Need help with RStudio

Read the national GDP file, which records GDP in millions, and count how many countries have a GDP greater than or less than 10,000 million: http://people.terry.uga.edu/rwatson/data/GDP.csv.

library(ggvis)

library(readr)

url <- 'http://people.terry.uga.edu/rwatson/GDP.cvs'

t <- read_delim(url, delim=',')

trowcol <- ggvis(select GDP, country from t where GDP < 10000000 and GDP >10000000)

1. Show on a Google map the office locations in Honduras.

libray(ggplot)

library(ggmap)

library(mapproj)

library(DBI)

conn <- dbConnect(RMySQL::MySQL(), richardwatson.com,

dbname=ClassicModels, user=db1, password=student)

# Google maps requires lon and lat, in that order, to create markers

d <- dbGetQuery(conn,SELECT y(officeLocation) AS lon, x(officeLocation) AS lat FROM Offices;)

# show offices in Honduras

# vary zoom to change the size of the map

map <- get_googlemap(honduras,marker=d,zoom=4)

ggmap(map) + labs(x = Longitude, y = Latitude) + ggtitle(Hondura offices)

2. Show on a Google map the university locations in North Carolina.

libray(ggplot)

library(ggmap)

library(mapproj)

library(DBI)

conn <- dbConnect(RMySQL::MySQL(), richardwatson.com,

dbname=ClassicModels, user=db1, password=student)

# Google maps requires lon and lat, in that order, to create markers

d <- dbGetQuery(conn,SELECT y(universityLocation) AS lon, x(universityLocation) AS lat FROM University;)

# show university locations in North Carolina

# vary zoom to change the size of the map

map <- get_googlemap(NC,marker=d,zoom=4)

ggmap(map) + labs(x = Longitude, y = Latitude) + ggtitle(NC university locations)

3. Show on a Google map the residential communities in Charlotte, NC.

libray(ggplot)

library(ggmap)

library(mapproj)

library(DBI)

conn <- dbConnect(RMySQL::MySQL(), richardwatson.com,

dbname=ClassicModels, user=db1, password=student)

# Google maps requires lon and lat, in that order, to create markers

d <- dbGetQuery(conn,SELECT y(communityLocation) AS lon, x(communityLocation) AS lat FROM Communities;)

# show residential communities in Charlotte,NC

# vary zoom to change the size of the map

map <- get_googlemap(Charlotte,NC,marker=d,zoom=4)

ggmap(map) + labs(x = Longitude, y = Latitude) + ggtitle(Charlotte,NC residential communities)

4. Take the recent annual reports for UPS and convert them to text using an online service, such as http://www.fileformat.info/convert/doc/pdf2txt.htm. Undertake a cluster analysis, identify which reports are similar in nature, and see if you can explain why some reports are in different clusters.

require(ggplot2)

require(ggdendro)

#name the columns for the report's year

colnames(tdm) <- 2008:2012

#remove sparse terms

tdm1 <- removeSparseTerms(tdm, 0.5)

#transpose the matrix

tdmtranspose <- t(tdm1)

cluster = hclust(dist(tdmtranspose),method='centroid')

#get the clustering data

dend <- as.dendrogram(cluster)

#plot the tree

ggdendrogram(dend,rotate=T)

5. Build a topic model for the annual reports.

library(topicmodels)

library(slam)

dim(tdm)

# calculate tf-idf for each term

tfidf <- tapply(dtm$v/row_sums(dtm)[dtm$i], dtm$j, mean) * log2(nDocs(dtm)/col_sums(dtm > 0))

# report dimensions (terms)

dim(tfidf)

# report median to use as cut-off point

median(tfidf)