Merge branch 'dev-rpackage' into 'master'

v0.0.0.9004

See merge request eoc_foundation_wip/analysis-pipelines!11

.Rbuildignore

@@ -1,2 +1,3 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
+data-raw/

.gitignore

@@ -3,6 +3,7 @@
 .RData
 .Ruserdata
 metastore_db/
+inst/python/.ipynb_checkpoints/
 .DS_Store
 vignettes/metastore_db/
 vignettes/*.RDS

DESCRIPTION

@@ -1,20 +1,19 @@
 Package: analysisPipelines
 Type: Package
-Title: Compose interoperable analysis pipelines, and put them into production
-Version: 0.0.0.9003
+Title: This Package Allows Data Scientists to Compose Interoperable Analysis Pipelines, and Put Them into Production
+Version: 0.0.0.9004
 Authors@R: c(
-      person("Naren","Srinivasan", email = "Naren.Srinivasan@mu-sigma.com", role = c("aut")),
+      person("Naren","Srinivasan", email = "naren1991@gmail.com", role = c("aut")),
       person("Zubin Dowlaty","",  email = "Zubin.Dowlaty@mu-sigma.com", role = c("ctb")),
       person("Sanjay","",  email = "Sanjay@mu-sigma.com", role = c("ctb")),
       person("Neeratyoy","Mallik", email = "Neeratyoy.Mallik@mu-sigma.com", role = c("ctb")),
 		  person("Anoop S","",  email = "Anoop.S@mu-sigma.com", role = c("ctb")),
 		  person("Mu Sigma, Inc.", email = "ird.experiencelab@mu-sigma.com", role = c("cre"))
 		  )
-Description: The package aims at enabling data scientists to compose pipelines of analysis which consist of data manipulation, exploratory analysis & reporting, as well as modeling steps. It also aims to enable data scientists to use tools of their choice through an R interface, and compose interoperable pipelines between R, Spark, and Python. Credits to Mu Sigma for supporting the development of the package.
-Depends: R (>= 3.4.0), tibble, magrittr, data.table, pipeR, devtools
-Imports: ggplot2, dplyr, futile.logger, RCurl, proto
-Suggests: plotly, knitr, rmarkdown, SparkR, parallel, visNetwork, rjson, DT, shiny
-Remotes: github::cran/SparkR
+Description: This package aims at enabling data scientists to compose pipelines of analysis which consist of data manipulation, exploratory analysis & reporting, as well as modeling steps. It also aims to enable data scientists to use tools of their choice through an R interface, and compose interoperable pipelines between R, Spark, and Python. Credits to Mu Sigma for supporting the development of the package.
+Depends: R (>= 3.4.0), magrittr, pipeR, methods
+Imports: ggplot2, dplyr, futile.logger, RCurl, proto, rlang, purrr, devtools
+Suggests: plotly, knitr, rmarkdown, parallel, visNetwork, rjson, DT, shiny, R.devices, corrplot, reticulate
 Encoding: UTF-8
 License: Apache License 2.0
 LazyLoad: yes
@@ -28,5 +27,6 @@ Collate:
     'core-functions-meta-pipelines.R'
     'core-streaming-functions.R'
     'r-batch-eda-utilities.R'
+    'r-helper-utilites-python.R'
     'spark-structured-streaming-utilities.R'
     'zzz.R'

NAMESPACE

@@ -15,13 +15,18 @@ export(exportAsMetaPipeline)
 export(generateReport)
 export(genericPipelineException)
 export(getDatatype)
+export(getFeaturesForPyClassification)
 export(getInput)
 export(getLoggerDetails)
 export(getOutputById)
 export(getPipeline)
 export(getPipelinePrototype)
 export(getRegistry)
+export(getResponse)
+export(getTargetForPyClassification)
+export(getTerm)
 export(ignoreCols)
+export(isDependencyParam)
 export(loadMetaPipeline)
 export(loadPipeline)
 export(loadPredefinedFunctionRegistry)
@@ -34,6 +39,7 @@ export(savePipeline)
 export(saveRegistry)
 export(setInput)
 export(setLoggerDetails)
+export(setPythonEnvir)
 export(sparkRSessionCreateIfNotPresent)
 export(univarCatDistPlots)
 export(updateObject)
@@ -44,5 +50,19 @@ exportClasses(MetaAnalysisPipeline)
 exportClasses(StreamingAnalysisPipeline)
 exportMethods(checkSchemaMatch)
 exportMethods(generateOutput)
-exportMethods(initialize)
-import(SparkR)
+importFrom(graphics,image)
+importFrom(magrittr,"%>%")
+importFrom(methods,getClass)
+importFrom(methods,new)
+importFrom(methods,removeMethod)
+importFrom(methods,setClassUnion)
+importFrom(methods,setGeneric)
+importFrom(methods,setOldClass)
+importFrom(pipeR,"%>>%")
+importFrom(rlang,.data)
+importFrom(stats,as.formula)
+importFrom(stats,lm)
+importFrom(stats,reorder)
+importFrom(stats,terms)
+importFrom(utils,installed.packages)
+importFrom(utils,read.csv)

R/analysisPipelines_package.R

@@ -3,6 +3,9 @@
 #' The package aims at enabling data scientists to compose pipelines of analysis which consist of data manipulation,
 #' exploratory analysis & reporting, as well as modeling steps. It also aims to enable data scientists to use tools
 #' of their choice through an R interface, and compose interoperable pipelines between R, Spark, and Python.
+#'
+#' Important Note - This package uses 'SparkR' to interact with Spark and automatically installs it if not present
+#' from a Github repo as 'SparkR' is not distrubuted on CRAN
 #' @docType package
 #' @name analysisPipelines
 NULL