blob: 367bd7466b9f060b2caf53de068cd099eb6c3636 [file] [log] [blame]
{"paragraphs":[{"text":"%INTERPRETER_NAME\nsparkR.session()\n\nworking_storage <- \"WORKING_STORAGE\"\noutput_directory <- \"zeppelin/r\"\nprotocol_name <- 'PROTOCOL_NAME'\nfull_path <- function(file_path) {\n sprintf('%s://%s/%s/%s', protocol_name, working_storage, output_directory, file_path)\n}\nbucket_path <- function(file_path) {\n sprintf('%s://%s/zeppelin_dataset/%s', protocol_name, working_storage, file_path)\n}\ncarriers <- read.df(bucket_path(\"carriers.csv\"), \"csv\", header=\"true\", inferSchema=\"true\")\nwrite.df(carriers, path=full_path(\"carriers\"), source=\"parquet\", mode=\"overwrite\")\ncreateOrReplaceTempView(carriers, \"carriers\")\nhead(carriers, 20)","dateUpdated":"2018-01-03T14:24:46+0000","config":{"colWidth":12,"editorMode":"ace/mode/text","results":{},"enabled":true,"editorSetting":{"language":"text","editOnDblClick":false}},"settings":{"params":{},"forms":{}},"apps":[],"jobName":"paragraph_1514989446718_-373603271","id":"20170224-132230_714744516","dateCreated":"2018-01-03T14:24:06+0000","status":"READY","errorMessage":"","progressUpdateIntervalMs":500,"focus":true,"$$hashKey":"object:334"},{"text":"%INTERPRETER_NAME\nairports <- read.df(bucket_path(\"airports.csv\"), \"csv\", header=\"true\", inferSchema=\"true\")\nwrite.df(airports, path=full_path(\"airports\"), source=\"parquet\", mode=\"overwrite\")\ncreateOrReplaceTempView(airports, \"airports\")\nhead(airports, 20)","dateUpdated":"2018-01-03T14:24:48+0000","config":{"colWidth":12,"editorMode":"ace/mode/text","results":{},"enabled":true,"editorSetting":{"language":"text","editOnDblClick":false}},"settings":{"params":{},"forms":{}},"apps":[],"jobName":"paragraph_1514989446719_-373988020","id":"20170224-132306_851966551","dateCreated":"2018-01-03T14:24:06+0000","status":"READY","errorMessage":"","progressUpdateIntervalMs":500,"$$hashKey":"object:335"},{"text":"%INTERPRETER_NAME\nflights_w_na <- read.df(bucket_path(\"2008.csv.bz2\"), \"csv\", header=\"true\", inferSchema=\"true\")\nflights <- fillna(flights_w_na, 0, cols=colnames(flights_w_na)[c(15, 16, 25:29)])\nwrite.df(flights, path=full_path(\"flights\"), source=\"parquet\", mode=\"overwrite\")\ncreateOrReplaceTempView(flights, \"flights\")\ncolnames(flights)\nhead(flights_w_na, 5)[c(\"ArrDelay\",\"CarrierDelay\",\"WeatherDelay\",\"Distance\")]\nhead(flights, 5)[c(\"ArrDelay\",\"CarrierDelay\",\"WeatherDelay\",\"Distance\")]","dateUpdated":"2018-01-03T14:24:49+0000","config":{"colWidth":12,"editorMode":"ace/mode/text","results":{},"enabled":true,"editorSetting":{"language":"text","editOnDblClick":false}},"settings":{"params":{},"forms":{}},"apps":[],"jobName":"paragraph_1514989446719_-373988020","id":"20170224-132326_1724524583","dateCreated":"2018-01-03T14:24:06+0000","status":"READY","errorMessage":"","progressUpdateIntervalMs":500,"$$hashKey":"object:336"}],"name":"R_data_preparation","id":"2D57NEGDB","angularObjects":{"2C6RJRBD2:shared_process":[],"2C6RJRBD1:shared_process":[]},"config":{"looknfeel":"default","personalizedMode":"false"},"info":{}}