From 66c07118722c5dc1b98cbce2290ecae6aad17fb1 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 15 Apr 2024 22:36:16 +0000
Subject: [PATCH] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 ...s by genre category- Numbers over time.Rmd | 562 +++++++++---------
 src/narges/RQ-Trello.Rmd                      |  56 +-
 2 files changed, 319 insertions(+), 299 deletions(-)

diff --git a/code/narges/Visualization- Society-related genres by genre category- Numbers over time.Rmd b/code/narges/Visualization- Society-related genres by genre category- Numbers over time.Rmd
index defffd0f6..4930b37d7 100644
--- a/code/narges/Visualization- Society-related genres by genre category- Numbers over time.Rmd	
+++ b/code/narges/Visualization- Society-related genres by genre category- Numbers over time.Rmd	
@@ -22,19 +22,21 @@ pp <- function(percentage, accuracy = 0.01) {
 ```
 
 ```{r}
-#fbs_records_a
+# fbs_records_a
 ```
 
 ```{r}
-fbs_links_a <- select(fbs_links_a,-c('method'))
+fbs_links_a <- select(fbs_links_a, -c("method"))
 ```
 
 ```{r}
-fbs_records <- fbs_records_a %>% inner_join(vd17_id_a) %>% inner_join(fbs_links_a, by=('record_number')) %>%
-  inner_join(fbs_metadata_a%>% select(GND,member_number,First_name_new,Last_name_new,Estimated_admission_year))%>%
-  mutate(first_name=First_name_new,last_name=Last_name_new,admission_year=Estimated_admission_year)%>%
-  collect()%>%
-  select('record_number','vd17_id','member_number','method','set','first_name','last_name','admission_year')
+fbs_records <- fbs_records_a %>%
+  inner_join(vd17_id_a) %>%
+  inner_join(fbs_links_a, by = ("record_number")) %>%
+  inner_join(fbs_metadata_a %>% select(GND, member_number, First_name_new, Last_name_new, Estimated_admission_year)) %>%
+  mutate(first_name = First_name_new, last_name = Last_name_new, admission_year = Estimated_admission_year) %>%
+  collect() %>%
+  select("record_number", "vd17_id", "member_number", "method", "set", "first_name", "last_name", "admission_year")
 ```
 
 
@@ -45,37 +47,37 @@ vd17_normalized_years_local <- vd17_normalized_years_a %>%
 
 
 ```{r}
-#vd17_genres_local <- vd17_genres_a %>%
-  #collect()%>%
-  #select(record_number,genre)
+# vd17_genres_local <- vd17_genres_a %>%
+# collect()%>%
+# select(record_number,genre)
 
-#genre_cat1 <- vd17_genres_local%>%
-  #filter(grepl(paste(c(genre_list1_a,genre_list1_b,genre_list1_c,genre_list1_d,genre_list1_e,genre_list1_f,genre_list1_g,genre_list1_h,genre_list1_i),collapse="|"), genre))%>%
-  #select(record_number,genre)
+# genre_cat1 <- vd17_genres_local%>%
+# filter(grepl(paste(c(genre_list1_a,genre_list1_b,genre_list1_c,genre_list1_d,genre_list1_e,genre_list1_f,genre_list1_g,genre_list1_h,genre_list1_i),collapse="|"), genre))%>%
+# select(record_number,genre)
 ```
 
 
 ```{r}
 core_society <- fbs_records %>%
-  filter(set=="Society-contributed and society-purpose related")
+  filter(set == "Society-contributed and society-purpose related")
 society_interest <- fbs_records %>%
-  filter(set=="Society-contributed")
+  filter(set == "Society-contributed")
 ```
 
 ```{r}
 vd17_normalized_langs_local <- vd17_normalized_langs_a %>%
-  collect()%>%
-  filter(publication_language=="ger")
+  collect() %>%
+  filter(publication_language == "ger")
 ```
 
 # Visualization: Overall output of Society members in German: Numbers over time
 ```{r}
 fbs_german <- fbs_records %>%
-  inner_join(vd17_normalized_langs_local, by=c("record_number"))%>%
+  inner_join(vd17_normalized_langs_local, by = c("record_number")) %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  select(record_number,normalized_year,vd17_id)%>%
+  filter(nchar(normalized_year) == 4) %>%
+  select(record_number, normalized_year, vd17_id) %>%
   group_by(normalized_year) %>%
   summarize(records = n_distinct(record_number), .groups = "drop") %>%
   mutate(phase = case_when(
@@ -84,50 +86,52 @@ fbs_german <- fbs_records %>%
     normalized_year >= 1651 & normalized_year <= 1667 ~ "phase 2",
     normalized_year >= 1668 & normalized_year <= 1682 ~ "phase 3",
     normalized_year > 1682 ~ "> 1682"
-  ))%>%
+  )) %>%
   distinct()
 
