shhh <- function(expr) suppressPackageStartupMessages(suppressWarnings(suppressMessages(expr)))
shhh({
    library(tidyverse); library(lubridate)
    library(scales); library(data.table)
})


query <- 
"
SELECT
    event.editing_session_id as edit_attempt_id, 
    wiki,  
    event.platform as platform, 
    useragent.browser_family as browser_family, 
    useragent.os_family as os_family, 
    event.editor_interface as interface, 
    if(event.user_id != 0, concat(wiki, '-', event.user_id), event.anonymous_user_token) as user_id,
    event.user_id = 0 as user_is_anonymous_byid, 
    if(event.anonymous_user_token is NULL, false, true) as user_is_anonymous_bytoken, 
    event.user_id != 0 as user_is_registered, 
    event.action as action,
    event.init_timing as init_timing,
    event.bucket,  
    geocoded_data['country'] as country,
    event.user_editcount as user_edit_count
FROM event.editattemptstep
WHERE
    event.bucket in ('default-visual', 'default-source') and
    year = 2019 and (
        month = 7 and day >= 14 or
        month >= 8)
"


sessions = wmf::query_hive(query)

#recheck overall user bucket number to confirm any changes imbalance 

sessions_all <- sessions %>%
  group_by(bucket) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id))

sessions_all

## Break down by anonymous users to identify any discrepancy that occurs there

sessions_anonymous <- sessions %>%
  filter(user_is_anonymous_byid == 'true') %>%
  group_by(bucket) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id))

sessions_anonymous

## Look at user_isanonymous_bytoken to confirm it matches with user_is_anonymous_byid

sessions_anonymous_bytoken <- sessions %>%
  filter(user_is_anonymous_bytoken == "true") %>%
  group_by(bucket) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id))

sessions_anonymous_bytoken

## Break down by registered users to identify any discrepancy that occurs there

sessions_registered <- sessions %>%
  filter(user_is_registered == "true") %>%
  group_by(bucket) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id))

sessions_registered

sessions_bybrowser <- sessions %>%
  group_by(bucket, browser_family) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id)) %>%
  arrange(browser_family)

head(sessions_bybrowser)

sessions_bybrowser$users <- as.numeric(sessions_bybrowser$users)
sessions_bybrowser$attempts <- as.numeric(sessions_bybrowser$attempts)

sessions_bybrowser$bucket[sessions_bybrowser$bucket == "default-source"] <- "default_source"
sessions_bybrowser$bucket[sessions_bybrowser$bucket == "default-visual"] <- "default_visual"


# Look at test bucket user counts for top browsers 
sessions_bybrowser_plot <- sessions_bybrowser %>%
  filter(browser_family %in% c('Chrome Mobile', 'Mobile Safari', 'Samsung Internet', 'Chrome', 
                              'Chrome Mobile WebView', 'UC Browser', 'Opera Mobile', 'Firefox Mobile',
                              'Chrome Mobile iOS', 'Facebook', 'Android', 'Mobile Safari UI/WKWebView',
                              'Edge Mobile', 'Edge')) %>% # filter to top browsers for plot visibility
  ggplot(aes(x= browser_family, y = users, fill = bucket)) +
  geom_col() +
   scale_y_continuous("user counts") +
    labs(title = "Editor test bucket user counts by browser") +
    ggthemes::theme_tufte(base_size = 10, base_family = "Gill Sans") +
    theme(axis.text.x=element_text(angle = 45, hjust = 1),
        plot.title = element_text(hjust = 0.5),
        panel.grid = element_line("gray70"),
        legend.position= "none")


sessions_bybrowser_plot

sessions_bybrowser_percent_imbalance <- sessions_bybrowser %>%
 select(-4)  %>% ##look at user counts only
 spread(bucket,users) %>% 
 #mutate(percent_diff = round(abs((default_source-default_visual)/default_visual *100), 3)) %>%
 mutate(percent_wikitext_users = default_source/(default_source + default_visual) *100) %>%
 arrange(desc(percent_wikitext_users)) 

head(sessions_bybrowser_percent_imbalance)

sessions_bycountry <- sessions %>%
  group_by(bucket, country) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id)) %>%
  arrange(country, users) 

head(sessions_bycountry)


sessions_bywiki <- sessions %>%
  group_by(bucket, wiki) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id)) %>%
  arrange(wiki) 

sessions_bywiki

sessions_bywiki$users <- as.numeric(sessions_bywiki$users)
sessions_bywiki$attempts <- as.numeric(sessions_bywiki$attempts)

sessions_bywiki$bucket[sessions_bywiki$bucket == "default-source"] <- "default_source"
sessions_bywiki$bucket[sessions_bywiki$bucket == "default-visual"] <- "default_visual"

sessions_bywiki_percent_imbalance <- sessions_bywiki %>%
 select(-4)  %>% ##look at user counts only
 spread(bucket,users) %>% 
 #mutate(percent_diff = round(abs((default_source-default_visual)/default_visual *100), 3)) %>%
 mutate(percent_wikitext_users = default_source/(default_source + default_visual) *100) %>%
 arrange(desc(percent_wikitext_users)) 

head(sessions_bywiki_percent_imbalance)

Unable to isolate the imblance to a particular wiki. Similar imblance trends seen.

sessions_byaction <- sessions %>%
  group_by(bucket, action) %>%
  summarise(users = n_distinct(user_id),
        attempts = n_distinct(edit_attempt_id)) %>%
  arrange(action) 

sessions_byaction