In joebrew/vilaweb: Reproducible data analysis for www.vilaweb.cat

# Basic knitr options
library(knitr)
opts_chunk$set(comment = NA, 
               echo = FALSE, 
               warning = FALSE, 
               message = FALSE, 
               error = TRUE, 
               cache = FALSE,
               fig.path = 'figures/')

# Libraries
library(vilaweb)
library(rtweet)
library(tidyverse)
library(databrew)
library(translateR)
library(sentimentr) # https://github.com/trinker/sentimentr

# Define function for improving timeline
improve_timeline <- function(tmls){
  tmls$time_only <- sapply(strsplit(substr(tmls$created_at, 11,19), ":"),
                           function(x){as.numeric(x) %*% c(3600, 60, 1)})
  tmls$time_only <- tmls$time_only / 3600
  tmls$date <- as.Date(cut(tmls$created_at, 'day'))
  tmls$hour <- as.POSIXct(cut(tmls$created_at, 'hour'))
  return(tmls)
}

file_name <- '155ya.RData'
if(!file_name %in% dir()){
  rt <- search_tweets(
    '"#155YA"', 
    n = 1000000, 
    include_rts = T, 
    retryonratelimit = TRUE
  )
  save(rt, file = file_name)
} else {
  load(file_name)
}
message('---getting users')
users <- lookup_users(users = unique(rt$user_id))
save(users, file = '155ya_users.RData')
bots <- users %>% filter(followers_count <= 10)
# tls <- get_timelines(bots$screen_name, n = 3200)
# save(tls, bots, '155tls.RData')

joined <- rt %>%
  left_join(users %>% dplyr::select(account_created_at, screen_name))

users$x <- cut(users$account_created_at, 'day')
y <- users %>%
  group_by(x = as.Date(x)) %>%
  tally
ggplot(data = y %>% filter(x >= '2018-07-10'),
       aes(x = x,
           y = n)) +
  geom_bar(stat = 'identity')

users %>%
  filter(account_created_at >= '2018-12-18')
# ggplot(data = tls %>%
#          filter(date >= '2017-01-01'),
#        aes(x = time_only,
#            # y = as.factor(date),
#            y = date)) +
#   geom_point(size = 0.2,
#              aes(color = screen_name)) +
#   # geom_density_ridges() +
#   theme_minimal() +
#   theme(legend.position = 'none')
#   # facet_wrap(~screen_name,
#              # scales = 'free')
# 
# # Look at created_at, account_lang, 
# # profile_image_url: http://abs.twimg.com/sticky/default_profile_images/default_profile_normal.png