index.Rmd

---
title: "github.com/openpharma"
output: 
  flexdashboard::flex_dashboard:
    theme: 
      version: 4
      bootswatch: minty
    orientation: rows
    social: menu
    source_code: https://github.com/openpharma/openpharma.github.io
    navbar:
      - { title: "Github", href: "https://github.com/openpharma/", align: right, icon: github}
    includes: 
      in_header: googleanalytics.html
---

```{r, include=FALSE}
library(flexdashboard)
library(ggplot2)

library(dplyr)
library(lubridate)
library(glue)
library(tidyr)
library(fontawesome) # devtools::install_github("rstudio/fontawesome")
library(plotly)

library(purrr)
library(dm)
library(DiagrammeR)



thematic::thematic_rmd(
  font = "auto",
  # To get the dark bg on the geom_raster()
  sequential = thematic::sequential_gradient(fg_low = FALSE, fg_weight = 0, bg_weight = 1)
)
theme_set(theme_bw(base_size = 20))
```

```{r getdata}
library(readr)
  commits <- read_rds("scratch/commits.rds") %>%
    mutate(author = author_clean)
  people <- read_rds("scratch/people.rds")
  repos <- read_rds("scratch/repos.rds")
  help <- read_rds("scratch/help.rds")
  badges <- read_csv("scratch/badges.csv")
```


Organization
===================================== 

Value Boxes {data-width=200}
-------------------------------------

### Primary

```{r}
valueBox(n_distinct(repos$repo), caption = "Total repos", icon = "fa-github")
```

### Commits

```{r}
valueBox(nrow(commits), caption = "Commits", color = "success", icon = "fa-code-branch")
```

### People

```{r}
valueBox(
  n_distinct(people$author), 
  caption = "People", color = "success", icon = "fa-users")
```

### Intro issues

```{r}
valueBox(
  help  %>% nrow(), 
  caption = "Open issues needing help", color = "warning", icon = "fa-question")
```

### Companies

```{r}
valueBox(
  n_distinct(people$company), 
  caption = "Unique employers", color = "success", icon = "fa-building")
```

Value Boxes {data-width=200}
-------------------------------------


### 

```{r}
lookback <- 30*3
lookback_char <- "3 months"

valueBox(
  commits %>%
    filter(date > Sys.Date() - lookback) %>%
    pull(full_name) %>% n_distinct(),
  caption = glue("Repos active | Last {lookback_char}"), 
  color = "info", icon = "fa-chart-line"
  )
```

### 

```{r}
valueBox(
  commits %>%
    filter(date > Sys.Date() - lookback) %>%
    nrow(),
  caption = glue("Commits | Last {lookback_char}"),
  color = "info", icon = "glyphicon-time")
```

### 

```{r}
valueBox(
  commits %>%
    filter(date > Sys.Date() - lookback) %>%
    pull(author) %>% n_distinct(),
  caption = glue("People active | Last {lookback_char}"), 
  color = "info", icon = "glyphicon-time")
```

### 

```{r}
valueBox(
  repos %>% filter(lang == "python") %>% nrow(), 
  caption = "Python libraries", color = "info",
  icon = "fab fa-python"
)
```

### 

```{r}
valueBox(
  repos %>% filter(lang == "r") %>% nrow(), 
  caption = "R packages", color = "info",
  icon = "fab fa-r-project"
)
```

    
Tables {.tabset}
-------------------------------------

### Repositories
    
```{r}
hlp_repo_details <- function(x){
  DT::datatable(
      x %>% ungroup %>%
          mutate(
            `Last updated` = as.Date(gh_updated),
            ) %>%
          arrange(desc(`Last updated`)) %>%
          select(
              Repo = pretty_repo,
              Description = imputed_description,
              `Type` = lang,
              `Last updated`,
              `Contributor overlap` = similar
          ), 
      rownames = FALSE,
      escape = FALSE,
      fillContainer = FALSE)  
}

hlp_repo_details(repos)
```

### Help needed
    
```{r}

  DT::datatable(
      help %>% ungroup %>%
          arrange(desc(updated)) %>%
          select(
              Repo = full_name,
              Link = pretty_url,
              Created = created,
              Comments = comments,
              Updated = updated,
              Title = title,
              Description = body
              
          ), 
      rownames = FALSE,
      escape = FALSE,
      fillContainer = FALSE)  