-group.colors <- c("< 1617" = "grey", "phase 1" = "cyan", "phase 2" ="#9633FF", "phase 3" = "pink", "> 1682" = "grey")
-fbs_german%>%
-  ggplot(aes(x=normalized_year, y=records, fill = phase)) + 
-  geom_col()+
-  xlab("Year") + ylab("")+
-  ggtitle("Member Publications in German")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 500, by = 50))+
-  theme_hsci_discrete()+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  scale_fill_manual(values=group.colors)
-
+group.colors <- c("< 1617" = "grey", "phase 1" = "cyan", "phase 2" = "#9633FF", "phase 3" = "pink", "> 1682" = "grey")
+fbs_german %>%
+  ggplot(aes(x = normalized_year, y = records, fill = phase)) +
+  geom_col() +
+  xlab("Year") +
+  ylab("") +
+  ggtitle("Member Publications in German") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 500, by = 50)) +
+  theme_hsci_discrete() +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  scale_fill_manual(values = group.colors)
 ```
 
 # Visualization: Overall output of Society members in German: Average output by member over time
 # Considering 10 years prior to admission_year
 ```{r}
 fbs_records_german <- fbs_records %>%
-  inner_join(vd17_normalized_langs_local, by=c("record_number"))%>%
+  inner_join(vd17_normalized_langs_local, by = c("record_number")) %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  select(record_number,normalized_year,vd17_id,member_number,admission_year)
-
-fbs_records_10 <-fbs_records_german%>%
-  filter((admission_year>=(normalized_year-10))&(admission_year<=normalized_year))%>%
-  with(aggregate(member_number ~ normalized_year,FUN=function(x){length(unique(x))}))%>%
-  mutate(n_active_members=member_number)%>%
-  select(n_active_members,normalized_year)
-
-fbs_records_german_10 <- fbs_records_german %>% 
-  left_join(fbs_records_10,by=c("normalized_year"))%>%
+  filter(nchar(normalized_year) == 4) %>%
+  select(record_number, normalized_year, vd17_id, member_number, admission_year)
+
+fbs_records_10 <- fbs_records_german %>%
+  filter((admission_year >= (normalized_year - 10)) & (admission_year <= normalized_year)) %>%
+  with(aggregate(member_number ~ normalized_year, FUN = function(x) {
+    length(unique(x))
+  })) %>%
+  mutate(n_active_members = member_number) %>%
+  select(n_active_members, normalized_year)
+
+fbs_records_german_10 <- fbs_records_german %>%
+  left_join(fbs_records_10, by = c("normalized_year")) %>%
   distinct()
-  
+
 number_year_10 <- fbs_records_german_10 %>%
-  group_by(normalized_year,n_active_members) %>%
+  group_by(normalized_year, n_active_members) %>%
   summarize(number_pub = n_distinct(record_number), .groups = "drop")
 
-number_year_10$average_output=round(number_year_10$number_pub / number_year_10$n_active_members)
-number_year_10$number_of_years_prior_to_admission="10"
+number_year_10$average_output <- round(number_year_10$number_pub / number_year_10$n_active_members)
+number_year_10$number_of_years_prior_to_admission <- "10"
 
 number_year_10 <- number_year_10 %>%
   distinct()
@@ -135,23 +139,24 @@ number_year_10 <- number_year_10 %>%
 
