showLocalRepo: View the Lisf of Artifacts from a Repository

Description

showLocalRepo and showGithubRepo functions produce the data.frame of the artifacts from a Repository saved in a given repoDir (directory). showLocalRepo shows the artifacts from the Repository that exists on the user's computer, whereas showGithubRepo shows the artifacts of the Repository existing on a Github repository. To learn more about artifacts visit archivist-package.

Usage

showLocalRepo(repoDir = NULL, method = "md5hashes")
showGithubRepo(repo = NULL, user = NULL, branch = "master",
  repoDirGit = FALSE, method = "md5hashes")

Arguments

repoDir

A character denoting an existing directory of a Repository for which a summary will be returned. If set to NULL (by default), uses the repoDir specified in setLocalRepo.

method

A character specifying the method to be used to show the Repository. Available methods: md5hashes (default), tags and sets - see saveSetToRepo.

repo

Only if working with a Github repository. A character containing a name of a Github repository on which the Repository is archived. By default set to NULL - see Note.

user

Only if working with a Github repository. A character containing a name of a Github user on whose account the repo is created. By default set to NULL - see Note.

branch

Only if working with a Github repository. A character containing a name of Github Repository's branch on which a Repository is archived. Default branch is master.

repoDirGit

Only if working with a Github repository. A character containing a name of a directory on Github repository on which the Repository is stored. If the Repository is stored in main folder on Github repository, this should be set to repoDirGit = FALSE<

Value

If parameter method was set as md5hashes a data.frame with artifacts' names and archived md5hashes is returned.
If parameter method was set as tags a data.frame with archived Tags and archived artifacts' md5hashes is returned.
To learn more about Tags or md5hashes check: Tags or md5hash.

Details

Both functions show the current state of a Repository, inter alia, all archived artifacts can be seen with their unique md5hash or a data.frame with archived Tags can be obtained. Also there is an extra column with a date of creation the Tag or the md5hash.

Examples

Run this code

# objects preparation
# data.frame object
data(iris)

# ggplot/gg object
library(ggplot2)
df <- data.frame(gp = factor(rep(letters[1:3], each = 10)),y = rnorm(30))
library(plyr)
ds <- ddply(df, .(gp), summarise, mean = mean(y), sd = sd(y))
myplot123 <- ggplot(df, aes(x = gp, y = y)) +
  geom_point() +  geom_point(data = ds, aes(y = mean),
               colour = 'red', size = 3)

# lm object
model <- lm(Sepal.Length~ Sepal.Width + Petal.Length + Petal.Width, data= iris)


# lda object
library(MASS)

Iris <- data.frame(rbind(iris3[,,1], iris3[,,2], iris3[,,3]),
                  Sp = rep(c("s","c","v"), rep(50,3)))
train <- c(8,83,115,118,146,82,76,9,70,139,85,59,78,143,68,
           134,148,12,141,101,144,114,41,95,61,128,2,42,37,
           29,77,20,44,98,74,32,27,11,49,52,111,55,48,33,38,
           113,126,24,104,3,66,81,31,39,26,123,18,108,73,50,
           56,54,65,135,84,112,131,60,102,14,120,117,53,138,5)
lda1 <- lda(Sp ~ ., Iris, prior = c(1,1,1)/3, subset = train)

# qda object
tr <- c(7,38,47,43,20,37,44,22,46,49,50,19,4,32,12,29,27,34,2,1,17,13,3,35,36)
train <- rbind(iris3[tr,,1], iris3[tr,,2], iris3[tr,,3])
cl <- factor(c(rep("s",25), rep("c",25), rep("v",25)))
qda1 <- qda(train, cl)

# glmnet object
library( glmnet )

zk=matrix(rnorm(100*20),100,20)
bk=rnorm(100)
glmnet1=glmnet(zk,bk)

# creating example Repository - that examples will work

exampleRepoDir <- tempdir()
createEmptyRepo(repoDir = exampleRepoDir)
saveToRepo(myplot123, repoDir=exampleRepoDir)
saveToRepo(iris, repoDir=exampleRepoDir)
saveToRepo(model, repoDir=exampleRepoDir)

# show examples

showLocalRepo(method = "md5hashes", repoDir = exampleRepoDir)
showLocalRepo(method = "tags", repoDir = exampleRepoDir)

# let's add more artifacts

saveToRepo(glmnet1, repoDir=exampleRepoDir)
saveToRepo(lda1, repoDir=exampleRepoDir)
(qda1Md5hash <- saveToRepo(qda1, repoDir=exampleRepoDir))

# show now

showLocalRepo(method = "md5hashes", repoDir = exampleRepoDir)
showLocalRepo(method = "tags", repoDir = exampleRepoDir)

# what if we remove an artifact

rmFromRepo(qda1Md5hash, repoDir = exampleRepoDir)

# show now

showLocalRepo(method = "md5hashes", repoDir = exampleRepoDir)
showLocalRepo(method = "tags", repoDir = exampleRepoDir)

# GitHub version

showGithubRepo(method = "md5hashes", user = "pbiecek", repo = "archivist")
showGithubRepo(method = "tags", user = "pbiecek", repo = "archivist", branch = "master")



# sets method
setLocalRepo( exampleRepoDir )
library(ggplot2)
library(ggthemes)

data(iris)

plotArtifact <- ggplot( iris, aes(x = Sepal.Length, y = Species)) +
  geom_point()+
  theme_wsj()

plotData <- iris
plotFunctions <- list( ggplot, geom_point, theme_wsj)

saveSetToRepo( artifact = plotArtifact,
               data = plotData,
               functions = plotFunctions )
showLocalRepo( method = "sets" )


# removing an example Repository

deleteRepo( exampleRepoDir )

rm( exampleRepoDir )

# many archivist-like Repositories on one Github repository

showGithubRepo( user="MarcinKosinski", repo="Museum", branch="master",
repoDirGit="ex1")
showGithubRepo( user="MarcinKosinski", repo="Museum", branch="master",
                repoDirGit="ex2")

Run the code above in your browser using DataLab