<\/a>\u0412\u043e\u0437\u043c\u043e\u0436\u043d\u043e, \u043f\u0440\u0438 \u0431\u043e\u043b\u044c\u0448\u0435\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0435 \u0440\u0430\u0437\u043d\u043e\u0442\u0438\u043f\u043d\u044b\u0445 \u0444\u0430\u0439\u043b\u043e\u0432 \u0438\u0445 \u043b\u0443\u0447\u0448\u0435 \u0431\u044b\u043b\u043e \u0431\u044b \u0443\u043f\u0440\u043e\u0441\u0442\u0438\u0442\u044c \u0447\u0435\u0440\u0435\u0437 \u0444\u0443\u043d\u043a\u0446\u0438\u044e, \u0432\u043c\u0435\u0441\u0442\u043e \u0442\u043e\u0433\u043e, \u0447\u0442\u043e\u0431\u044b \u043f\u0438\u0441\u0430\u0442\u044c \u043a\u043e\u0434 \u0434\u043b\u044f \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u0442\u0438\u043f\u0430. \u041d\u043e \u0438\u0434\u0435\u044f \u043e\u0442 \u044d\u0442\u043e\u0433\u043e \u043d\u0435 \u043c\u0435\u043d\u044f\u0435\u0442\u0441\u044f \u2014 \u0441\u043b\u0435\u0434\u0443\u0435\u0442 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u0442\u044c \u043d\u0430\u043b\u0438\u0447\u0438\u0435 \u0434\u0438\u0440\u0435\u043a\u0442\u043e\u0440\u0438\u0438 \u0438 \u0432 \u0441\u043b\u0443\u0447\u0430\u0435 \u043e\u0442\u0441\u0443\u0442\u0441\u0442\u0432\u0438\u044f, \u0441\u043e\u0437\u0434\u0430\u0442\u044c \u0435\u0435. \u041f\u043e\u0441\u043b\u0435 \u044d\u0442\u043e\u0433\u043e \u043d\u0443\u0436\u043d\u043e \u043f\u0435\u0440\u0435\u043c\u0435\u0441\u0442\u0438\u0442\u044c \u0444\u0430\u0439\u043b\u044b \u0432 \u0441\u043e\u0437\u0434\u0430\u043d\u043d\u0443\u044e \u0434\u0438\u0440\u0435\u043a\u0442\u043e\u0440\u0438\u044e.<\/p>\n\u0421\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u0435 \u0438 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 PostgreSQL \u0447\u0435\u0440\u0435\u0437 R<\/h4>\n
\u041a\u0430\u043a \u0442\u043e\u043b\u044c\u043a\u043e \u0444\u0430\u0439\u043b\u044b \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u044b, \u043c\u043e\u0436\u043d\u043e \u043d\u0430\u0447\u0438\u043d\u0430\u0442\u044c \u0437\u0430\u0433\u0440\u0443\u0436\u0430\u0442\u044c \u0438\u0445 \u0432 PostgreSQL, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f RPostgreSQL \u043f\u0430\u043a\u0435\u0442 R. RPostgreSQL DBI-\u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u044b\u0439, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0441\u0442\u0440\u043e\u043a\u0430 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u0431\u0443\u0434\u0435\u0442 \u043e\u0434\u0438\u043d\u0430\u043a\u043e\u0432\u043e\u0439 \u0434\u043b\u044f \u043b\u044e\u0431\u043e\u0433\u043e \u0442\u0438\u043f\u0430 \u044f\u0434\u0440\u0430 \u0431\u0430\u0437\u044b \u0434\u0430\u043d\u043d\u044b\u0445; \u043f\u0440\u0438 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0435 \u0447\u0430\u0441\u0442\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 \u0411\u0414 \u043f\u0440\u0430\u043a\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u0433\u0430\u0440\u0430\u043d\u0442\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e \u043f\u043e\u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u043e\u0440\u043c\u0430\u0442 (\u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f colClasses = \u0430\u0440\u0433\u0443\u043c\u0435\u043d\u0442 \u201ccharacter\u201d \u0432 R). \u0422\u0430\u043a\u0430\u044f \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u0441\u0442\u044c \u0432\u043e\u0437\u043d\u0438\u043a\u0430\u0435\u0442 \u0438\u0437-\u0437\u0430 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0445 \u0438\u0437\u043c\u0435\u043d\u0435\u043d\u0438\u0439 \u0438 \u043c\u043e\u0434\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0439 Adobe Analytics (\u043f\u0430\u043a\u0435\u0442 \u0440\u0435\u0448\u0435\u043d\u0438\u0439 \u043a\u043e\u0440\u043f\u043e\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0433\u043e \u0443\u0440\u043e\u0432\u043d\u044f \u0434\u043b\u044f \u0441\u0431\u043e\u0440\u0430 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0438 \u0441\u0430\u0439\u0442\u043e\u0432 \u0438 \u0440\u0430\u0431\u043e\u0442\u044b \u0441 \u043d\u0435\u0439); \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u043e\u0440\u043c\u0430\u0442 \u0441\u0442\u043e\u043b\u0431\u0446\u0430 \u043d\u0435 \u0434\u043e\u043f\u0443\u0441\u043a\u0430\u0435\u0442 \u043f\u043e\u0442\u0435\u0440\u0438 \u0434\u0430\u043d\u043d\u044b\u0445.