Fixed figure rendering R scripts, added data to plot figure 2

Code/DistantCRC_Figures_Fig2.Rmd

@@ -13,14 +13,13 @@ library(ggplot2)
 library(readr)
 library(dplyr)
 library(scales)
-library(cowplot)
 ```
 
 
 #Read in data
 ```{r, message=FALSE}
 # Read in SEER extracted table
-CRCStages <- readr::read_delim("K:/SEER_DataTables/SEER_2000-2014_StageDistribution_noStratify.txt", "\t", escape_double = FALSE, trim_ws = TRUE)
+CRCStages <- readr::read_delim("../Data/SEER_2000-2014_StageDistribution_noStratify.txt", "\t", escape_double = FALSE, trim_ws = TRUE)
 colnames(CRCStages) <- c("Year", "Stage","Rate", "Count", "Population")
 CRCStages <- CRCStages %>% filter(Year != "2000-2014")
 CRCStages$Year <- as.numeric(CRCStages$Year)
@@ -54,7 +53,7 @@ library(readxl)
 
 ```{r}
 # Read in General CRC rate data
-Stage_JPs <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageOnly.xlsx", sheet=1) %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model))
+Stage_JPs <- read_excel("../Data/JoinPoint/Rate_StageOnly.xlsx", sheet=1) %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model))
 
 
 ```
@@ -72,21 +71,21 @@ lwds <- c(3, 4, 2, 1)
 
 ##Rates and Proportions by disease stage
 ```{r}
-Figure1A <- ggplot() + 
+Figure2A <- ggplot() + 
      geom_point(data=CRCStages3 %>% filter(Stage %in% c("Localized","Regional","Distant")), aes(x=Year, y=Rate, group=Stage, col=Stage, shape=Stage), show.legend = FALSE) + 
      geom_line(data=Stage_JPs, aes(x=Year, y=Model, group=Stage, col=Stage), show.legend = FALSE) +
 scale_x_continuous(breaks=c(1998, 2000, 2005, 2010, 2014), labels = c("1998", "2000", "2005", "2010", "2014"), minor_breaks = seq(1998,2014,1)) + 
      theme_classic() + theme(axis.text.x = element_text(angle=45, vjust=0.5), legend.position = "bottom") + 
      scale_color_manual(name="Stage",values = colorclasses) +
      scale_shape_manual(values=shapes) + 
      ylab("Rate per 100,000")
-Figure1A
+Figure2A
 ```
 
 # Format figure to export
 
 ```{r}
-Figure1Export <- ggplot() + 
+Figure2Export <- ggplot() + 
      geom_point(data=(CRCStages3 %>% filter(Stage %in% c("Localized","Regional","Distant"))), aes(x=Year, y=Rate, group=Stage, col=Stage, shape=Stage)) + 
      geom_line(data=Stage_JPs, aes(x=Year, y=Model, group=Stage, col=Stage)) +
      scale_x_continuous(breaks=c(1998, 2000, 2005, 2010, 2014), 
@@ -105,8 +104,8 @@ Figure1Export <- ggplot() +
           axis.text = element_text(size=10),
           axis.text.x = element_text(angle=45, vjust=0.5)
      )
-Figure1Export
-#ggsave(plot=Figure1Export, filename="Figure1.tiff", path="path/to/folder/DistantCRC_BriefComm", device = "tiff", width=16, height=10, units="cm", dpi = 300)
+Figure2Export
+#ggsave(plot=Figure2Export, filename="Figure2.tiff", path="path/to/folder/DistantCRC_BriefComm", device = "tiff", width=16, height=10, units="cm", dpi = 300)
 ```
 
 

Code/DistantCRC_Figures_Fig3_cowplot.Rmd

@@ -1,5 +1,5 @@
 ---
-title: "Full Figure 2 with cowplot"
+title: "Full Figure 3 with cowplot"
 output: 
      html_notebook:
           toc: true
@@ -24,9 +24,9 @@ library(readxl)
 