```

### People
    
```{r, echo = FALSE}
DT::datatable(
  people %>%
    mutate(my = format(last_active, "%Y-%m")) %>% 
    group_by(my) %>% mutate(month_commits = sum(commits)) %>% ungroup %>%
    mutate(
      last_active = Sys.Date() - last_active,
      contributor = as.character(glue(
        '<img src="{avatar}" alt="" height="30" width = "30"> {name} (<a href="https://github.com/{author}">{author}</a>)'
        )),
      Blog = case_when(
        blog == "" ~ "",
        TRUE ~ as.character(glue('<a href="{blog}">link</a>'))
        ),
      Name = glue("{name} ({author})")
      ) %>%
    arrange(desc(my),desc(month_commits), desc(contributed_to), desc(commits)) %>%
    select(
      `Name (GH handle)` = contributor,
      Repos = contributed_to,
      `Repo list` = repo_list,
      `Commits` = commits,
      `Days since active` = last_active,
      Company = company,
      Location = location,
      Blog
      ) , 
    escape = FALSE,
    rownames = FALSE,
    fillContainer = FALSE)
```

### Health
    
```{r}
# kaplan mier estimate?


repos %>% ungroup %>%
  mutate(
    riskmetric_score = round(riskmetric_score,2)
  ) %>%
  # tidy title
  select(
    Repo = pretty_repo,
    `OS Health` = os_health,
    `riskmetric` = riskmetric_score,
    Commits,
    Contributors
  ) %>%
  arrange(
    desc(`OS Health`)
  ) %>%
  # table it
  DT::datatable(
    escape = FALSE,
    rownames = FALSE,
    fillContainer = FALSE
    )
```

### Growth

```{r}
### People activity over time
plot <- commits %>%
  mutate(
    month = format(date, "%m"), 
    year = format(date, "%Y"),
    year_mon = as.Date(glue("{year}-{month}-01"))
    ) %>%
  group_by(year_mon) %>%
  summarise(
    Repos = n_distinct(full_name),
    People = n_distinct(author)
  ) %>%
  filter(year_mon >= as.Date("2020-01-01")) %>%
  pivot_longer(
    !year_mon,
    names_to = "Active by month",
    values_to = "Value"
  ) %>%
  # remove last 
  group_by(`Active by month`) %>%
  arrange(year_mon) %>%
  slice(1:(n() - 1)) %>%
  ggplot(
    aes(
      year_mon, 
      Value, 
      group = `Active by month`,
      colour = `Active by month`
    )
  ) +
  geom_line() +
  geom_point() +
  labs(
    title = "Active repos and people defined by monthly commit activity",
    x = "Monthly",
    y = "Active"
  ) + theme(legend.title = element_blank())

ggplotly(plot)
```

### Growth - with denominator

```{r}
range <- commits %>%
  mutate(
    month = format(date, "%m"), 
    year = format(date, "%Y"),
    year_mon = as.Date(glue("{year}-{month}-01"))
  ) %>%
  summarise(
    min = min(year_mon), max = max(year_mon)
  )

### People activity over time
plot <- commits %>%
  mutate(
    month = format(date, "%m"), 
    year = format(date, "%Y"),
    year_mon = as.Date(glue("{year}-{month}-01"))
    ) %>%
  group_by(year_mon) %>%
  summarise(
    Repos = n_distinct(full_name),
    People = n_distinct(author)
  ) %>%
  left_join(
    tibble(
  year_mon = seq.Date(min(range$min), max(range$max), by=1)
  ) %>%
  left_join(
    commits %>%
      mutate(
        month = format(date, "%m"), 
        year = format(date, "%Y"),
        year_mon = as.Date(glue("{year}-{month}-01"))
      ) %>%
      group_by(full_name) %>% 
      arrange(year_mon) %>% slice(1) %>% 
      # check one per date!
      group_by(year_mon) %>% summarise(total = n()),
    by = "year_mon"
  ) %>%
  mutate(
    total = case_when(
      is.na(total) ~ as.integer(0),
      TRUE ~ total
    ),
    tracked_repos = cumsum(total)
  ) %>%
  select(year_mon, `Repo's tracked` = tracked_repos),
    by = "year_mon"
  ) %>%
  filter(year_mon >= as.Date("2020-01-01")) %>%
  pivot_longer(
    !year_mon,
    names_to = "Active by month",
    values_to = "Value"
  ) %>%
  # remove last 
  group_by(`Active by month`) %>%
  arrange(year_mon) %>%
  slice(1:(n() - 1)) %>%
  ggplot(
    aes(
      year_mon, 
      Value, 
      group = `Active by month`,
      colour = `Active by month`
    )
  ) +
  geom_line() +
  geom_point() +
  labs(
    title = "Active repos and people defined by monthly commit activity",
    x = "Monthly",
    y = "Active"
  ) + theme(legend.title = element_blank())

ggplotly(plot)
```


Manifesto
=====================================     
   
Column 
-------------------------------------

### Manifesto

The objective of the Github [organisation github.com/openpharm](https://github.com/openpharma) (openpharma) is to provide a neutral home for open source software that is not tied to one company or institution. This Github organization is managed under the following principals:

