the SQL database (in this case MySQL) converts the data to data frames and exports it into MongoDB, where the new database will live. There is a fairly exact translation from the migration, but it is found that variables are shifted during the process maybe due to the preferences of the order that MongoDB likes to store data. This migration is mainly carried the `RMySQL` and `mongolite` packages. `mongolite` seems to be the new, popular kid on the block (~2015) due to its lightweight and versatile nature; competing packages (at the dawn of `mongolite`) have fallen out of favor due to their overhead or removal from "current CRAN approved packages" because of their instability.

A look at Flipboard and the methods of optimizing UX through recommender systems

This assignment looks at email collections tagged as either "spam" or "ham", i.e., non-spam. and the training methods used in order to establish an appropriate spam filtering method. Three models are used in the training\testing process: simple vector machines (SVM), random forest (TREE) and maximum entropy (MAXENT). It was found that the MAXENT model is the most accurate in predicting spam and should be used in the implementation of a spam filter.

Using the NYTimes API

Creating HTML, json and XML objects and reading them into data frames

Using tidy data principles, transform data and perform analysis with tools form dplyr and tidyr

Normal data distribution.

From a semi-structured text file, regex and R packages are used to create and export a data table

Using regex to ascertain data

Using FEC data, basic tools for statistics, subsetting and plotting are used to analyze committee contributions for the 2016 election

Using presidential election contributions from committees, some of RStudio's basic tools are used to subset the data, provide some basic statistics and visual the data with plotting tools.

Creating user defined functions to calculate the binomial coefficient, i.e. n-choose-r

Using graphical tools in R to display data

Using subsets and altering data