 
 ```{r}
-Early_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageEarly.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Early")
-Middle_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageMiddle.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Middle")
-Late_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageLate.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Late")
+Early_JP <- read_excel("../Data/JoinPoint/Rate_StageEarly.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Early")
+Middle_JP <- read_excel("../Data/JoinPoint/Rate_StageMiddle.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Middle")
+Late_JP <- read_excel("../Data/JoinPoint/Rate_StageLate.xlsx") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value", "Rate" = "Observed Y Value") %>% mutate(Year = as.integer(Year), Model = as.numeric(Model), Rate = as.numeric(Rate), AgeCategory = "Late")
 
 AllAges_JP <- rbind(Early_JP, Middle_JP, Late_JP)
 AllAges_JP$AgeCategory <- factor(AllAges_JP$AgeCategory, levels = c("Early","Middle","Late"))
@@ -71,8 +71,8 @@ Figure2A_themed
 
 # B: Sidedness
 ```{r}
-Prox_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageProximal.xlsx") %>% rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Side = "Proximal")
-Dist_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageDistal.xlsx") %>% rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Side = "Distal")
+Prox_JP <- read_excel("../Data/JoinPoint/Rate_StageProximal.xlsx") %>% rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Side = "Proximal")
+Dist_JP <- read_excel("../Data/JoinPoint/Rate_StageDistal.xlsx") %>% rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Side = "Distal")
 
 AllSides_JP <- rbind(Prox_JP, Dist_JP)
 AllSides_JP$Side <- factor(AllSides_JP$Side, levels=c("Proximal","Distal"))
@@ -143,19 +143,19 @@ library(readxl)
 ```
 
 ```{r}
-AI_JPs <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageAmericanIndian.xlsx", sheet=3) %>% 
+AI_JPs <- read_excel("../Data/JoinPoint/Rate_StageAmericanIndian.xlsx", sheet=3) %>% 
      mutate(Race = "American Indian/Alaska Native") %>% 
      rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Model = as.numeric(Model), APC=NULL)
-A_JPs <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageAsian.xlsx", sheet=3) %>% 
+A_JPs <- read_excel("../Data/JoinPoint/Rate_StageAsian.xlsx", sheet=3) %>% 
      mutate(Race = "Asian or Pacific Islander") %>% 
      rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Model = as.numeric(Model))
-B_JPs <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageBlack.xlsx", sheet=1) %>% 
+B_JPs <- read_excel("../Data/JoinPoint/Rate_StageBlack.xlsx", sheet=1) %>% 
      mutate(Race = "Black or African American") %>% 
      rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Model = as.numeric(Model))
-W_JPs <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageWhite.xlsx", sheet=1) %>% 
+W_JPs <- read_excel("../Data/JoinPoint/Rate_StageWhite.xlsx", sheet=1) %>% 
      mutate(Race = "White") %>% rename("Year" = "X Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Model = as.numeric(Model), X__1=NULL, X__2=NULL)
 