Hosting repositories in a neutral space:

* openpharma allows repositories housed within it to set their own governance model
* openpharma is open to any project related to the Pharma industry
* openpharma makes no assumptions on what packages are part of an ‘ideal’ workflow
* a preference is always placed on opensource from day 1, but openpharma will also host packages in private repos on request
* [at launch, Roche has admin status for the organization] openpharma will work towards a governance model that is inclusive and builds trust in those contributing to packages (e.g. use a more formalized consortia like the pharmaverse to provide governance of the Github organization)
* openpharma is open to collaborating with relevant organizations like PHUSE, R Consortium, PSI and the pharmaverse – but  openpharma will remain an open host to share projects and provide a platform for repositories looking for a neutral host. 
* openpharma will not hold any IP or copyright of associated projects, it will not be a platform for discussion or host initiatives, and it will not release opinions or standards on which repositories form part of an ideal workflow.

Promoting collaboration on projects:

* openpharma will aim to build an inclusive list of collaborative projects hosted on github.com that goes beyond those physically hosted in github.com/openpharma.
* openpharma will surface these projects to encourage collaboration (e.g. provide a front end like https://insights.lfx.linuxfoundation.org/projects). As a starter, a proof of concept
has been made (this site)


### Links

- R/Pharma conference: [rinpharma.com](https://rinpharma.com/)
- R Consortium: [r-consortium.org](https://www.r-consortium.org/)
- Get your R project funded!: [ISC](https://www.r-consortium.org/projects/call-for-proposals)

Data
=====================================    
   
Row {.tabset}
-------------------------------------

### Details on the data pull

The data for this site builds daily. You can access the latest metadata via the 
links on this page. See the Snakefile for an example of the build
process

The code that generates this data is in the repo
[openpharma/openpharma.github.io](https://github.com/openpharma/openpharma.github.io).

Right now the data is not stable - as it is planned to be used in the 
upcoming pharmaverse.org website. Please reach out on the repo if you want to 
use this data, or have ideas to improve / standardise it.

These files contains *all* the data up to today, and was pulled ~ `r Sys.time()`.

- Latest repo data ([csv](http://openpharma.s3-website.us-east-2.amazonaws.com/repos.csv), `r format(object.size(repos), units = "Mb")`)

- Latest people data ([csv](http://openpharma.s3-website.us-east-2.amazonaws.com/people.csv), `r format(object.size(people), units = "Mb")`)

- Latest who needs help data ([csv](http://openpharma.s3-website.us-east-2.amazonaws.com/help.csv), `r format(object.size(help), units = "Mb")`)

- Latest commits data ([csv](http://openpharma.s3-website.us-east-2.amazonaws.com/commits.csv), `r format(object.size(commits), units = "Mb")`)

### Data generation DAG

```{r}
grViz('
digraph snakemake_dag {
    ratio=0.6
    graph[bgcolor=white, margin=0];
    node[shape=box, style=rounded, fontname=sans, fontsize=7, penwidth=2];
    edge[penwidth=2, color=grey];
	1[label = "website", color = "0.13 0.6 0.85", style="rounded"];
	2[label = "merge", color = "0.27 0.6 0.85", style="rounded"];
	3[label = "yaml", color = "0.40 0.6 0.85", style="rounded"];
	4[label = "Github", color = "0.07 0.6 0.85", style="rounded"];
	5[label = "S3 historical data", color = "0.20 0.6 0.85", style="rounded"];
	6[label = "metacran", color = "0.53 0.6 0.85", style="rounded"];
	7[label = "make shields", color = "0.33 0.6 0.85", style="rounded"];
	2 -> 1
	3 -> 2
	4 -> 2
	6 -> 2
	5 -> 2
	3 -> 4
	5 -> 4
	3 -> 6
	2 -> 7
}
')
```

### Available data



```{r}
dm(repos, people, help, commits,badges) %>%
  dm_add_pk(table = badges, columns = full_name) %>%
  dm_add_pk(table = repos, columns = full_name) %>%
  dm_add_pk(table = people, columns = author) %>%
  dm_add_pk(table = help, columns = full_name) %>%
  dm_add_pk(table = commits, columns = full_name) %>%
  dm_add_fk(table = repos, columns = full_name, ref_table = commits) %>%
  dm_add_fk(table = repos, columns = full_name, ref_table = help) %>%
  dm_add_fk(table = repos, columns = full_name, ref_table = badges) %>%
  dm_draw(
    view_type = "all", 
    column_types = TRUE, rankdir = "TB")
```

<!-- ### Links to all raw data -->

<!-- ```{r} -->
<!-- readRDS("scratch/s3_contents.rds") %>% knitr::kable() -->
<!-- ``` -->