 # Considering 20 years prior to admission_year
 ```{r}
-
-fbs_records_20 <-fbs_records_german%>%
-  filter((admission_year>=(normalized_year-20))&(admission_year<=normalized_year))%>%
-  with(aggregate(member_number ~ normalized_year,FUN=function(x){length(unique(x))}))%>%
-  mutate(n_active_members=member_number)%>%
-  select(n_active_members,normalized_year)
-
-fbs_records_german_20 <- fbs_records_german %>% 
-  left_join(fbs_records_20,by=c("normalized_year"))%>%
+fbs_records_20 <- fbs_records_german %>%
+  filter((admission_year >= (normalized_year - 20)) & (admission_year <= normalized_year)) %>%
+  with(aggregate(member_number ~ normalized_year, FUN = function(x) {
+    length(unique(x))
+  })) %>%
+  mutate(n_active_members = member_number) %>%
+  select(n_active_members, normalized_year)
+
+fbs_records_german_20 <- fbs_records_german %>%
+  left_join(fbs_records_20, by = c("normalized_year")) %>%
   distinct()
-  
+
 number_year_20 <- fbs_records_german_20 %>%
-  group_by(normalized_year,n_active_members) %>%
+  group_by(normalized_year, n_active_members) %>%
   summarize(number_pub = n_distinct(record_number), .groups = "drop")
 
-number_year_20$average_output=round(number_year_20$number_pub / number_year_20$n_active_members)
-number_year_20$number_of_years_prior_to_admission="20"
+number_year_20$average_output <- round(number_year_20$number_pub / number_year_20$n_active_members)
+number_year_20$number_of_years_prior_to_admission <- "20"
 
 number_year_20 <- number_year_20 %>%
   distinct()
@@ -159,23 +164,24 @@ number_year_20 <- number_year_20 %>%
 
 # Considering 30 years prior to admission_year
 ```{r}
-
-fbs_records_30 <-fbs_records_german%>%
-  filter((admission_year>=(normalized_year-30))&(admission_year<=normalized_year))%>%
-  with(aggregate(member_number ~ normalized_year,FUN=function(x){length(unique(x))}))%>%
-  mutate(n_active_members=member_number)%>%
-  select(n_active_members,normalized_year)
-
-fbs_records_german_30 <- fbs_records_german %>% 
-  left_join(fbs_records_30,by=c("normalized_year"))%>%
+fbs_records_30 <- fbs_records_german %>%
+  filter((admission_year >= (normalized_year - 30)) & (admission_year <= normalized_year)) %>%
+  with(aggregate(member_number ~ normalized_year, FUN = function(x) {
+    length(unique(x))
+  })) %>%
+  mutate(n_active_members = member_number) %>%
+  select(n_active_members, normalized_year)
+
+fbs_records_german_30 <- fbs_records_german %>%
+  left_join(fbs_records_30, by = c("normalized_year")) %>%
   distinct()
-  
+
 number_year_30 <- fbs_records_german_30 %>%
-  group_by(normalized_year,n_active_members) %>%
+  group_by(normalized_year, n_active_members) %>%
   summarize(number_pub = n_distinct(record_number), .groups = "drop")
 
-number_year_30$average_output=round(number_year_30$number_pub / number_year_30$n_active_members)
-number_year_30$number_of_years_prior_to_admission="30"
+number_year_30$average_output <- round(number_year_30$number_pub / number_year_30$n_active_members)
+number_year_30$number_of_years_prior_to_admission <- "30"
 
 number_year_30 <- number_year_30 %>%
   distinct()
@@ -183,111 +189,116 @@ number_year_30 <- number_year_30 %>%
 
 # Considering 40 years prior to admission_year
 ```{r}
-
-fbs_records_40 <-fbs_records_german%>%
-  filter((admission_year>=(normalized_year-40))&(admission_year<=normalized_year))%>%
-  with(aggregate(member_number ~ normalized_year,FUN=function(x){length(unique(x))}))%>%
-  mutate(n_active_members=member_number)%>%
-  select(n_active_members,normalized_year)
-
-fbs_records_german_40 <- fbs_records_german %>% 
-  left_join(fbs_records_40,by=c("normalized_year"))%>%
+fbs_records_40 <- fbs_records_german %>%
+  filter((admission_year >= (normalized_year - 40)) & (admission_year <= normalized_year)) %>%
+  with(aggregate(member_number ~ normalized_year, FUN = function(x) {
+    length(unique(x))
+  })) %>%
+  mutate(n_active_members = member_number) %>%
+  select(n_active_members, normalized_year)
+
+fbs_records_german_40 <- fbs_records_german %>%
+  left_join(fbs_records_40, by = c("normalized_year")) %>%
   distinct()
-  
+
 number_year_40 <- fbs_records_german_40 %>%
-  group_by(normalized_year,n_active_members) %>%
+  group_by(normalized_year, n_active_members) %>%
   summarize(number_pub = n_distinct(record_number), .groups = "drop")
 
-number_year_40$average_output=round(number_year_40$number_pub / number_year_40$n_active_members)
-number_year_40$number_of_years_prior_to_admission="40"
+number_year_40$average_output <- round(number_year_40$number_pub / number_year_40$n_active_members)
+number_year_40$number_of_years_prior_to_admission <- "40"
 
 number_year_40 <- number_year_40 %>%
   distinct()
 ```
 
 ```{r}
-avg_number_per_year <- rbind(number_year_10,number_year_20,number_year_30,number_year_40)
-
+avg_number_per_year <- rbind(number_year_10, number_year_20, number_year_30, number_year_40)
 ```
 
 ```{r}
-#avg_number_per_year%>%
-  #ggplot(aes(x=normalized_year,y=average_output,fill=number_of_years_prior_to_admission))+
-  #geom_col()+
-  #ggtitle("Average Number of Member Publications in German")+
-  #xlab("") + ylab("")+
-  #scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  #scale_y_continuous(breaks = seq(0, 300, by = 10))+
-  #theme_hsci_discrete()+
-  #theme(plot.title = element_text(hjust = 0.5))+
-  #theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
+# avg_number_per_year%>%
+# ggplot(aes(x=normalized_year,y=average_output,fill=number_of_years_prior_to_admission))+
+# geom_col()+
+# ggtitle("Average Number of Member Publications in German")+
+# xlab("") + ylab("")+
+# scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
+# scale_y_continuous(breaks = seq(0, 300, by = 10))+
+# theme_hsci_discrete()+
+# theme(plot.title = element_text(hjust = 0.5))+
+# theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
 ```
 