<\/p>\n
library(RPostgreSQL) # Connect to database conn = dbConnect(dbDriver("PostgreSQL"), user="postgres", password="", host="localhost", port=5432, dbname="adobe") #Set directory to avoid having to use paste to build urls setwd("~\/Downloads\/datafeed\/servercalls") #Set column headers for server calls column_headers <- read.delim("~\/Downloads\/datafeed\/lookup\/column_headers.tsv", stringsAsFactors=FALSE) #Loop over entire list of files #Setting colClasses to character only way to guarantee all data loads #File formats or implementations can change over time; fix schema in database after data loaded for(file in list.files()){ print(file) df <- read.csv2(file, sep = "\\t", header = FALSE, stringsAsFactors = FALSE, colClasses = "character") dbWriteTable(conn, name = 'servercalls', value = df, row.names=FALSE, append = TRUE) rm(df) } #Run analyze in PostgreSQL so that query planner has accurate information dbGetQuery(conn, "analyze servercalls") <\/code><\/pre>\n \u041f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u043e\u0433\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0430 \u043a\u043e\u0434\u0430 \u0431\u044b\u043b\u0430 \u0441\u0433\u0435\u043d\u0435\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u0430 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u043d\u0430\u044f \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0430 \u0442\u0430\u0431\u043b\u0438\u0446\u044b, \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u043b\u0438\u0441\u044c \u0434\u0430\u043d\u043d\u044b\u0435 \u0438 PostgreSQL \u043d\u0430\u0447\u0430\u043b \u043f\u0440\u043e\u0432\u043e\u0434\u0438\u0442\u044c \u0430\u043d\u0430\u043b\u0438\u0437 \u0438 \u0441\u0431\u043e\u0440 \u0441\u0442\u0430\u0442\u0438\u0441\u0442\u0438\u043a\u0438 \u0434\u043b\u044f \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u044b\u0445 \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u044b\u0445 \u0437\u0430\u043f\u0440\u043e\u0441\u043e\u0432.<\/p>\n
\u0417\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0442\u0430\u0431\u043b\u0438\u0446 \u043f\u043e\u0438\u0441\u043a\u0430 \u0432 PostgreSQ<\/h4>\n
\u0412\u043c\u0435\u0441\u0442\u0435 \u0441 \u0434\u0430\u043d\u043d\u044b\u043c\u0438 \u0432\u044b\u0437\u043e\u0432\u0430 \u0441\u0435\u0440\u0432\u0435\u0440\u0430, \u0447\u0442\u043e \u0437\u0430\u0433\u0440\u0443\u0436\u0435\u043d\u044b \u0432 \u0411\u0414, \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u0442\u044c \u0438 \u0442\u0430\u0431\u043b\u0438\u0446\u044b \u043f\u043e\u0438\u0441\u043a\u0430. \u041e\u043d\u0438 \u0441\u043e\u0445\u0440\u0430\u043d\u044f\u044e\u0442 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0439 \u0444\u043e\u0440\u043c\u0430\u0442 \u0438 RPostgreSQL \u043f\u043e\u043b\u0443\u0447\u0430\u0435\u0442 \u043a\u043e\u0440\u0440\u0435\u043a\u0442\u043d\u044b\u0435 \u0442\u0438\u043f\u044b \u0441\u0442\u043e\u043b\u0431\u0446\u043e\u0432.<\/p>\n
