In bryanvictor/BibWrangleR: Software Tool for Converting Bibliographic Text Files into an Analyzable Data Frame
r knitr::opts_chunk$set(echo=FALSE, message=FALSE, warning=FALSE, comment=NA)
Workspace initialization
Set the working directory of this document to the directory containing the historical database.
rm(list=ls())
library(dplyr)
library(ggplot2)
library(gridExtra)
source("./Functions/pretty.R")
# Load data files
load("./Data/HistoricalDatabase.RData")
hodge.df <- readLines("./Data/hodge.txt", n = -1)
scopus.df <- read.csv("./Data/scopus.csv")
abb.df <- read.csv("./Data/master.csv")
sangam.df <- read.csv("./Data/sangam.csv")
# Create colour palette for consistent plotting
# http://colorbrewer2.org/?type=diverging&scheme=PuOr&n=4
cp <- c("#fdb864", "#e66101", "#b2abd2", "#5e3c99" )
Descriptive summaries
#=======================================
# Descriptives
#=======================================
numberArticles <- length(which(full.df$attributes == "article"))
numberJournals <- filter(full.df, attributes == "journal") %>%
summarise(Unique = n_distinct(record))
unique.swHistory <- filter(full.df, attributes == "journal") %>%
distinct(record)
hodge.swHistory.intersect <- intersect(hodge.df, unique.swHistory$record)
hodge.swHistory.diff <- setdiff(hodge.df, unique.swHistory$record)
Table 1
#=======================================
# Table 1. Journal summary
#=======================================
# Integrate min - max years for each journal
unique.titles <- filter(full.df, attributes == "journal") %>%
group_by(record) %>%
mutate(Hodge = ifelse(record %in% hodge.df == TRUE, "Y", "N")) %>%
summarise(N = n(), Hodge.list = max(Hodge))
unique.year <- filter(full.df, attributes == "pubYear") %>%
group_by(record)
n.so <- filter(full.df, attributes == "journal") %>%
mutate(title = record) %>%
select(-attributes, -record)
n.yr <- filter(full.df, attributes == "pubYear") %>%
mutate(year = record ) %>%
select(-attributes, -record)
n.so.yr <- left_join(n.so, n.yr) %>%
group_by(title) %>%
summarise(first = min(year), last = max(year), n = n()) %>%
arrange(desc(n)) %>%
rename(Journal = title) %>%
mutate(index="index_variable")
table1 <- left_join(n.so.yr, abb.df) %>%
select(-X) %>%
select(Journal, Abbrev, n, first, last)
sum_Articles <- sum(table1$n)
median_Articles <- median(table1$n)
mean_Articles <- mean(table1$n)
sd_Articles <- sd(table1$n)
print(table1)
Figure 1 - Small Multiples
This figure is for the manuscript. Please note that the rendering is optimized for the manuscript, not an online rendering.
# Create an initial data frame from HD
sm.df <- left_join(n.so, n.yr) %>%
group_by(title, year) %>%
summarize(N = n()) %>%
mutate(Overall.N = sum(N), year = as.numeric(year)) %>%
ungroup() %>%
arrange(desc(Overall.N), title) %>%
rename(Year = year, Journal= title)
sm.df.reduced <- sm.df %>% select(-Overall.N)
scopus.df$DataBase <- rep("Scopus", nrow(scopus.df))
DataBase <- rep("HD", nrow(sm.df.reduced))
sm.df.reduced$DataBase <- DataBase
sm.df.reduced <- sm.df.reduced %>% rename(Documents = N)
sm.df.reduced$Documents <- ifelse(sm.df.reduced$Documents == 0, NA, sm.df.reduced$Documents)
sm.df.reduced <- na.omit(sm.df.reduced)
combined <- rbind(scopus.df, sm.df.reduced)
combined_reduced <- combined[combined$Journal %in% c("Families in Society", "Social Work", "British Journal of Social Work", "Journal of Gerontological Social Work", "Research on Social Work Practice", "Social Work in Health Care", "International Social Work", "Health & Social Work", "Journal of Social Work Education"), ]
