Added more variables to the pdf summary

Author: DanielThedie

R/Text_utils.r

@@ -50,31 +50,24 @@ format_summary_stats <- function(summary_stats) {
   # Merge Start_year and End_year into "Date Range"
   summary_stats$Date_Range <- paste(summary_stats$Start_year, summary_stats$End_year, sep = "-")
 
-  # Define the columns to keep
-  columns_to_keep <- c("Date_Range",
-                       "Total_Papers",
-                       "Total_Authors",
-                       "Density",
-                       "Transitivity",
-                       "Mean_shortest_path",
-                       "Number_of_cutpoints")
-
-  # Filter the columns
-  summary_stats <- summary_stats[, columns_to_keep, drop = FALSE]
-
   # Give Density and Transitivity in percentage
   summary_stats$Density <- summary_stats$Density * 100
   summary_stats$Transitivity <- summary_stats$Transitivity * 100
 
   # Rename columns
   summary_stats <- summary_stats %>%
-    dplyr::rename(`Dates` = Date_Range,
-                  `Papers` = Total_Papers,
-                  `Authors` = Total_Authors,
-                  `Density (%)` = Density,
-                  `Transitivity (%)` = Transitivity,
-                  `Mean Shortest Path` = Mean_shortest_path,
-                  `Cutpoints` = Number_of_cutpoints)
+    dplyr::rename_with(dplyr::recode,
+                       "Date_Range" = "Dates",
+                       "Total_Papers" = "Papers",
+                       "Total_Authors" = "Authors",
+                       "Average_Authors_per_Paper" = "Authors per Paper",
+                       "Density" = "Density (%)",
+                       "Transitivity" = "Transitivity (%)",
+                       "Mean_degree_centrality" = "Degree Centrality",
+                       "Mean_betweenness_centrality" = "Betweenness Centrality",
+                       "Mean_harmonic_centrality" = "Harmonic Centrality",
+                       "Mean_shortest_path" = "Shortest Path",
+                       "Number_of_cutpoints" = "Cutpoints")
 
   return(summary_stats)
 }

inst/Templates/Summary_template.Rmd

@@ -11,7 +11,35 @@ toc: FALSE
 
 Input data: `r report_var$config$input_name`
 
-```{r echo=FALSE}
-knitr::kable(summary_var$summary_stats, format = "latex", booktabs = TRUE, digits = 1)
+# General information
+```{r echo=FALSE, warning=FALSE}
+columns_to_keep <- c("Dates",
+                     "Papers",
+                     "Authors",
+                     "Authors per Paper")
+df <- summary_var$summary_stats[, columns_to_keep, drop = FALSE]
+knitr::kable(df, format = "latex", booktabs = TRUE, digits = 1)
 ```
+
+# Network properties
+```{r echo=FALSE, warning=FALSE}
+columns_to_keep <- c("Dates",
+                     "Density (%)",
+                     "Transitivity (%)",
+                     "Shortest Path",
+                     "Cutpoints")
+df <- summary_var$summary_stats[, columns_to_keep, drop = FALSE]
+knitr::kable(df, format = "latex", booktabs = TRUE, digits = 1)
+```
+
+# Author centrality
+```{r echo=FALSE, warning=FALSE}
+columns_to_keep <- c("Dates",
+                     "Degree Centrality",
+                     "Betweenness Centrality",
+                     "Harmonic Centrality")
+df <- summary_var$summary_stats[, columns_to_keep, drop = FALSE]
+knitr::kable(df, format = "latex", booktabs = TRUE, digits = 1)
+```
+
 More statistics in csv format can be found in `data/Summary_statistics.csv`.

tests/testthat/test-Text-utils.R

@@ -17,6 +17,7 @@ test_that("format_summary_stats works correctly", {
     End_year = c(2001, 2003),
     Total_Papers = c(10, 15),
     Total_Authors = c(5, 7),
+    Average_Authors_per_Paper = c(2, 2.5),
     Density = c(0.5, 0.6),
     Transitivity = c(0.3, 0.4),
     Mean_shortest_path = c(2.5, 2.8),
@@ -27,15 +28,15 @@ test_that("format_summary_stats works correctly", {
   formatted_stats <- format_summary_stats(summary_stats)
 
   # Check the structure of the formatted_stats
-  expect_equal(ncol(formatted_stats), 7)
-  expect_equal(colnames(formatted_stats), c("Dates", "Papers", "Authors", "Density (%)", "Transitivity (%)", "Mean Shortest Path", "Cutpoints"))
+  expect_equal(ncol(formatted_stats), 10)
+  expect_true(all(c("Dates", "Papers", "Authors", "Density (%)", "Transitivity (%)", "Shortest Path", "Cutpoints") %in% colnames(formatted_stats)))
 
   # Check the values of the formatted_stats
   expect_equal(formatted_stats$Dates, c("2000-2001", "2002-2003"))
   expect_equal(formatted_stats$Papers, c(10, 15))
   expect_equal(formatted_stats$Authors, c(5, 7))
   expect_equal(formatted_stats$`Density (%)`, c(50, 60))
   expect_equal(formatted_stats$`Transitivity (%)`, c(30, 40))
-  expect_equal(formatted_stats$`Mean Shortest Path`, c(2.5, 2.8))
+  expect_equal(formatted_stats$`Shortest Path`, c(2.5, 2.8))
   expect_equal(formatted_stats$Cutpoints, c(1, 2))
 })