library(RPostgreSQL) # Connect to database conn = dbConnect(dbDriver("PostgreSQL"), user="postgres", password="", host="localhost", port=5432, dbname="adobe") setwd("~\/Downloads\/datafeed\/lookup\/") #Create function due to repetitiveness #Since we're loading lookup tables with mostly same values each time, put source file in table loadlookup <- function(tblname){ df <- read.csv2(paste(tblname,".tsv", sep=""), sep = "\\t", header = FALSE, stringsAsFactors = FALSE) df$file <- file dbWriteTable(conn, name = tblname, value = df, row.names=FALSE, append = TRUE) } #untar files, place in directory by day for(file in list.files(pattern = "*.tar.gz")){ print(file) untar(file) for(tbl in c("browser_type", "browser", "color_depth", "column_headers", "connection_type", "country", "event", "javascript_version", "languages", "operating_systems", "plugins", "referrer_type", "resolution", "search_engines")){ loadlookup(tbl) } } <\/code><\/pre>\n<\/div>\n
\u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 https:\/\/habrahabr.ru\/post\/278897\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" \u0418\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u044f\u0437\u044b\u043a\u0430 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f R \u0432\u043c\u0435\u0441\u0442\u0435 \u0441\u043e \u0441\u0432\u043e\u0431\u043e\u0434\u043d\u043e\u0439 \u0440\u0435\u043b\u044f\u0446\u0438\u043e\u043d\u043d\u043e\u0439 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0431\u0430\u0437\u0430\u043c\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 PostgresSQL \u043c\u043e\u0436\u0435\u0442 \u0437\u043d\u0430\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u0443\u0441\u043a\u043e\u0440\u0438\u0442\u044c \u0438 \u0443\u043f\u0440\u043e\u0441\u0442\u0438\u0442\u044c \u043f\u0440\u043e\u0446\u0435\u0441\u0441 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 \u0411\u0414. <\/p>\n
![](\"https:\/\/habrastorage.org\/files\/d6d\/c84\/1f1\/d6dc841f117a41ebb4ecc040f6aaafca.jpeg\"\/)
<\/p>\n
\u0421\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0444\u0430\u0439\u043b\u043e\u0432<\/h4>\n
\u041f\u0435\u0440\u0435\u0434 \u043d\u0430\u0447\u0430\u043b\u043e\u043c \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 PostgreSQL, \u0441\u043b\u0435\u0434\u0443\u0435\u0442 \u0440\u0430\u0441\u0441\u043e\u0440\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0444\u0430\u0439\u043b\u044b \u043f\u043e \u0442\u0438\u043f\u0443 \u0432 \u0440\u0430\u0437\u043d\u044b\u0435 \u0434\u0438\u0440\u0435\u043a\u0442\u043e\u0440\u0438\u0438. R \u0434\u0435\u043b\u0430\u0435\u0442 \u043e\u043f\u0435\u0440\u0430\u0446\u0438\u0438 \u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e \u043f\u0440\u043e\u0441\u0442\u044b\u043c\u0438 \u043d\u0430 \u0443\u0440\u043e\u0432\u043d\u0435 \u041e\u0421:<\/p>\n
#### 1. Setting directory to FTP folder where files incoming from Adobe ## Has ~2000 files in it from 2 years of data setwd("~\/Downloads\/datafeed\/") #### 2. Sort files into three separate folders ## Manifests - plain text files if(!dir.exists("manifest")){ dir.create("manifest") lapply(list.files(pattern = "*.txt"), function(x) file.rename(x, paste("manifest", x, sep = "\/")) } ## Server calls tsv.gz if(!dir.exists("servercalls")){ dir.create("servercalls") lapply(list.files(pattern = "*.tsv.gz"), function(x) file.rename(x, paste("servercalls", x, sep = "\/"))) } ## Lookup files .tar.gz if(!dir.exists("lookup")){ dir.create("lookup") lapply(list.files(pattern = "*.tar.gz"), function(x) file.rename(x, paste("lookup", x, sep = "\/"))) } <\/code><\/pre>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-277257","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/277257","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=277257"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/277257\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=277257"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=277257"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=277257"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}