Update

Data.descriptor/Technical_validation.Rmd

@@ -25,14 +25,16 @@ library(patchwork)
 library(splus2R)
 library(ggpubr)
 
+options(dplyr.summarise.inform=F)
+
 ```
 
 # Preface
 This code corresponds with the Technical Validation section in the Data Descriptor "Building schematic of Vienna in the late 1920s", published by Nature Scientific Data.
 
 Please consider the following steps to run the code
 1. Create a new directory on your computer (e.g. "c:/building.schematic")
-2. Download the files from the [Github repository](https://github.com/ukral/building.registry) into your new directory.
+2. Download the files from the [Github repository](https://github.com/ukral/building.registry) and save them in your new directory.
 3. Copy the path of your new directory into the code at line 42.
 
 # Import datasets
@@ -50,25 +52,24 @@ dataset <- read.csv(file=paste(path, "Dataset.csv", sep = ""), sep = ";", string
 cadastral_raw <- read.csv(file=paste(path, "/Data.descriptor/Online-only Table 2.csv", sep=""),  sep = ";" , stringsAsFactors = F)
 cadastral <- cadastral_raw[1:66,] # Cadastral communities mentioned in the analog building schematic
 
-# Import file "adressen_standorte_wien_20201015.csv". This file includes today's street names. The is available on the Open Government Data platform and can be retrieved from https://www.data.gv.at/katalog/dataset/stadt-wien_adressdatenderstadtwien. We retrieved the file at 15 October 2020 and copied it the the Github repository.
+# Import file "adressen_standorte_wien_20201015.csv". This file includes today's street names in the city of Vienna. [Open data Österreich](https://www.data.gv.at/katalog/dataset/stadt-wien_adressdatenderstadtwien)
 adressen <- read.csv(file=paste(path, "/Data.descriptor/adressen_standorte_wien_20201015.csv", sep=""), sep = ";", stringsAsFactors = F,fileEncoding = "UTF-8")
 
-# Import file "statistical_yearbook (1914).xlsx"
-floors_1914 <- data.frame(read_xlsx(paste(path, "/Data.descriptor/statistical_yearbook (1914).xlsx", sep=""), sheet = "STKW_hist", col_names = F, range = "B7:I27"), stringsAsFactors = F)
+# Import file "statistical_yearbook (1914).xlsx". Data retrieved from digitized report [Statistisches Jahrbuch der Stadt Wien. Bd. 1914](https://www.digital.wienbibliothek.at/wbrobv/periodical/titleinfo/2057276)
+floors_1914 <- read_xlsx(paste(path, "/Data.descriptor/statistical_yearbook (1914).xlsx", sep=""), sheet = "STKW_hist", col_names = TRUE, range = "B7:I27")
 
 colnames(floors_1914) <- c("UD.1920s", "FLOORS_0", "FLOORS_1", "FLOORS_2", "FLOORS_3", "FLOORS_4", "FLOORS_5", "FLOORS_unknown")
 
-# Import file "statistical_yearbook (1923).xlsx"
+# Import file "statistical_yearbook (1923).xlsx". Data retrieved from digitized report [Statistisches Jahrbuch der Stadt Wien. Bd. 1929 (1. Jahrgang)](https://www.digital.wienbibliothek.at/wbrobv/periodical/titleinfo/2057276)
 yearbook_1923 <- read_xlsx(paste(path, "/Data.descriptor/statistical_yearbook (1923).xlsx", sep=""), sheet = "Rohdaten", col_names =  TRUE, col_types = rep("numeric", times = 2))
 
 
-
-
 ```
 
 
 # Internal validation
 This code section produces Figure 6 in the Data Descriptor.
+
 ## ID
 ```{r}
 # Create categories
@@ -150,7 +151,7 @@ dataset <- merge(dataset, str_gesamt, by.x = "str_2010_norm", by.y = "str_gesamt
 # Assigning standardized names from "Adressen Standorte Wien" to the standardized names of STR.1920s.
 dataset <- merge(dataset, str_gesamt, by.x = "str_1920_norm", by.y = "str_gesamt", all.x = TRUE)
 
-length(levels(as.factor(dataset$str_ma37.y))) 
+check_length_ma37.y <- length(levels(as.factor(dataset$str_ma37.y))) 
 
 match_yes<- dataset[which(dataset$str_ma37.y != ""),] 
 match_no <- dataset[which(is.na(dataset$str_ma37.y) == T),] 
@@ -179,7 +180,7 @@ pos_str_1920_spelling_1 <- c(which(dataset$str_1920_norm == dataset$str_2010_nor
 
 pos_str_1920_spelling_2 <- c(which(is.na(match_no_control$str_ma37.y) == T &is.na(match_no_control$str_ma37.x) == F),which(is.na(match_no_control$str_ma37.y) == T &is.na(match_no_control$str_ma37.x) == T))
 
-length(pos_str_1920_spelling_1)+length(pos_str_1920_spelling_2)-nrow(dataset)
+control_length_str_1920 <- length(pos_str_1920_spelling_1)+length(pos_str_1920_spelling_2)-nrow(dataset)
 
 str_1920_spelling_t1 <- c(match_yes_control[,"ID"], test1[,"ID"], test2[,"ID"])
 str_1920_spelling_t2 <- c(test3[,"ID"], test4[,"ID"])
@@ -467,8 +468,7 @@ floor_plot <- ggplot(floors_plot_bez, aes(fill=FLOORS.1920s, y=count, x=UD.1920s
     geom_bar(position="stack", stat="identity") +
     geom_text(data=totals, aes(x=UD.1920s, label=total, y=total, fill=NULL), nudge_y=150, size = 3) + 
     labs(title = "FLOORS.1920s", x="Urban district (UD.1920s)", y="Number of data entries", fill ="Number of floors\nabove ground floor")  +
-    #scale_fill_manual(name = "Data class")+  
-     scale_x_continuous(breaks = c(1:21))+
+    scale_x_continuous(breaks = c(1:21))+
     theme(plot.title = element_text(face = "bold")) +
     geom_point(aes(x = 1, y = 1, size = "Data not\navailable"), shape = NA, colour = "grey") +
     guides(size = guide_legend("", override.aes = list(shape = 15, size = 7)))
@@ -601,7 +601,7 @@ pdf_plot <-ggplot(data=pdf, aes(x=UD.1920s, y=Page.pdf)) +
   labs(title = "Page.pdf", x="Urban district (UD.1920s)", y="Page number (Page.pdf)\n[page count]") +
   scale_colour_discrete("Volume of analog\nbuilding schematic") +
   guides(color = guide_legend(override.aes = list(size=3, shape = rep(15,10))))+
-  theme(plot.title = element_text(face = "bold", family = "Helvetica"))+
+  theme(plot.title = element_text(face = "bold"))+
   scale_x_continuous(breaks = c(1:21))+
   geom_text(data=totals, aes(x=UD.1920s, label= label_text, y = max), nudge_y=10, size =3)
 pdf_plot