Apple_Persons_Locations
sundeep
November 27, 2016
rm(list=ls())
Sys.setenv(JAVA_HOME='C:\\Program Files\\Java\\jre1.8.0_66') # for 64-bit
install.packages("rJava",repos="http://cran.rstudio.com/")## Installing package into 'C:/Users/sundeep/Documents/R/win-library/3.3'
## (as 'lib' is unspecified)## package 'rJava' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Public\Documents\Wondershare\CreatorTemp\Rtmpgdz4v1\downloaded_packageslibrary(rvest)## Loading required package: xml2library(NLP)
install.packages("openNLP",repos="http://cran.rstudio.com/")## Installing package into 'C:/Users/sundeep/Documents/R/win-library/3.3'
## (as 'lib' is unspecified)## package 'openNLP' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Public\Documents\Wondershare\CreatorTemp\Rtmpgdz4v1\downloaded_packagesinstall.packages("rworldxtra",repos="http://cran.rstudio.com/")## Installing package into 'C:/Users/sundeep/Documents/R/win-library/3.3'
## (as 'lib' is unspecified)## package 'rworldxtra' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Public\Documents\Wondershare\CreatorTemp\Rtmpgdz4v1\downloaded_packageslibrary(rworldxtra)## Loading required package: splibrary(openNLP)
install.packages("ggmap",repos="http://cran.rstudio.com/")## Installing package into 'C:/Users/sundeep/Documents/R/win-library/3.3'
## (as 'lib' is unspecified)## package 'ggmap' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Public\Documents\Wondershare\CreatorTemp\Rtmpgdz4v1\downloaded_packageslibrary(ggmap)## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following object is masked from 'package:NLP':
##
## annotateinstall.packages("rworldmap",repos="http://cran.rstudio.com/")## Installing package into 'C:/Users/sundeep/Documents/R/win-library/3.3'
## (as 'lib' is unspecified)## package 'rworldmap' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Public\Documents\Wondershare\CreatorTemp\Rtmpgdz4v1\downloaded_packageslibrary(rworldmap)## ### Welcome to rworldmap ##### For a short introduction type : vignette('rworldmap')Read Wiki Page
page = read_html('https://en.wikipedia.org/wiki/Apple_Inc.')
text = html_text(html_nodes(page,'p'))
text = text[text != ""]
text = gsub("\\[[0-9]]|\\[[0-9][0-9]]|\\[[0-9][0-9][0-9]]","",text) # removing refrences [101] typeMake one complete document
text = paste(text,collapse = " ")
text = as.String(text)
t1 = Sys.time()
sent_annot = Maxent_Sent_Token_Annotator()
word_annot = Maxent_Word_Token_Annotator()
loc_annot = Maxent_Entity_Annotator(kind = "location")
Person_annot = Maxent_Entity_Annotator(kind = "person")
Person_annot## An annotator inheriting from classes
## Simple_Entity_Annotator Annotator
## with description
## Computes entity annotations using the Apache OpenNLP Maxent name
## finder employing the default model for language 'en' and kind
## 'person'.annot.l1 = NLP::annotate(text, list(sent_annot,word_annot,loc_annot,Person_annot))Retrieve locations and persons
k <- sapply(annot.l1$features, `[[`, "kind")
## retrieve the locations on the page
apple_locations = text[annot.l1[k == "location"]]
## Retrieve persons names on the page
Persons= text[annot.l1[k == "person"]]List the persons
Persons## [1] "Mac" "Mac App Store"
