dgrapov

#get linear model residuals
#' @import dplyr
#' @export
dave_lm_adjust<-function(data,formula,test_vars,adjust=TRUE,progress=TRUE){
  
  if (progress == TRUE){ pb <- txtProgressBar(min = 0, max = ncol(data), style = 3)} else {pb<-NULL}
  
  out <- lapply(1:length(test_vars), function(i) {
    if (progress == TRUE) {
      setTxtProgressBar(pb, i)

dgrapov

DATA SCIENCE EXERCISE

The following challenge requires the beer reviews data set called beer_reviews.csv. This data set can be downloaded from the following site: https://data.world/socialmediadata/beeradvocate . Note you can create a free temporary account to download this .csv.

Questions to answer using this data:
Which brewery produces the strongest beers by ABV%?
If you had to pick 3 beers to recommend using only this data, which would you pick?
Which of the factors (aroma, taste, appearance, palette) are most important in determining the overall quality of a beer?

Additional math/coding question unrelated to the data:

dgrapov

> in
Error: unexpected 'in' in "in"

dgrapov

# Basic PCA example
# use www.createdatasol.com for 
# an advanced user interface 

#required packages for plotting
library(ggplot2)
library(ggrepel)

#load data
data<-read.csv('~/Sampledata.csv', 

dgrapov

#initialize
library(shiny)
library(ggplot2)
library(purrr)
library(dplyr)


#example data
data(iris)

dgrapov

#' @title fast_tanimoto 
#' @param mat matrix or data frame of numeric values
#' @param output 'matrix' (default) or 'edge list' (non-redundant and undirected)
#' @param progress TRUE, show progress
#' @imports reshape2
fast_tanimoto<-function(mat,output='matrix',progress=TRUE){
  mat[is.na(mat)]<-0 
  
  #scoring function
  score<-function(x){sum(x==2)/sum(x>0)}

dgrapov

#plotly box or lasso select linked to 
# DT data table
# using Wage data
# the out group: is sex:Male, region:Middle Atlantic +


library(ggplot2)
library(plotly)
library(dplyr) 
library(ISLR) 

dgrapov

#SOM example using wines data set
library(kohonen)
data(wines)
set.seed(7)

#create SOM grid
sommap <- som(scale(wines), grid = somgrid(2, 2, "hexagonal"))

## use hierarchical clustering to cluster the codebook vectors
groups<-3

dgrapov

library(reshape2)

gen.mat.to.edge.list<-function(mat,symmetric=TRUE,diagonal=FALSE,text=FALSE){
	#create edge list from matrix
	# if symmetric duplicates are removed
	mat<-as.matrix(mat)
	id<-is.na(mat) # used to allow missing
	mat[id]<-"nna"
	if(symmetric){mat[lower.tri(mat)]<-"na"} # use to allow missing values
	if(!diagonal){diag(mat)<-"na"}

dgrapov

#R code, testing RECA with the iris data
library(RECA)  

#test data
data(iris)
x<-iris[,-5] 
y<-iris$Species

#similar groups (species) in each chunk (n=3)
chunksvec<-as.numeric(y)