 
 ```{r}
 library(ggalt)
-avg10<-number_year_10%>%
-  ggplot(aes(x=normalized_year,y=average_output))+
-  geom_xspline(color="blue")+
-  ggtitle("10 years")+
-  xlab("") + ylab("")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 300, by = 10))+
-  theme_hsci_discrete()+
-  theme(plot.title = element_text(hjust = 0.5))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
-
-avg20<-number_year_20%>%
-  ggplot(aes(x=normalized_year,y=average_output))+
-  geom_xspline(color="green")+
-  ggtitle("20 years")+
-  xlab("") + ylab("")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 300, by = 10))+
-  theme_hsci_discrete()+
-  theme(plot.title = element_text(hjust = 0.5))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
-
-avg30<-number_year_30%>%
-  ggplot(aes(x=normalized_year,y=average_output))+
-  geom_xspline(color="red")+
-  ggtitle("30 years")+
-  xlab("") + ylab("")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 300, by = 10))+
-  theme_hsci_discrete()+
-  theme(plot.title = element_text(hjust = 0.5))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
-
-avg40<-number_year_40%>%
-  ggplot(aes(x=normalized_year,y=average_output))+
-  geom_xspline(color="purple")+
-  ggtitle("40 years")+
-  xlab("") + ylab("")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 300, by = 10))+
-  theme_hsci_discrete()+
-  theme(plot.title = element_text(hjust = 0.5))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
-
-plot <- ggarrange(avg10,avg20,avg30,avg40,nrow = 2,ncol = 2)
-annotate_figure(plot, top = text_grob("Average number of member publications in German per active person per year, with active persons calculated as having joined at most 20/40/60 years prior to the year under calculation", 
-               color = "black", face = "bold", size = 9))
+avg10 <- number_year_10 %>%
+  ggplot(aes(x = normalized_year, y = average_output)) +
+  geom_xspline(color = "blue") +
+  ggtitle("10 years") +
+  xlab("") +
+  ylab("") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 300, by = 10)) +
+  theme_hsci_discrete() +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
+
+avg20 <- number_year_20 %>%
+  ggplot(aes(x = normalized_year, y = average_output)) +
+  geom_xspline(color = "green") +
+  ggtitle("20 years") +
+  xlab("") +
+  ylab("") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 300, by = 10)) +
+  theme_hsci_discrete() +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
+
+avg30 <- number_year_30 %>%
+  ggplot(aes(x = normalized_year, y = average_output)) +
+  geom_xspline(color = "red") +
+  ggtitle("30 years") +
+  xlab("") +
+  ylab("") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 300, by = 10)) +
+  theme_hsci_discrete() +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
+
+avg40 <- number_year_40 %>%
+  ggplot(aes(x = normalized_year, y = average_output)) +
+  geom_xspline(color = "purple") +
+  ggtitle("40 years") +
+  xlab("") +
+  ylab("") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 300, by = 10)) +
+  theme_hsci_discrete() +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
+
+plot <- ggarrange(avg10, avg20, avg30, avg40, nrow = 2, ncol = 2)
+annotate_figure(plot, top = text_grob("Average number of member publications in German per active person per year, with active persons calculated as having joined at most 20/40/60 years prior to the year under calculation",
+  color = "black", face = "bold", size = 9
+))
 ```
 ```{r}
 vd17_genre_categorisation_a
 ```
 
 ```{r}
-#list_society_genre <- c("Lyrik/Poetry","Drama/Theatre","Epik/Prose","Other Literature Related","Linguistic and Language","Virtue, Civility and Ethics","Other Society Related","Occasional Literature","German as a scientific language")
-vd17_society_genres <- vd17_genre_categorisation_a%>%
-  left_join(vd17_genres_a,by=c("genre"))%>%
-  collect()%>%
-  filter(!(group_2=="Formats"))%>%
-  mutate(genre_category=group_2,genre_group=group_1)%>%
-  select(record_number,genre_category,genre_group,genre)
-  
-vd17_society_genres$genre_category[vd17_society_genres$genre_category == 'General works'] <- 'General Works'
+# list_society_genre <- c("Lyrik/Poetry","Drama/Theatre","Epik/Prose","Other Literature Related","Linguistic and Language","Virtue, Civility and Ethics","Other Society Related","Occasional Literature","German as a scientific language")
+vd17_society_genres <- vd17_genre_categorisation_a %>%
+  left_join(vd17_genres_a, by = c("genre")) %>%
+  collect() %>%
+  filter(!(group_2 == "Formats")) %>%
+  mutate(genre_category = group_2, genre_group = group_1) %>%
+  select(record_number, genre_category, genre_group, genre)
+
+vd17_society_genres$genre_category[vd17_society_genres$genre_category == "General works"] <- "General Works"
 ```
 