## [3] "Apple Music" "Steve Jobs"
## [5] "Steve Wozniak" "Ronald Wayne"
## [7] "Apple Inc." "115,000"
## [9] "Steve Jobs" "Steve Wozniak"
## [11] "Ronald Wayne" "RAM"
## [13] "Wayne" "Mike Markkula"
## [15] "Ridley Scott" "John Sculley"
## [17] "John Sculley" "Michael Spindler"
## [19] "Gil Amelio" "Mac OS"
## [21] "Gershwin" "Steve Jobs"
## [23] "Jonathan Ive" "Mac OS X"
## [25] "Mac OS" "Mac OS"
## [27] "Intel-based Mac" "Mac"
## [29] "Mac Pro" "Mac OS X"
## [31] "Michael Dell" "EMI"
## [33] "Mac OS X Lion" "Mac OS X."
## [35] "Apple" "Tim Cook"
## [37] "Cook" "Andrea Jung"
## [39] "Arthur" "Steve Jobs"
## [41] "Phil Schiller" "Mac OS"
## [43] "Siri" "Mac Mini"
## [45] "Tim Cook" "Cook"
## [47] "Paul Deneve" "Yves Saint Laurent"
## [49] "Tim Cook" "Angela Ahrendts"
## [51] "Randall Stephenson" "Edward Snowden NSA"
## [53] "Cook" "Jimmy Iovine"
## [55] "Anand Lal Shimpi" "Paul Hunter"
## [57] "James Vincent" "Magic Mouse"
## [59] "Magic Trackpad" "Magic Keyboard"
## [61] "Steve Jobs" "Mac OS X"
## [63] "Mac OS" "Jonathan Ive"
## [65] "Logic Pro" "Johnson Controls"
## [67] "Steve Jobs" "Ron Wayne"
## [69] "Isaac Newton" "Rob Janoff"
## [71] "Alan Turing" "Steve Jobs"
## [73] "Steve Wozniak" "Newton"
## [75] "Guy Kawasaki" "John Sculley"
## [77] "Jonathan Ive" "SixtyEight Research"
## [79] "Norman Foster." "Bill Atkinson"
## [81] "Capps" "Rod Holt,Alan Kay"
## [83] "Guy Kawasaki,Al Alcorn" "Don Norman"
## [85] "Page" "Steve Wozniak"
## [87] "Ron Johnson<U+0097>Senior" "Cook"
## [89] "Scott Forstall" "Thomas Ricker"
## [91] "Tim Kobe" "Steven Dowling"
## [93] "Silver" "Lisa P. Jackson"
## [95] "Tim Cook" "Greenpeace"
## [97] "115,000" "George Osborne"
## [99] "Christian Kern"List the locations
apple_locations## [1] "California" "United States"
## [3] "Ireland" "Macintosh"
## [5] "Microsoft" "Key"
## [7] "Virginia" "California"
## [9] "Tokyo" "Paris"
## [11] "France" "Cisco"
## [13] "Silicon Valley" "New York City"
## [15] "India" "India"
## [17] "India" "Silicon Valley-based"
## [19] "Tel Aviv." "Turkey"
## [21] "Ankara" "Turkey"
## [23] "Istanbul" "Tokyo"
## [25] "Japan" "Tokyo"
## [27] "India" "San Jose"
## [29] "Magic Mouse" "Magic Trackpad"
## [31] "Magic Keyboard" "3G"
## [33] "Japan" "Sydney"
## [35] "Herald" "California"
## [37] "Nevada" "North Carolina"
## [39] "North Carolina" "Newton"
## [41] "London" "New York City"
## [43] "Fifth Avenue" "Tokyo"
## [45] "United States" "Silicon Valley"
## [47] "California" "(79,000"
## [49] "Sunnyvale" "California"
## [51] "Europe" "Middle East"
## [53] "Africa" "Cork"
## [55] "Ireland" "United States"
## [57] "Apple" "United Kingdom"
## [59] "Stockley Park" "London"
## [61] "Herzliya" "Israel"
## [63] "Israel" "Haifa"
## [65] "Manhattan" "Fifth Avenue"
## [67] "Regent Street" "London"
## [69] "Europe" "London"
## [71] "Covent Garden" "New York City"
## [73] "United States" "Fifth Avenue"
## [75] "New York City" "Paris Sydney Hong Kong"
## [77] "Apple" "Virginia"
## [79] "California" "United States"
## [81] "America" "China"
## [83] "China" "China"
## [85] "China" "China"
## [87] "Jackson" "Maine"
## [89] "North Carolina" "China"
## [91] "China" "China"
## [93] "Singapore" "California"
## [95] "China" "China"
## [97] "China" "United States"
## [99] "Ireland" "the Netherlands"
## [101] "Virgin Islands" "Irish"
## [103] "the Netherlands" "Caribbean"
## [105] "United States of America" "United States"
## [107] "United States" "United States"
## [109] "Ireland" "Irish"
## [111] "Austria" "Austria"
## [113] "Earth" "San Francisco"print the execution time
difftime(Sys.time(), t1, units = 'sec')## Time difference of 23.34937 secs## We could do much with this info, e.g., improve lists by editing them with external domain knowledge, etc.