combined_reduced$Journal <- factor(combined_reduced$Journal, levels = c("Families in Society", "Social Work", "British Journal of Social Work", "Journal of Gerontological Social Work", "Research on Social Work Practice", "Social Work in Health Care", "International Social Work", "Health & Social Work", "Journal of Social Work Education") )
# Create Scopus labels for the facets
scopus.df$Year <- as.numeric(scopus.df$Year)
scopus.df <- filter(scopus.df, Year <= 2013)
scopus.df$Year <- as.numeric(scopus.df$Year)
scopus_annotate <- filter(scopus.df, Year <= 2013) %>%
group_by(Journal) %>%
summarize(N = pretty(sum(Documents)))
scopus_annotate_paper <-scopus_annotate[scopus_annotate$Journal %in% combined_reduced$Journal, ]
scopus_annotate_paper$label <- paste0("N=", pretty(scopus_annotate_paper$N))
# Create HD Labels for the facets
hd_annotate <- combined_reduced %>%
filter(DataBase == "HD") %>%
group_by(Journal) %>%
summarize(N = sum(Documents))%>%
mutate(label = paste0("N=", pretty(N)))
small_multiples_paper <- ggplot(combined_reduced, aes(Year, Documents, colour = DataBase)) +
geom_line(size = .5) +
facet_wrap(~ Journal) +
theme_bw() +
theme(strip.text.x = element_text(size = 14)) +
theme(legend.position = "bottom", legend.text = element_text(size = 14)) +
scale_colour_discrete(guide = guide_legend(title = "Database"),
breaks = c("HD", "Scopus"), labels = c("Historical Database", "Scopus")) +
scale_colour_manual(values = c("black", "#999999"), labels = c("Social Work Research Database", "Scopus"),
guide = guide_legend(title = "")) +
ylab("Number of Articles") +
xlab("\nYear") +
annotate("segment", x = 1992, xend = 1995, y = 140, yend = 140, colour = "black", size = 1, alpha = .80) +
annotate("segment", x = 1992, xend = 1995, y = 120, yend = 120, colour = "#999999", size = 1, alpha = .80) +
geom_text(data = scopus_annotate_paper, aes(x = 1999, y = 120, label = label), colour = "black", size = 5) +
geom_text(data = hd_annotate, aes(x = 1999, y = 140, label = label), colour = "black", size = 5)
#------------Create high quality jpeg-----------------
#ggsave(small_multiples_paper, file = "Figure_1_small_multiples.jpg", dpi = 1200, height = 8, width = 12, units = "in")
print(small_multiples_paper)
Small Multiples - Online Supplement
# Create an initial data frame from HD
sm.df <- left_join(n.so, n.yr) %>%
group_by(title, year) %>%
summarize(N = n()) %>%
mutate(Overall.N = sum(N), year = as.numeric(year)) %>%
ungroup() %>%
arrange(desc(Overall.N), title) %>%
rename(Year = year, Journal= title)
scopus.df$Year <- as.numeric(scopus.df$Year)
scopus.df <- filter(scopus.df, Year <= 2013)
# Join HD with Scopus and join abbreviation names
sm.scopus.merged <-full_join(sm.df, scopus.df, by = c("Journal", "Year")) %>%
select(Year, Journal, N, Overall.N, Documents)
sm.scopus.merged.table <- group_by(sm.scopus.merged, Journal) %>%
summarize(DataBase.N = sum(N, na.rm=TRUE), Scopus.N = sum(Documents, na.rm=TRUE)) %>%
arrange(desc(DataBase.N))
abb.df$ID <- 1:nrow(abb.df)
sm.scopus.merged <- full_join(sm.scopus.merged, abb.df, by = "Journal") %>%
select(-X) %>%
mutate(Documents = ifelse(Documents == 0, NA, Documents))
# Re-order the factor by Overall.N
title <- sm.scopus.merged %>% arrange(desc(Overall.N)) %>%
distinct(Abbrev) %>%
filter(!is.na(Abbrev)) %>%
distinct()
title.order = title$Abbrev
sm.scopus.merged$Abbrev <- factor(sm.scopus.merged$Abbrev, levels = (title.order))
sm.scopus.merged <- group_by(sm.scopus.merged, Journal) %>%
mutate(Overall.Scopus = sum(Documents, na.rm=TRUE)) %>%
ungroup()
# Create labels for the facets
Overall.N <- distinct(sm.scopus.merged, Abbrev)
lab1 <- gsub(" ", "", paste("N=", pretty(Overall.N$Overall.N), sep=""))
lab2 <- gsub(" ", "", paste("N=", pretty(Overall.N$Overall.Scopus), sep=""))
lab <- paste(lab1, lab2, sep="\n")
xpos = rep(1999, 80)
ypos = rep(190, 80)
