# install pacman once if not avaible on your machine
# install.packages("pacman")

pacman::p_load(tidyverse, rtweet, ggraph, igraph, tidygraph)

# twitter_token <- readRDS("twitter_token.rds")

rt <- search_tweets(
  "#ic2s2 OR #IC2S2", n = 5000, include_rts = T, retryonratelimit = T
)

save(rt, file = "data/rt.Rdata")

load("data/rt.Rdata")

rt %>% glimpse # the same as str, returns a df overview

# load("rt.Rdata")
rt %>% 
  filter(!is_retweet) %>% 
  select(screen_name, text, retweet_count) %>% 
  filter(!str_detect(text, "^RT")) %>% 
  mutate(text = str_replace_all(text, "\\\n", " ")) %>% 
  arrange(desc(retweet_count)) %>% 
  top_n(n = 10) %>% 
  knitr::kable(., format = "markdown")

rt %>%
  ## parse date format
  mutate(created_at = lubridate::as_datetime(created_at, "Europe/Germany")) %>% 
  mutate(
    cdate = created_at %>% 
      str_extract("\\d{4}-\\d{2}-\\d{2}") %>% 
      lubridate::ymd(),
    hour = lubridate::hour(created_at)
  ) %>% #select(created_at)
  ## select relevant time period
  filter(cdate >= as.Date("2019-07-17") & cdate <= as.Date("2019-07-20")) %>% 
  ## count tweet per and and hour
  group_by(cdate, hour) %>%
  tally %>%
  ungroup %>%
  ggplot(aes(hour, n)) +
  geom_line() +
  ## split the visualization 
  facet_wrap(~cdate, ncol = 1) +
  ggthemes::theme_hc() +
  scale_x_continuous(labels =  seq(5, 24, 3), breaks = seq(5, 24, 3)) +
  # scale_y_continuous(labels = seq(0, 60, 20), 
                     # breaks = seq(0, 60, 20), 
                     # minor_breaks = seq(0, 60, 20)) +
  ggtitle("Number of Tweets by Hour of the Day mentioning #ic2s2") +
  xlab("Hour of the Day") +
  ylab("Number of Tweets")

rt_graph <- rt %>% 
  ## select relevant variables
  dplyr::select(screen_name, retweet_screen_name) %>% 
  ## unnest list of mentions_screen_name
  unnest %>% 
  ## count the number of coocurences
  group_by(screen_name, retweet_screen_name) %>% 
  tally(sort = T) %>%
  ungroup %>% 
  ## drop missing values
  drop_na %>% 
  ## filter those coocurences that appear at least 2 times
  filter(n > 1) %>% 
  ## transforming the dataframe to a graph object
  as_tbl_graph() %>% 
  ## calculating node centrality
  mutate(centrality = centrality_degree(mode = 'in'))

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "kk") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Retweet Network")

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "kk") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## define node labels
  geom_node_text(aes(label = name), repel = T, fontface = "bold") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Retweet Network") +
  theme(plot.title = element_text(size = 20, hjust = 0.5))

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "circle") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## define node labels
  geom_node_text(aes(label = name), repel = F, fontface = "bold") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Retweet Network")

rt_graph <- rt %>% 
  ## remove retweets
  filter(!is_retweet) %>% 
  ## select relevant variables
  dplyr::select(screen_name, mentions_screen_name) %>% 
  ## unnest list of mentions_screen_name
  unnest %>% 
  ## count the number of coocurences
  group_by(screen_name, mentions_screen_name) %>% 
  tally(sort = T) %>%
  ungroup %>% 
  ## drop missing values
  drop_na %>% 
  ## filter those coocurences that appear at least 2 times
  filter(n > 1) %>% 
  ## transforming the dataframe to a graph object
  as_tbl_graph() %>% 
  ## calculating node centrality
  mutate(centrality = centrality_degree(mode = 'in'))

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "kk") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Twitter Mentions Network")