 # Visualization: Society-related genres by genre category: Numbers over time
@@ -295,17 +306,17 @@ vd17_society_genres$genre_category[vd17_society_genres$genre_category == 'Genera
 core_society_genre <- core_society %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  left_join(vd17_society_genres,by = c("record_number"))%>%
-  select(record_number,normalized_year,vd17_id,genre_category,genre_group,genre)%>%
+  filter(nchar(normalized_year) == 4) %>%
+  left_join(vd17_society_genres, by = c("record_number")) %>%
+  select(record_number, normalized_year, vd17_id, genre_category, genre_group, genre) %>%
   distinct()
 
 society_interest_genre <- society_interest %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  left_join(vd17_society_genres,by = c("record_number"))%>%
-  select(record_number,normalized_year,vd17_id,genre_category,genre_group,genre)%>%
+  filter(nchar(normalized_year) == 4) %>%
+  left_join(vd17_society_genres, by = c("record_number")) %>%
+  select(record_number, normalized_year, vd17_id, genre_category, genre_group, genre) %>%
   distinct()
 ```
 
@@ -315,163 +326,172 @@ colour_list <- c(
   "dodgerblue2", "#E31A1C",
   "green4",
   "#6A3D9A",
-  "#FF7F00", 
+  "#FF7F00",
   "black", "gold1",
   "skyblue2", "#FB9A99",
   "palegreen2",
-  "#CAB2D6", 
+  "#CAB2D6",
   "#FDBF6F",
   "gray70", "khaki2",
   "maroon", "orchid1", "deeppink1"
 )
-plot1 <-core_society_genre%>%
-  group_by(normalized_year)%>%
-  count(genre_category,genre_group)%>%
-  arrange(desc(n))%>%
-  distinct()%>%
-  ggplot(aes(x = normalized_year, y = n, fill= genre_category,colour = genre_category)) + geom_point(size = 3)+
-  ggtitle("Member Publications in Society-Related Genre Categories (core_society)")+
-  ylab("")+xlab("Year")+
+plot1 <- core_society_genre %>%
+  group_by(normalized_year) %>%
+  count(genre_category, genre_group) %>%
+  arrange(desc(n)) %>%
+  distinct() %>%
+  ggplot(aes(x = normalized_year, y = n, fill = genre_category, colour = genre_category)) +
+  geom_point(size = 3) +
+  ggtitle("Member Publications in Society-Related Genre Categories (core_society)") +
+  ylab("") +
+  xlab("Year") +
   scale_x_continuous(breaks = seq(1000, 2000, by = 3)) +
   scale_y_continuous(breaks = seq(0, 500, by = 50)) +
   theme_hsci_discrete() +
-  theme(legend.position="bottom",legend.text=element_text(size=15))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),,text = element_text(size = 15))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  facet_wrap(~ genre_group)
-
-plot2 <-society_interest_genre%>%
-  group_by(normalized_year)%>%
-  count(genre_category,genre_group)%>%
-  arrange(desc(n))%>%
-  distinct()%>%
-  ggplot(aes(x = normalized_year, y = n, fill= genre_category,colour = genre_category)) + geom_point(size = 3)+
-  ggtitle("Member Publications in Society-Related Genre Categories (links_of_interest)")+
-  ylab("")+xlab("Year")+
+  theme(legend.position = "bottom", legend.text = element_text(size = 15)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), , text = element_text(size = 15)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  facet_wrap(~genre_group)
+
+plot2 <- society_interest_genre %>%
+  group_by(normalized_year) %>%
+  count(genre_category, genre_group) %>%
+  arrange(desc(n)) %>%
+  distinct() %>%
+  ggplot(aes(x = normalized_year, y = n, fill = genre_category, colour = genre_category)) +
+  geom_point(size = 3) +
+  ggtitle("Member Publications in Society-Related Genre Categories (links_of_interest)") +
+  ylab("") +
+  xlab("Year") +
   scale_x_continuous(breaks = seq(1000, 2000, by = 3)) +
   scale_y_continuous(breaks = seq(0, 500, by = 50)) +
   theme_hsci_discrete() +
-  theme(legend.position="bottom",legend.text=element_text(size=15))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),text = element_text(size = 15))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  facet_wrap(~ genre_group)
-
-ggarrange(plot1,plot2,nrow = 2,ncol = 1)
-ggsave(file="plot1.jpg", width=20, height=20, dpi=200)
+  theme(legend.position = "bottom", legend.text = element_text(size = 15)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), text = element_text(size = 15)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  facet_wrap(~genre_group)
 
+ggarrange(plot1, plot2, nrow = 2, ncol = 1)
+ggsave(file = "plot1.jpg", width = 20, height = 20, dpi = 200)
 ```
 