ldata <- data.frame(xpos, ypos, lab, Overall.N$Abbrev) %>%
rename(Abbrev = Overall.N.Abbrev)
ldata <- na.omit(ldata)
titles.reduced <- unique(sm.scopus.merged$Journal)
titles.reduced.1 <- titles.reduced[1:40]
titles.reduced.2 <- titles.reduced[41:length(titles.reduced)]
cp <- c("#fdb864", "#e66101", "#b2abd2", "#5e3c99" )
# Plotting function
#
plotSmallMultiples.1 <- ggplot(sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.1, ],
aes(Year, N)) +
geom_line(colour="#e66101") +
geom_line(data = sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.1, ],
aes(Year, Documents), colour = "#533c99", alpha = .80) +
facet_wrap(~ Abbrev) +
theme_bw() +
theme(strip.text.x = element_text(size = 8)) +
theme(legend.position = "bottom",
panel.grid.minor = element_blank(),
axis.text.x = element_text(angle=45, hjust=1, size =8)) +
geom_text(data = ldata[1:40, ], aes(x =xpos, y = ypos, label = lab), size =2.5) +
ylim(c(0,225)) +
scale_x_continuous(breaks=seq(1989, 2015, 8)) +
annotate("segment", x = 1989, xend = 1992, y = 210, yend = 210, colour = "#e66101") +
annotate("segment", x = 1989, xend = 1992, y = 170, yend = 170, colour = "#533c99") +
ggtitle("Number of Article Records by Journal, 1989 - 2013 (Part 1)")
plotSmallMultiples.2 <- ggplot(sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.2, ],
aes(Year, N)) +
geom_line(colour="#e66101") +
geom_line(data = sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.2, ],
aes(Year, Documents), colour = "#533c99", alpha = .80) +
facet_wrap(~ Abbrev) +
theme_bw() +
theme(strip.text.x = element_text(size = 8)) +
theme(legend.position = "bottom",
panel.grid.minor = element_blank(),
axis.text.x = element_text(angle=45, hjust=1, size =8)) +
geom_text(data = ldata[41:80, ], aes(x =xpos, y = ypos, label = lab), size =2.5) +
ylim(c(0,225)) +
scale_x_continuous(breaks=seq(1989, 2015, 8)) +
annotate("segment", x = 1989, xend = 1992, y = 210, yend = 210, colour = "#e66101") +
annotate("segment", x = 1989, xend = 1992, y = 170, yend = 170, colour = "#533c99") +
ggtitle("Number of Article Records by Journal, 1989 - 2013 (Part 2)")
print(plotSmallMultiples.1)
print(plotSmallMultiples.2)
ggsave(plotSmallMultiples.1, file = "smallMultiples1.jpeg", width = 10, height = 7, units = "in", dpi=1200)
ggsave(plotSmallMultiples.2, file = "smallMultiples2.jpeg", width = 10, height = 7, units = "in", dpi=1200)
Figure 2 - Growth of Social Work Research
#=======================================
# Journals
#=======================================
n.journals.year <- filter(full.df, attributes == "journal") %>%
select(articleID, record)
n.year <- filter(full.df, attributes == "pubYear") %>%
select(articleID, record)
n.journals.year <- left_join(n.journals.year, n.year, by = "articleID", copy=TRUE) %>%
group_by(record.y) %>%
summarise(Journal.count = n_distinct(record.x)) %>%
mutate(record.y = as.numeric(record.y))
exp.047 <- c(31, rep(NA, 24))
for(i in 2:25){
exp.047[i] <- exp.047[i-1] + exp.047[i-1]*.047
}
exp.0307 <- c(31, rep(NA, 24))
for(i in 2:25){
exp.0307[i] <- exp.0307[i-1] + exp.0307[i-1]*.0307
}
n.journals.year$Price <- exp.047
n.journals.year$SWHD <- exp.0307
n.journals.year <- mutate(n.journals.year, Journal.count = as.numeric(Journal.count))
n.journals.year <- as.data.frame(n.journals.year)
years <- c(1989, 2005, 2013, 2013)
points <- c(31, n.journals.year$Journal.count[c(17,25)], max(n.journals.year$exp.05))
annotate.df <- data.frame(years, points)
cols = c("Observed Growth" = cp[1], "3.07% CAGR" = cp[4], "4.7% CAGR" = cp[3])
figure2 <- ggplot(n.journals.year, aes(record.y,
y = Journal.count)) +
theme_bw() +
theme(axis.text.x = element_text(size=8),
title = element_text(size = 10), plot.title=element_text(size=10)) +
