ggplot(literature, aes(YearPublished)) + geom_histogram(binwidth = 1, fill = "darkgreen") + 
    ggtitle("Year published") + xlab("Year") + ylab("Article count")

# Calculate relative publication counts yearTable <-
# as.data.frame(table(literature$YearPublished)) names(yearDF) <- c('Year',
# 'Freq') # Fix column names

# Merge to dataframe of total publication numbers (years) yearDF <-
# merge(yearDF, years, by.x = 'Year', by.y = 'Year', all.x = TRUE)
# yearDF$Year <- as.numeric(as.character(yearDF$Year)) # factor to numeric
# Calculate published articles per total articles by year yearDF$Fraction <-
# yearDF$Freq / yearDF$Records

# ADD PLOT HERE!
print("Placeholder")

# Get author network nodes, which contain the required information
author_network <- get_author_network(literature)
author_nodes <- author_network$author_nodes
# Change Id to AuthorFullName
names(author_nodes)[names(author_nodes) == "Id"] <- "AuthorFullName"

# Sort by number of articles by author
author_nodes <- author_nodes[with(author_nodes, order(-Freq)), ]
# Re-order factor levels
author_nodes <- transform(author_nodes, AuthorFullName = reorder(AuthorFullName, 
    Freq))

ggplot(head(author_nodes, 25), aes(AuthorFullName, Freq)) + geom_bar(stat = "identity", 
    fill = "blue") + coord_flip() + ggtitle("Productive authors") + xlab("Author") + 
    ylab("Number of articles")

# Reorder AuthorFullName factor according to TotalTimesCited (decreasing
# order)
author_nodes <- transform(author_nodes, AuthorFullName = reorder(AuthorFullName, 
    TotalTimesCited))

# Sort by number of articles by author
author_nodes <- author_nodes[with(author_nodes, order(-TotalTimesCited)), ]

ggplot(head(author_nodes, 25), aes(AuthorFullName, TotalTimesCited)) + geom_bar(stat = "identity", 
    fill = "blue") + coord_flip() + ggtitle("Most cited authors") + xlab("Author") + 
    ylab("Total times cited")

# Calculate publication occurences
publications <- as.data.frame(table(literature$PublicationName))

# Fix names
names(publications) <- c("Publication", "Count")

# Trim publication name to maximum of 50 characters for displaying in plot
publications$Publication <- strtrim(publications$Publication, 50)

# Sort descending
publications <- publications[with(publications, order(-Count)), ]

# Reorder factor levels
publications <- transform(publications, Publication = reorder(Publication, Count))


# WHY???  literature <- merge(literature, citation_sums, by =
# 'PublicationName' )

ggplot(head(publications, 25), aes(Publication, Count)) + geom_bar(stat = "identity", 
    fill = "orange") + coord_flip() + theme(legend.position = "none") + ggtitle("Most popular publications") + 
    xlab("Publication") + ylab("Article count")

# Calculating total citations for each publication.
citation_sums <- aggregate(literature$TimesCited, by = list(PublicationName = literature$PublicationName), 
    FUN = sum, na.rm = T)

# Fix column names
names(citation_sums) <- c("PublicationName", "PublicationTotalCitations")

# Trim publication name to maximum of 50 characters for displaying in plot
citation_sums$PublicationName <- strtrim(citation_sums$PublicationName, 50)

# Sort descending and reorder factor levels accordingly
citation_sums <- citation_sums[with(citation_sums, order(-PublicationTotalCitations)), 
    ]
citation_sums <- transform(citation_sums, PublicationName = reorder(PublicationName, 
    PublicationTotalCitations))
ggplot(head(citation_sums, 25), aes(PublicationName, PublicationTotalCitations)) + 
    geom_bar(stat = "identity", fill = "orange") + coord_flip() + theme(legend.position = "none") + 
    ggtitle("Most cited publications") + xlab("Publication") + ylab("Total times cited")

# Calculating total citations for each keyword

literature_by_keywords <- arrange_by(literature, "AuthorKeywords")



# Sometimes AuthorKeywords column is empty.  Following if-else hack prevents
# crashing in those situations, either by using KeywordsPlus column or
# skipping keyword analysis.
if (nrow(literature_by_keywords) == 0) {
    cat("No keywords.")
} else {
    keyword_citation_sum <- aggregate(literature_by_keywords$TimesCited, by = list(AuthorKeywords = literature_by_keywords$AuthorKeywords), 
        FUN = sum, na.rm = T)
    names(keyword_citation_sum) <- c("AuthorKeywords", "TotalTimesCited")
    
    keywords <- unlist(strsplit(literature$AuthorKeywords, ";"))
    keywords <- trim(keywords)
    keywords <- as.data.frame(table(keywords))
    names(keywords) <- c("AuthorKeywords", "Freq")
    
    keywords <- merge(keywords, keyword_citation_sum, by = "AuthorKeywords")
    keywords <- keywords[with(keywords, order(-Freq)), ]
    keywords <- transform(keywords, AuthorKeywords = reorder(AuthorKeywords, 
        Freq))
    
    ggplot(head(keywords, 25), aes(AuthorKeywords, Freq)) + geom_bar(stat = "identity", 
        fill = "purple") + coord_flip() + ggtitle("Popular keywords") + xlab("Keyword") + 
        ylab("Number of occurences")
}

if (nrow(literature_by_keywords) > 0) {
    keywords <- keywords[with(keywords, order(-TotalTimesCited)), ]
    keywords <- transform(keywords, AuthorKeywords = reorder(AuthorKeywords, 
        TotalTimesCited))
    ggplot(head(keywords, 25), aes(AuthorKeywords, TotalTimesCited)) + geom_bar(stat = "identity", 
        fill = "purple") + coord_flip() + ggtitle("Most cited keywords") + xlab("Keyword") + 
        ylab("Total times cited")
}

# Extract citation nodes
citation_network <- get_citation_network(literature)
citation_nodes <- citation_network$citation_nodes


# Extract the articles included in the data set and articles not included in
# the dataset
citations_lit <- citation_nodes[citation_nodes$Origin == "literature", ]
citations_ref <- citation_nodes[citation_nodes$Origin == "reference", ]

# Create article strings (document title, reference information and abstract
# separated by '|')
citations_lit$Article <- paste(toupper(citations_lit$DocumentTitle), " | ", 
    citations_lit$FullReference, " | ", citations_lit$Abstract)

references <- unlist(strsplit(literature$CitedReferences, ";"))

get_publication <- function(x) {
    publication <- "Not found"
    try(publication <- unlist(strsplit(x, ","))[[3]], silent = TRUE)
    return(publication)
}

refPublications <- sapply(references, get_publication)
refPublications <- sapply(refPublications, trim)
refPublications <- refPublications[refPublications != "Not found"]
refPublications <- as.data.frame(table(refPublications))
names(refPublications) <- c("Publication", "Count")
refPublications <- refPublications[with(refPublications, order(-Count)), ]

refPublications <- transform(refPublications, Publication = reorder(Publication, 
    Count))

ggplot(head(refPublications, 25), aes(Publication, Count)) + geom_bar(stat = "identity", 
    fill = "orange") + coord_flip() + theme(legend.position = "none") + ggtitle("Most referenced publications") + 
    xlab("Publication") + ylab("Count")

topicmodel <- build_topicmodel_from_literature(literature)

topickeywords <- topicmodels::terms(topicmodel$fit, 10)
tw <- data.frame(topickeywords)
colnames(tw) <- gsub("X", "Topic ", colnames(tw))
knitr::kable(tw, col.names = colnames(tw))