 # Visualization: Society-related genres by genre category: Proportion over time
 
 ```{r}
-core_society_frequency <- core_society_genre%>%
-  select(vd17_id,record_number,normalized_year,genre,genre_category,genre_group)%>%
-  distinct(vd17_id,record_number,normalized_year,genre,genre_category,genre_group)%>%
-  group_by(normalized_year)%>%
-  count(genre_category,genre_group)%>%
-  arrange(desc(n))%>%
-  mutate(percentage=n/sum(n))%>%
+core_society_frequency <- core_society_genre %>%
+  select(vd17_id, record_number, normalized_year, genre, genre_category, genre_group) %>%
+  distinct(vd17_id, record_number, normalized_year, genre, genre_category, genre_group) %>%
+  group_by(normalized_year) %>%
+  count(genre_category, genre_group) %>%
+  arrange(desc(n)) %>%
+  mutate(percentage = n / sum(n)) %>%
   distinct()
 
-society_interest_frequency <- society_interest_genre%>%
-  select(vd17_id,record_number,normalized_year,genre,genre_category,genre_group)%>%
-  distinct(vd17_id,record_number,normalized_year,genre,genre_category,genre_group)%>%
-  group_by(normalized_year)%>%
-  count(genre_category,genre_group)%>%
-  arrange(desc(n))%>%
-  mutate(percentage=n/sum(n))%>%
+society_interest_frequency <- society_interest_genre %>%
+  select(vd17_id, record_number, normalized_year, genre, genre_category, genre_group) %>%
+  distinct(vd17_id, record_number, normalized_year, genre, genre_category, genre_group) %>%
+  group_by(normalized_year) %>%
+  count(genre_category, genre_group) %>%
+  arrange(desc(n)) %>%
+  mutate(percentage = n / sum(n)) %>%
   distinct()
-
 ```
 
 ```{r}
-p1 <-core_society_frequency%>%
-  ggplot(aes(x = normalized_year, y = percentage, fill= genre_category,colour = genre_category)) + geom_point(size = 3)+
-  ggtitle("Member Publications in Society-Related Genres (core_society)")+
-  ylab("")+xlab("Year")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(labels = scales::percent)+
-  theme_hsci_discrete()+
-  theme(legend.position="bottom",legend.text=element_text(size=15))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),,text = element_text(size = 15))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  facet_wrap(~ genre_group)
-
-p2 <-society_interest_frequency%>%
-  ggplot(aes(x = normalized_year, y = percentage, fill= genre_category,colour = genre_category)) + geom_point(size = 3)+
-  ggtitle("Member Publications in Society-Related Genres (links_of_interest)")+
-  ylab("")+xlab("Year")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(labels = scales::percent)+
-  theme_hsci_discrete()+
-  theme(legend.position="bottom",legend.text=element_text(size=15))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),,text = element_text(size = 15))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  facet_wrap(~ genre_group)
-
-ggarrange(p1,p2,nrow = 2,ncol = 1)
-ggsave(file="plot2.jpg", width=20, height=20, dpi=200)
+p1 <- core_society_frequency %>%
+  ggplot(aes(x = normalized_year, y = percentage, fill = genre_category, colour = genre_category)) +
+  geom_point(size = 3) +
+  ggtitle("Member Publications in Society-Related Genres (core_society)") +
+  ylab("") +
+  xlab("Year") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(labels = scales::percent) +
+  theme_hsci_discrete() +
+  theme(legend.position = "bottom", legend.text = element_text(size = 15)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), , text = element_text(size = 15)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  facet_wrap(~genre_group)
+
+p2 <- society_interest_frequency %>%
+  ggplot(aes(x = normalized_year, y = percentage, fill = genre_category, colour = genre_category)) +
+  geom_point(size = 3) +
+  ggtitle("Member Publications in Society-Related Genres (links_of_interest)") +
+  ylab("") +
+  xlab("Year") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(labels = scales::percent) +
+  theme_hsci_discrete() +
+  theme(legend.position = "bottom", legend.text = element_text(size = 15)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), , text = element_text(size = 15)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  facet_wrap(~genre_group)
+
+ggarrange(p1, p2, nrow = 2, ncol = 1)
+ggsave(file = "plot2.jpg", width = 20, height = 20, dpi = 200)
 ```
 