xlab("Year") +
ylab("Journals") +
scale_y_continuous(breaks = c(seq(0, 100, 10)), limits = c(20, 95)) +
theme(axis.title.x = element_text(vjust=-0.5), axis.title.y = element_text(vjust=.75)) +
geom_line(aes(x = record.y, y = Price, colour = "Estimated 5% CAGR"),
data = n.journals.year, colour = "#999999", alpha = .80) +
geom_line(aes(x = record.y, y = SWHD, colour = "Estimated 4% CAGR"),
data = n.journals.year, colour = "#999999", alpha = .80) +
geom_line(aes(colour = "Observed Growth"), colour = "black", size = 1.5) +
stat_smooth(method = "lm", se = FALSE, colour = "#999999") +
annotate("text", x = 2014.5, y = 60, label = "3.07% CAGR", size = 4) +
annotate("text", x = 2016, y = 74.5, label = "Linear growth", size = 4) +
annotate("text", x = 2015.5, y = 95, label = "4.7% CAGR", size = 4) +
annotate("text", x = 2016.5, y = 67, label = "Observed growth", size = 4) +
scale_x_continuous(limits = c(1989, 2020), breaks = c(1989, 1993, 1997, 2001, 2005, 2009, 2013)) +
#ggtitle("Figure 2. Observed Versus Estimated Growth of Journals (1989-2013)") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.border = element_blank(), axis.line = element_line(),
axis.text.x = element_text(size = 16),
axis.text.y = element_text(size = 16),
axis.title.x = element_text(size = 16),
axis.title.y = element_text(size = 16)) +
theme(plot.title = element_text(size = 19))
#ggsave(figure2, file = "figure2.jpeg", width = 7, height = 7, units = "in", dpi = 1200)
print(figure2)
n.journals.year <- filter(full.df, attributes == "journal") %>%
select(articleID, record)
n.year <- filter(full.df, attributes == "pubYear") %>%
select(articleID, record)
n.journals.year <- left_join(n.journals.year, n.year, by = "articleID", copy=TRUE) %>%
group_by(record.y) %>%
summarise(Journal.count = n_distinct(record.x)) %>%
mutate(record.y = as.numeric(record.y))
n.journals.year$yearCount <- c(1:nrow(n.journals.year))
Figure 3 Annual Change
curr <- n.journals.year$Journal.count[-1]
prev <- n.journals.year$Journal.count[1:(length(n.journals.year$Journal.count)-1)]
annualChange.numeric <- c(0, (100 * (curr-prev)/ prev))
annualChange.dichotomous <- ifelse(annualChange.numeric < 0, "Decrease", "Increase")
annualChange.df <- data.frame(annualChange.numeric, annualChange.dichotomous)
annualChange.df$year <- c(1989:2013)
figure3 <- ggplot(annualChange.df, aes(year, annualChange.numeric, fill =annualChange.dichotomous)) +
theme_bw() +
geom_bar(stat="identity") +
scale_fill_manual(values = c("black", "#999999"), limits = c("Increase", "Decrease")) +
theme(legend.position = c(1,1), legend.justification = c(1,1), legend.title = element_blank()) +
ylab("Percent change") +
xlab("Year") +
scale_x_continuous(breaks=seq(1989, 2015, 4)) +
scale_y_continuous(breaks = seq(-10, 15, 5)) +
geom_hline(yintercept=seq(-5, 15, 5), col="white", lwd=0.4) +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.border = element_blank(), axis.line = element_line(),
axis.text.x = element_text(size = 16),
axis.text.y = element_text(size = 16),
axis.title.x = element_text(size = 16),
axis.title.y = element_text(size = 16)) +
geom_hline(yintercept=0, col="gray", lwd=0.6, alpha =.8) +
#ggtitle("Figure 3. Annual Percentage Change in the Number Journals (1989 - 2013)") +
theme(plot.title = element_text(size = 19))
#ggsave(figure3, file = "figure3.jpeg", width = 7, height = 7, units = "in", dpi=1200)
print(figure3)
bryanvictor/BibWrangleR documentation built on May 13, 2019, 8:11 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
r knitr::opts_chunk$set(echo=FALSE, message=FALSE, warning=FALSE, comment=NA)
Workspace initialization
Set the working directory of this document to the directory containing the historical database.