E.g., geocode the locations and create a map of the world of each article.
all_places = unique(apple_locations)## Get the geo codes
all_places_geocoded <- geocode(all_places) #[1:10]## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=California&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=United%20States&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Ireland&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Macintosh&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Microsoft&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Key&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "Key"## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Virginia&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Tokyo&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Paris&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=France&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Cisco&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Silicon%20Valley&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=New%20York%20City&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=India&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Silicon%20Valley-based&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Tel%20Aviv.&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Turkey&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Ankara&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Istanbul&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Japan&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=San%20Jose&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Magic%20Mouse&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "Magic Mouse"## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Magic%20Trackpad&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "Magic
## Trackpad"## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Magic%20Keyboard&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "Magic
## Keyboard"## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=3G&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Sydney&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Herald&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Nevada&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=North%20Carolina&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Newton&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=London&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Fifth%20Avenue&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=(79,000&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "(79,000"## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Sunnyvale&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Europe&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Middle%20East&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Africa&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Cork&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Apple&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=United%20Kingdom&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Stockley%20Park&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Herzliya&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Israel&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Haifa&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Manhattan&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Regent%20Street&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Covent%20Garden&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Paris%20Sydney%20Hong%20Kong&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=America&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=China&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Jackson&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Maine&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Singapore&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=the%20Netherlands&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Virgin%20Islands&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Irish&sensor=false## Warning: geocode failed with status ZERO_RESULTS, location = "Irish"## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Caribbean&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=United%20States%20of%20America&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Austria&sensor=false## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=Earth&sensor=false## .## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=San%20Francisco&sensor=false## List the geo codes
all_places_geocoded## lon lat
## 1 -119.4179324 36.778261
## 2 -95.7128910 37.090240
## 3 -8.2438900 53.412910
## 4 -118.4505268 35.135952
## 5 -122.1304930 47.640282
## 6 NA NA
## 7 -78.6568942 37.431573
## 8 139.6917064 35.689487
## 9 2.3522219 48.856614
## 10 2.2137490 46.227638
## 11 -98.9792336 32.388186
## 12 -122.0575434 37.387474
## 13 -74.0059413 40.712784
## 14 78.9628800 20.593684
## 15 -122.0575434 37.387474
## 16 34.7817676 32.085300
## 17 35.2433220 38.963745
## 18 32.8597419 39.933363
## 19 28.9783589 41.008238
## 20 138.2529240 36.204824
## 21 -121.8863286 37.338208
## 22 NA NA
## 23 NA NA
## 24 NA NA
## 25 -71.5303386 43.715973
## 26 151.2092955 -33.868820
## 27 -121.2455569 38.294758
## 28 -116.4193890 38.802610
## 29 -79.0192997 35.759573
## 30 -71.2092214 42.337041
## 31 -0.1277583 51.507351
## 32 -73.9969848 40.731412
## 33 NA NA
## 34 -122.0363496 37.368830
## 35 15.2551187 54.525961
## 36 42.5509603 29.298528
## 37 34.5085230 -8.783195
## 38 -8.4863157 51.896892
## 39 -114.0757739 35.912754
## 40 -3.4359730 55.378051
## 41 -1.7018229 52.829064
## 42 34.8446750 32.162413
## 43 34.8516120 31.046051
## 44 34.9895710 32.794046
## 45 -96.5716694 39.183608
## 46 -89.4362855 43.068016
## 47 -0.1232697 51.511732
## 48 114.1094970 22.396428
## 49 -95.7128910 37.090240
## 50 104.1953970 35.861660
## 51 -90.1848103 32.298757
## 52 -69.4454689 45.253783
## 53 103.8198360 1.352083
## 54 5.2912660 52.132633
## 55 -64.8963350 18.335765
## 56 NA NA
## 57 -78.6568942 21.469114
## 58 -95.7128910 37.090240
## 59 14.5500720 47.516231
## 60 -102.4107493 34.233137
## 61 -122.4194155 37.774929Load the map and highlight the loctions
## Recemmendations From the above data, Wiki page talks more about the founders of the Apple company and its products. Steve Jobs and Steve Wozniak played a key role in the apple’s establishment.Page talks about the products like magic mouse, siri and Mas OS.It provides information about the strength of the employees.
Looking at the locations data, Seems like apples concentration is more in North America region, Europe and to some extent in Asian Countries.
Apple can try to increase their market in African and South American regions.
Increasing their foot print in Asia, South America and South Africa would increase their revenue more.
Further, Apple can look at Asian countries to manufacturing and assembling their products. This would decrease the actual involved in the making the products.