 
 # Visualization: Comparison with VD17: Society-related genre categories
 ```{r}
-vd17_local_id <- vd17_id_a%>%
+vd17_local_id <- vd17_id_a %>%
   collect()
 genres_vd17_society <- vd17_local_id %>%
-  inner_join(vd17_normalized_langs_local, by=c("record_number"))%>%
+  inner_join(vd17_normalized_langs_local, by = c("record_number")) %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  left_join(vd17_society_genres,by = c("record_number"))%>%
-  select(record_number,normalized_year,vd17_id,genre_category,genre_group,genre)%>%
+  filter(nchar(normalized_year) == 4) %>%
+  left_join(vd17_society_genres, by = c("record_number")) %>%
+  select(record_number, normalized_year, vd17_id, genre_category, genre_group, genre) %>%
   distinct()
 
 
-genres_vd17_society%>%
-  group_by(normalized_year)%>%
-  count(genre_category,genre_group)%>%
-  arrange(desc(n))%>%
-  distinct()%>%
-  ggplot(aes(x = normalized_year, y = n, fill= genre_category,colour = genre_category)) + geom_point(size = 3)+
-  ggtitle("Seventeenth-Century Publications in Society-Related Genres")+
-  ylab("")+xlab("Year")+
+genres_vd17_society %>%
+  group_by(normalized_year) %>%
+  count(genre_category, genre_group) %>%
+  arrange(desc(n)) %>%
+  distinct() %>%
+  ggplot(aes(x = normalized_year, y = n, fill = genre_category, colour = genre_category)) +
+  geom_point(size = 3) +
+  ggtitle("Seventeenth-Century Publications in Society-Related Genres") +
+  ylab("") +
+  xlab("Year") +
   scale_x_continuous(breaks = seq(1000, 2000, by = 3)) +
   scale_y_continuous(breaks = seq(0, 700, by = 50)) +
   theme_hsci_discrete() +
-  theme(legend.position="bottom",legend.text=element_text(size=15))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),,text = element_text(size = 15))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  facet_wrap(~ genre_group)
+  theme(legend.position = "bottom", legend.text = element_text(size = 15)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), , text = element_text(size = 15)) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  facet_wrap(~genre_group)
 
-ggsave(file="plot3.jpg", width=20, height=20, dpi=200)
+ggsave(file = "plot3.jpg", width = 20, height = 20, dpi = 200)
 ```
 # Visualization: Comparison with VD17: Society output in German
 ```{r}
-vd17_fbs <- vd17_normalized_langs_local%>%
+vd17_fbs <- vd17_normalized_langs_local %>%
   left_join(vd17_normalized_years_local, by = c("record_number")) %>%
   filter(normalized_year >= 1600, normalized_year <= 1700) %>%
-  filter(nchar(normalized_year)==4)%>%
-  left_join(fbs_records,by=c('record_number')) %>%
-  select ('normalized_year','record_number','vd17_id','member_number')%>%
-   mutate(group = case_when(
+  filter(nchar(normalized_year) == 4) %>%
+  left_join(fbs_records, by = c("record_number")) %>%
+  select("normalized_year", "record_number", "vd17_id", "member_number") %>%
+  mutate(group = case_when(
     (is.na(member_number)) ~ "VD17",
     (!is.na(member_number)) ~ "Society"
-  ))%>%
-  distinct()%>%
+  )) %>%
+  distinct() %>%
   group_by(normalized_year) %>%
-  count(group)%>%
+  count(group) %>%
   arrange(desc(n))
 
 
-vd17_fbs%>%
-  ggplot(aes(x=normalized_year,y=n,fill=group))+
-  geom_col()+
-  ggtitle("Seventeenth-Century Publications in German")+
-  xlab("") + ylab("")+
-  scale_x_continuous(breaks = seq(1000, 2000, by = 2))+
-  scale_y_continuous(breaks = seq(0, 10000, by = 200))+
-  theme_hsci_discrete()+
-  theme(plot.title = element_text(hjust = 0.5))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))
-```
\ No newline at end of file
+vd17_fbs %>%
+  ggplot(aes(x = normalized_year, y = n, fill = group)) +
+  geom_col() +
+  ggtitle("Seventeenth-Century Publications in German") +
+  xlab("") +
+  ylab("") +
+  scale_x_continuous(breaks = seq(1000, 2000, by = 2)) +
+  scale_y_continuous(breaks = seq(0, 10000, by = 200)) +