rm(list=ls()) library(dplyr) library(ggplot2) library(gridExtra) source("./Functions/pretty.R") # Load data files load("./Data/HistoricalDatabase.RData") hodge.df <- readLines("./Data/hodge.txt", n = -1) scopus.df <- read.csv("./Data/scopus.csv") abb.df <- read.csv("./Data/master.csv") sangam.df <- read.csv("./Data/sangam.csv") # Create colour palette for consistent plotting # http://colorbrewer2.org/?type=diverging&scheme=PuOr&n=4 cp <- c("#fdb864", "#e66101", "#b2abd2", "#5e3c99" )
Descriptive summaries
#======================================= # Descriptives #======================================= numberArticles <- length(which(full.df$attributes == "article")) numberJournals <- filter(full.df, attributes == "journal") %>% summarise(Unique = n_distinct(record)) unique.swHistory <- filter(full.df, attributes == "journal") %>% distinct(record) hodge.swHistory.intersect <- intersect(hodge.df, unique.swHistory$record) hodge.swHistory.diff <- setdiff(hodge.df, unique.swHistory$record)
Table 1
#======================================= # Table 1. Journal summary #======================================= # Integrate min - max years for each journal unique.titles <- filter(full.df, attributes == "journal") %>% group_by(record) %>% mutate(Hodge = ifelse(record %in% hodge.df == TRUE, "Y", "N")) %>% summarise(N = n(), Hodge.list = max(Hodge)) unique.year <- filter(full.df, attributes == "pubYear") %>% group_by(record) n.so <- filter(full.df, attributes == "journal") %>% mutate(title = record) %>% select(-attributes, -record) n.yr <- filter(full.df, attributes == "pubYear") %>% mutate(year = record ) %>% select(-attributes, -record) n.so.yr <- left_join(n.so, n.yr) %>% group_by(title) %>% summarise(first = min(year), last = max(year), n = n()) %>% arrange(desc(n)) %>% rename(Journal = title) %>% mutate(index="index_variable") table1 <- left_join(n.so.yr, abb.df) %>% select(-X) %>% select(Journal, Abbrev, n, first, last) sum_Articles <- sum(table1$n) median_Articles <- median(table1$n) mean_Articles <- mean(table1$n) sd_Articles <- sd(table1$n) print(table1)
Figure 1 - Small Multiples
This figure is for the manuscript. Please note that the rendering is optimized for the manuscript, not an online rendering.
# Create an initial data frame from HD sm.df <- left_join(n.so, n.yr) %>% group_by(title, year) %>% summarize(N = n()) %>% mutate(Overall.N = sum(N), year = as.numeric(year)) %>% ungroup() %>% arrange(desc(Overall.N), title) %>% rename(Year = year, Journal= title) sm.df.reduced <- sm.df %>% select(-Overall.N) scopus.df$DataBase <- rep("Scopus", nrow(scopus.df)) DataBase <- rep("HD", nrow(sm.df.reduced)) sm.df.reduced$DataBase <- DataBase sm.df.reduced <- sm.df.reduced %>% rename(Documents = N) sm.df.reduced$Documents <- ifelse(sm.df.reduced$Documents == 0, NA, sm.df.reduced$Documents) sm.df.reduced <- na.omit(sm.df.reduced) combined <- rbind(scopus.df, sm.df.reduced) combined_reduced <- combined[combined$Journal %in% c("Families in Society", "Social Work", "British Journal of Social Work", "Journal of Gerontological Social Work", "Research on Social Work Practice", "Social Work in Health Care", "International Social Work", "Health & Social Work", "Journal of Social Work Education"), ] combined_reduced$Journal <- factor(combined_reduced$Journal, levels = c("Families in Society", "Social Work", "British Journal of Social Work", "Journal of Gerontological Social Work", "Research on Social Work Practice", "Social Work in Health Care", "International Social Work", "Health & Social Work", "Journal of Social Work