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "kk") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## define node labels
  geom_node_text(aes(label = name), repel = T, fontface = "bold") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Twitter Mentions Network")

rt_graph %>% 
  ## create graph layout
  ggraph(layout = "circle") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## define node labels
  geom_node_text(aes(label = name), repel = F, fontface = "bold") +
  ## equal width and height
  coord_fixed() +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Twitter Mentions Network")

rt_graph2 <- rt %>% 
  ## select relevant variables
  dplyr::select(screen_name, mentions_screen_name) %>% 
  ## unnest list of mentions_screen_name
  unnest %>% 
  ## count the number of coocurences
  group_by(screen_name, mentions_screen_name) %>% 
  tally(sort = T) %>%
  ungroup %>% 
  ## drop missing values
  drop_na %>% 
  ## filter those coocurences that appear more than 2 times
  filter(n > 2) %>% 
  ## transforming the dataframe to a graph object
  as_tbl_graph() %>% 
  ## calculating node centrality
  mutate(centrality = centrality_degree(mode = 'in'))

rt_graph2 %>% 
  ## create graph layout
  ggraph(layout = "kk") + 
  ## define edge aestetics
  geom_edge_fan(aes(alpha = n, edge_width = n, color = n)) + 
  ## scale down link saturation
  scale_edge_alpha(range = c(.5, .9)) +
  ## define note size param
  scale_edge_color_gradient(low = "gray50", high = "#1874CD") +
  geom_node_point(aes(size = centrality), color = "gray30") +
  ## equal width and height
  coord_fixed() +
  geom_node_text(aes(label = name), repel = T, fontface = "bold") +
  ## plain theme
  theme_void() +
  ## title
  ggtitle("#ic2s2 Twitter Mentions Network")

rt_hashtags <- rt %>% 
  filter(!is_retweet) %>% 
  select(hashtags) %>% 
  ## unnest list of hastags
  unnest %>% 
    na.omit %>% 
  ## clean hashtags
  mutate(hashtags = stringr::str_to_lower(hashtags) %>% 
           str_replace_all("2018", "18") %>% 
           ## add #symbol to vector
           paste0("#", .)) %>% 
  ## count each hashtag and sort
  count(hashtags, sort = T) %>% 
  filter(n > 5)

rt_hashtags %>% 
  filter(hashtags != "#ic2s2") %>%
  mutate(hashtags = forcats::fct_reorder(hashtags, n)) %>% 
  ggplot(aes(hashtags, n)) +
  geom_bar(stat = "identity", alpha = .7) +
  coord_flip() +
  theme_minimal() +
  ggtitle("Most Frequent Hastags related to #ic2s2")

gg_bigram <- rt %>%
  ## remove retweets
  filter(!is_retweet) %>% 
  select(text) %>% 
  ## remove text noise
  mutate(text = stringr::str_remove_all(text, "w |amp ")) %>% 
  ## remove retweets
  filter(!stringr::str_detect(text, "^RT")) %>% 
  ## remove urls
  mutate(text = stringr::str_remove_all(text, "https?[:]//[[:graph:]]+")) %>% 
  mutate(id = 1:n()) %>% 
  ## split text into words
  tidytext::unnest_tokens(word, text, token = "words") %>% 
  ## remove stop words
  anti_join(tidytext::stop_words) %>% 
  ## paste words to text by id
  group_by(id) %>% 
  summarise(text = paste(word, collapse = " ")) %>% 
  ungroup %>% 
  ## again split text into bigrams (word occurences or collocations)
  tidytext::unnest_tokens(bigram, text, token = "ngrams", n = 2) %>% 
  separate(bigram, c("word1", "word2"), sep = " ") %>% 
  ## remove the hashtag and count bigrams 
  filter(word1 != "ic2s2", word2 != "ic2s2") %>%
  count(word1, word2, sort = T) %>% 
  ## select first 50
  slice(1:50) %>% 
  drop_na() %>%
  ## create tidy graph object
  as_tbl_graph() %>% 
  ## calculate node centrality
  mutate(centrality = centrality_degree(mode = 'in'))

gg_bigram %>% 
  ggraph() +
  geom_edge_link(aes(edge_alpha = n, edge_width = n)) +
  geom_node_point(aes(size = centrality)) + 
  geom_node_text(aes(label = name),  repel = TRUE) +
  theme_void() +
  scale_edge_alpha("", range = c(0.3, .6)) +
  ggtitle("Top Bigram Network from Tweets using hashtag #ic2s2")

sessionInfo()