+  theme_hsci_discrete() +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
+```
diff --git a/src/narges/RQ-Trello.Rmd b/src/narges/RQ-Trello.Rmd
index 31c0a75ca..b79987908 100644
--- a/src/narges/RQ-Trello.Rmd
+++ b/src/narges/RQ-Trello.Rmd
@@ -85,28 +85,27 @@ unified_places_of_publications <- unified_places_of_publication %>%
   collect()
 
 vd17_normalized_years <- vd17_normalized_years_a %>%
-  select(record_number,normalized_year)%>%
+  select(record_number, normalized_year) %>%
   collect()
 
 vd17_genres <- vd17_genres_a %>%
   collect()
 
-vd17_genre_categorisation <-vd17_genre_categorisation_a %>%
+vd17_genre_categorisation <- vd17_genre_categorisation_a %>%
   collect()
 ```
 
 ```{r}
-
 fbsgenre_place <- fbs_records_a %>%
-      filter(set=="Active member substantive role and society purpose related") %>%
-      inner_join(vd17_id_a, join_by(vd17_id)) %>%
-  collect()%>%
-      inner_join(vd17_genres, by=c("record_number")) %>%
-      inner_join(vd17_normalized_years, by=c("record_number")) %>%    
-      left_join(vd17_genre_categorisation)%>%
-  left_join(unified_places_of_publications,by=c("record_number"))
-
-fbsgenre_place <- select(fbsgenre_place,-c('3','7'))
+  filter(set == "Active member substantive role and society purpose related") %>%
+  inner_join(vd17_id_a, join_by(vd17_id)) %>%
+  collect() %>%
+  inner_join(vd17_genres, by = c("record_number")) %>%
+  inner_join(vd17_normalized_years, by = c("record_number")) %>%
+  left_join(vd17_genre_categorisation) %>%
+  left_join(unified_places_of_publications, by = c("record_number"))
+
+fbsgenre_place <- select(fbsgenre_place, -c("3", "7"))
 ```
 
 ```{r}
@@ -114,27 +113,27 @@ colour_list <- c(
   "dodgerblue2", "#E31A1C",
   "green4",
   "#6A3D9A",
-  "#FF7F00", 
+  "#FF7F00",
   "black", "gold1",
   "skyblue2", "#FB9A99",
   "palegreen2",
-  "#CAB2D6", 
+  "#CAB2D6",
   "#FDBF6F",
   "gray70", "khaki2",
   "maroon", "orchid1", "deeppink1"
 )
 fbsgenre_place %>%
-  count(genre, places_of_publication,group_1, group_3) %>%
-      filter(group_1=="Society-related") %>%
-  group_by(places_of_publication,group_3)%>%
-  #summarise(average=mean(n),.groups="drop") %>%
-  ggplot(aes(x=places_of_publication,y=n,color=group_3)) +
+  count(genre, places_of_publication, group_1, group_3) %>%
+  filter(group_1 == "Society-related") %>%
+  group_by(places_of_publication, group_3) %>%
+  # summarise(average=mean(n),.groups="drop") %>%
+  ggplot(aes(x = places_of_publication, y = n, color = group_3)) +
   geom_point() +
-  theme_hsci_discrete()+
-  theme(legend.position="bottom",legend.text=element_text(size=8))+
-  theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5),text = element_text(size = 8,face = "bold"))+
-  theme(plot.title = element_text(hjust = 0.5))+
-  scale_fill_manual(values=colour_list)
+  theme_hsci_discrete() +
+  theme(legend.position = "bottom", legend.text = element_text(size = 8)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5), text = element_text(size = 8, face = "bold")) +
+  theme(plot.title = element_text(hjust = 0.5)) +
+  scale_fill_manual(values = colour_list)
 ```
 
 
@@ -164,11 +163,12 @@ gs4_auth(cache = ".secrets", email = "narges.azizifard@gmail.com")
 
 # Creating the google spreadsheet
 ```{r}
-fbs_genre_place_link <- fbsgenre_place%>%
-     mutate(vd17_id=gs4_formula(str_c('=HYPERLINK("https://kxp.k10plus.de/DB=1.28/CMD?ACT=SRCHA&IKT=8079&TRM=%27',vd17_id,'%27","',vd17_id,'")')))
+fbs_genre_place_link <- fbsgenre_place %>%
+  mutate(vd17_id = gs4_formula(str_c('=HYPERLINK("https://kxp.k10plus.de/DB=1.28/CMD?ACT=SRCHA&IKT=8079&TRM=%27', vd17_id, '%27","', vd17_id, '")')))
 
-fbs_genre_place<- gs4_create(
+fbs_genre_place <- gs4_create(
   "fbs_genre_place",
-  sheets = fbs_genre_place_link)
+  sheets = fbs_genre_place_link
+)
 fbs_genre_place
 ```