Education") ) # Create Scopus labels for the facets scopus.df$Year <- as.numeric(scopus.df$Year) scopus.df <- filter(scopus.df, Year <= 2013) scopus.df$Year <- as.numeric(scopus.df$Year) scopus_annotate <- filter(scopus.df, Year <= 2013) %>% group_by(Journal) %>% summarize(N = pretty(sum(Documents))) scopus_annotate_paper <-scopus_annotate[scopus_annotate$Journal %in% combined_reduced$Journal, ] scopus_annotate_paper$label <- paste0("N=", pretty(scopus_annotate_paper$N)) # Create HD Labels for the facets hd_annotate <- combined_reduced %>% filter(DataBase == "HD") %>% group_by(Journal) %>% summarize(N = sum(Documents))%>% mutate(label = paste0("N=", pretty(N))) small_multiples_paper <- ggplot(combined_reduced, aes(Year, Documents, colour = DataBase)) + geom_line(size = .5) + facet_wrap(~ Journal) + theme_bw() + theme(strip.text.x = element_text(size = 14)) + theme(legend.position = "bottom", legend.text = element_text(size = 14)) + scale_colour_discrete(guide = guide_legend(title = "Database"), breaks = c("HD", "Scopus"), labels = c("Historical Database", "Scopus")) + scale_colour_manual(values = c("black", "#999999"), labels = c("Social Work Research Database", "Scopus"), guide = guide_legend(title = "")) + ylab("Number of Articles") + xlab("\nYear") + annotate("segment", x = 1992, xend = 1995, y = 140, yend = 140, colour = "black", size = 1, alpha = .80) + annotate("segment", x = 1992, xend = 1995, y = 120, yend = 120, colour = "#999999", size = 1, alpha = .80) + geom_text(data = scopus_annotate_paper, aes(x = 1999, y = 120, label = label), colour = "black", size = 5) + geom_text(data = hd_annotate, aes(x = 1999, y = 140, label = label), colour = "black", size = 5) #------------Create high quality jpeg----------------- #ggsave(small_multiples_paper, file = "Figure_1_small_multiples.jpg", dpi = 1200, height = 8, width = 12, units = "in") print(small_multiples_paper)
Small Multiples - Online Supplement
# Create an initial data frame from HD sm.df <- left_join(n.so, n.yr) %>% group_by(title, year) %>% summarize(N = n()) %>% mutate(Overall.N = sum(N), year = as.numeric(year)) %>% ungroup() %>% arrange(desc(Overall.N), title) %>% rename(Year = year, Journal= title) scopus.df$Year <- as.numeric(scopus.df$Year) scopus.df <- filter(scopus.df, Year <= 2013) # Join HD with Scopus and join abbreviation names sm.scopus.merged <-full_join(sm.df, scopus.df, by = c("Journal", "Year")) %>% select(Year, Journal, N, Overall.N, Documents) sm.scopus.merged.table <- group_by(sm.scopus.merged, Journal) %>% summarize(DataBase.N = sum(N, na.rm=TRUE), Scopus.N = sum(Documents, na.rm=TRUE)) %>% arrange(desc(DataBase.N)) abb.df$ID <- 1:nrow(abb.df) sm.scopus.merged <- full_join(sm.scopus.merged, abb.df, by = "Journal") %>% select(-X) %>% mutate(Documents = ifelse(Documents == 0, NA, Documents)) # Re-order the factor by Overall.N title <- sm.scopus.merged %>% arrange(desc(Overall.N)) %>% distinct(Abbrev) %>% filter(!is.na(Abbrev)) %>% distinct() title.order = title$Abbrev sm.scopus.merged$Abbrev <- factor(sm.scopus.merged$Abbrev, levels = (title.order)) sm.scopus.merged <- group_by(sm.scopus.merged, Journal) %>% mutate(Overall.Scopus = sum(Documents, na.rm=TRUE)) %>% ungroup() # Create labels for the facets Overall.N <- distinct(sm.scopus.merged, Abbrev) lab1 <- gsub(" ", "", paste("N=", pretty(Overall.N$Overall.N), sep="")) lab2 <- gsub(" ", "", paste("N=", pretty(Overall.N$Overall.Scopus), sep="")) lab <- paste(lab1, lab2, sep="\n") xpos = rep(1999, 80) ypos = rep(190, 80) ldata <- data.frame(xpos, ypos, lab, Overall.N$Abbrev) %>% rename(Abbrev = Overall.N.Abbrev) ldata <- na.omit(ldata) titles.reduced <- unique(sm.scopus.merged$Journal) titles.reduced.1 <- titles.reduced[1:40] titles.reduced.2 <- titles.reduced[41:length(titles.reduced)] cp <- c("#fdb864", "#e66101", "#b2abd2", "#5e3c99" ) # Plotting function # plotSmallMultiples.1 <- ggplot(sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.1, ], aes(Year, N)) + geom_line(colour="#e66101") + geom_line(data = sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.1, ], aes(Year, Documents), colour = "#533c99", alpha = .80) + facet_wrap(~ Abbrev) + theme_bw() + theme(strip.text.x = element_text(size = 8)) + theme(legend.position = "bottom", panel.grid.minor = element_blank(), axis.text.x = element_text(angle=45, hjust=1, size =8)) + geom_text(data = ldata[1:40, ], aes(x =xpos, y = ypos, label = lab), size =2.5) + ylim(c(0,225)) + scale_x_continuous(breaks=seq(1989, 2015, 8)) + annotate("segment", x = 1989, xend = 1992, y = 210, yend = 210, colour = "#e66101") + annotate("segment", x = 1989, xend = 1992, y = 170, yend = 170, colour = "#533c99") + ggtitle("Number of Article Records by Journal, 1989 - 2013 (Part 1)") plotSmallMultiples.2 <- ggplot(sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.2, ], aes(Year, N)) + geom_line(colour="#e66101") + geom_line(data = sm.scopus.merged[sm.scopus.merged$Journal %in% titles.reduced.2, ], aes(Year, Documents), colour = "#533c99", alpha = .80) + facet_wrap(~ Abbrev) + theme_bw() + theme(strip.text.x = element_text(size = 8)) + theme(legend.position = "bottom", panel.grid.minor = element_blank(), axis.text.x = element_text(angle=45, hjust=1, size =8)) + geom_text(data = ldata[41:80, ], aes(x =xpos, y = ypos, label = lab), size =2.5) + ylim(c(0,225)) + scale_x_continuous(breaks=seq(1989, 2015, 8)) + annotate("segment", x = 1989, xend = 1992, y = 210, yend = 210, colour = "#e66101") + annotate("segment", x = 1989, xend = 1992, y = 170, yend = 170, colour = "#533c99") + ggtitle("Number of Article Records by Journal, 1989 - 2013 (Part 2)") print(plotSmallMultiples.1) print(plotSmallMultiples.2) ggsave(plotSmallMultiples.1, file = "smallMultiples1.jpeg", width = 10, height = 7, units = "in", dpi=1200) ggsave(plotSmallMultiples.2, file = "smallMultiples2.jpeg", width = 10, height = 7, units = "in", dpi=1200)
Figure 2 - Growth of Social Work Research
#======================================= # Journals #======================================= n.journals.year <- filter(full.df, attributes == "journal") %>% select(articleID, record) n.year <- filter(full.df, attributes == "pubYear") %>% select(articleID, record) n.journals.year <- left_join(n.journals.year, n.year, by = "articleID", copy=TRUE) %>% group_by(record.y) %>% summarise(Journal.count = n_distinct(record.x)) %>% mutate(record.y = as.numeric(record.y)) exp.047 <- c(31, rep(NA, 24)) for(i in 2:25){ exp.047[i] <- exp.047[i-1] + exp.047[i-1]*.047 } exp.0307 <- c(31, rep(NA, 24)) for(i in 2:25){ exp.0307[i] <- exp.0307[i-1] + exp.0307[i-1]*.0307 } n.journals.year$Price <- exp.047 n.journals.year$SWHD <- exp.0307 n.journals.year <- mutate(n.journals.year, Journal.count = as.numeric(Journal.count)) n.journals.year <- as.data.frame(n.journals.year) years <- c(1989, 2005, 2013, 2013) points <- c(31, n.journals.year$Journal.count[c(17,25)], max(n.journals.year$exp.05)) annotate.df <- data.frame(years, points) cols = c("Observed Growth" = cp[1], "3.07% CAGR" = cp[4], "4.7% CAGR" = cp[3]) figure2 <- ggplot(n.journals.year, aes(record.y, y = Journal.count)) + theme_bw() + theme(axis.text.x = element_text(size=8), title = element_text(size = 10), plot.title=element_text(size=10)) + xlab("Year") + ylab("Journals") + scale_y_continuous(breaks = c(seq(0, 100, 10)), limits = c(20, 95)) + theme(axis.title.x = element_text(vjust=-0.5), axis.title.y = element_text(vjust=.75)) + geom_line(aes(x = record.y, y = Price, colour = "Estimated 5% CAGR"), data = n.journals.year, colour = "#999999", alpha = .80) + geom_line(aes(x = record.y, y = SWHD, colour = "Estimated 4% CAGR"), data = n.journals.year, colour = "#999999", alpha = .80) + geom_line(aes(colour = "Observed Growth"), colour = "black", size = 1.5) + stat_smooth(method = "lm", se = FALSE, colour = "#999999") + annotate("text", x = 2014.5, y = 60, label = "3.07% CAGR", size = 4) + annotate("text", x = 2016, y = 74.5, label = "Linear growth", size = 4) + annotate("text", x = 2015.5, y = 95, label = "4.7% CAGR", size = 4) + annotate("text", x = 2016.5, y = 67, label = "Observed growth", size = 4) + scale_x_continuous(limits = c(1989, 2020), breaks = c(1989, 1993, 1997, 2001, 2005, 2009, 2013)) + #ggtitle("Figure 2. Observed Versus Estimated Growth of Journals (1989-2013)") + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), panel.border = element_blank(), axis.line = element_line(), axis.text.x = element_text(size = 16), axis.text.y = element_text(size = 16), axis.title.x = element_text(size = 16), axis.title.y = element_text(size = 16)) + theme(plot.title = element_text(size = 19)) #ggsave(figure2, file = "figure2.jpeg", width = 7, height = 7, units = "in", dpi = 1200) print(figure2)
n.journals.year <- filter(full.df, attributes == "journal") %>% select(articleID, record) n.year <- filter(full.df, attributes == "pubYear") %>% select(articleID, record) n.journals.year <- left_join(n.journals.year, n.year, by = "articleID", copy=TRUE) %>% group_by(record.y) %>% summarise(Journal.count = n_distinct(record.x)) %>% mutate(record.y = as.numeric(record.y)) n.journals.year$yearCount <- c(1:nrow(n.journals.year))
Figure 3 Annual Change
curr <- n.journals.year$Journal.count[-1] prev <- n.journals.year$Journal.count[1:(length(n.journals.year$Journal.count)-1)] annualChange.numeric <- c(0, (100 * (curr-prev)/ prev)) annualChange.dichotomous <- ifelse(annualChange.numeric < 0, "Decrease", "Increase") annualChange.df <- data.frame(annualChange.numeric, annualChange.dichotomous) annualChange.df$year <- c(1989:2013) figure3 <- ggplot(annualChange.df, aes(year, annualChange.numeric, fill =annualChange.dichotomous)) + theme_bw() + geom_bar(stat="identity") + scale_fill_manual(values = c("black", "#999999"), limits = c("Increase", "Decrease")) + theme(legend.position = c(1,1), legend.justification = c(1,1), legend.title = element_blank()) + ylab("Percent change") + xlab("Year") + scale_x_continuous(breaks=seq(1989, 2015, 4)) + scale_y_continuous(breaks = seq(-10, 15, 5)) + geom_hline(yintercept=seq(-5, 15, 5), col="white", lwd=0.4) + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), panel.border = element_blank(), axis.line = element_line(), axis.text.x = element_text(size = 16), axis.text.y = element_text(size = 16), axis.title.x = element_text(size = 16), axis.title.y = element_text(size = 16)) + geom_hline(yintercept=0, col="gray", lwd=0.6, alpha =.8) + #ggtitle("Figure 3. Annual Percentage Change in the Number Journals (1989 - 2013)") + theme(plot.title = element_text(size = 19)) #ggsave(figure3, file = "figure3.jpeg", width = 7, height = 7, units = "in", dpi=1200) print(figure3)
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.