@@ -216,10 +216,10 @@ Figure2C_themed
 
 # D: Sex
 ```{r}
-RateFemale_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageFemale.xlsx") %>% 
+RateFemale_JP <- read_excel("../Data/JoinPoint/Rate_StageFemale.xlsx") %>% 
      rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Sex = "Female")
-RateMale_JP <- read_excel("U:/Box Sync/ProjectDocs/2017_DistantCRC/JoinPoint/Rate_StageMale.xlsx") %>% 
+RateMale_JP <- read_excel("../Data/JoinPoint/Rate_StageMale.xlsx") %>% 
      rename("Year" = "X Value", "Rate" = "Observed Y Value", "Model" = "Modeleded Y Value") %>% 
      mutate(Year = as.integer(Year), Rate = as.numeric(Rate), Model = as.numeric(Model), Sex = "Male")
 

Data/SEER_2000-2014_StageDistribution_noStratify.txt

@@ -0,0 +1,97 @@
+"Year of diagnosis"	"Summary stage 2000 (1998+)"	"Age-Adjusted Rate"	"Count"	"Population"
+2000-2014	In situ	0.0	0	1257898299
+2000-2014	Localized	18.3	228069	1257898299
+2000-2014	Regional	16.1	201425	1257898299
+2000-2014	Distant	8.8	110872	1257898299
+2000-2014	Unknown/unstaged	2.7	33638	1257898299
+2000-2014	Blank(s)	0.0	0	1257898299
+2000	In situ	0.0	0	78996813
+2000	Localized	21.2	15340	78996813
+2000	Regional	20.0	14457	78996813
+2000	Distant	9.4	6855	78996813
+2000	Unknown/unstaged	3.8	2708	78996813
+2000	Blank(s)	0.0	0	78996813
+2001	In situ	0.0	0	79867817
+2001	Localized	21.2	15539	79867817
+2001	Regional	19.8	14550	79867817
+2001	Distant	9.5	7044	79867817
+2001	Unknown/unstaged	3.4	2475	79867817
+2001	Blank(s)	0.0	0	79867817
+2002	In situ	0.0	0	80629975
+2002	Localized	21.0	15685	80629975
+2002	Regional	19.0	14250	80629975
+2002	Distant	9.7	7282	80629975
+2002	Unknown/unstaged	3.3	2475	80629975
+2002	Blank(s)	0.0	0	80629975
+2003	In situ	0.0	0	81347854
+2003	Localized	20.3	15516	81347854
+2003	Regional	18.5	14151	81347854
+2003	Distant	9.4	7232	81347854
+2003	Unknown/unstaged	3.2	2389	81347854
+2003	Blank(s)	0.0	0	81347854
+2004	In situ	0.0	0	82055585
+2004	Localized	19.7	15293	82055585
+2004	Regional	17.8	13823	82055585
+2004	Distant	9.3	7303	82055585
+2004	Unknown/unstaged	2.9	2246	82055585
+2004	Blank(s)	0.0	0	82055585
+2005	In situ	0.0	0	80414394
+2005	Localized	19.6	15105	80414394
+2005	Regional	17.1	13190	80414394
+2005	Distant	9.2	7134	80414394
+2005	Unknown/unstaged	2.8	2129	80414394
+2005	Blank(s)	0.0	0	80414394
+2006	In situ	0.0	0	83099557
+2006	Localized	19.2	15467	83099557
+2006	Regional	16.6	13366	83099557
+2006	Distant	9.0	7331	83099557
+2006	Unknown/unstaged	2.8	2242	83099557
+2006	Blank(s)	0.0	0	83099557
+2007	In situ	0.0	0	83810676
+2007	Localized	19.1	15777	83810676
+2007	Regional	16.4	13554	83810676
+2007	Distant	8.8	7295	83810676
+2007	Unknown/unstaged	2.7	2212	83810676
+2007	Blank(s)	0.0	0	83810676
+2008	In situ	0.0	0	84618783
+2008	Localized	18.8	15838	84618783
+2008	Regional	15.9	13342	84618783
+2008	Distant	8.8	7453	84618783
+2008	Unknown/unstaged	2.5	2133	84618783
+2008	Blank(s)	0.0	0	84618783
+2009	In situ	0.0	0	85402713
+2009	Localized	18.0	15515	85402713
+2009	Regional	15.2	13058	85402713
+2009	Distant	8.6	7482	85402713
+2009	Unknown/unstaged	2.5	2151	85402713
+2009	Blank(s)	0.0	0	85402713
+2010	In situ	0.0	0	86160539
+2010	Localized	16.7	14770	86160539
+2010	Regional	14.6	12844	86160539
+2010	Distant	8.5	7547	86160539
+2010	Unknown/unstaged	2.4	2110	86160539
+2010	Blank(s)	0.0	0	86160539
+2011	In situ	0.0	0	86864476
+2011	Localized	16.0	14436	86864476
+2011	Regional	14.1	12708	86864476
+2011	Distant	8.4	7622	86864476
+2011	Unknown/unstaged	2.3	2136	86864476
+2011	Blank(s)	0.0	0	86864476
+2012	In situ	0.0	0	87543781
+2012	Localized	15.8	14599	87543781
+2012	Regional	13.9	12854	87543781
+2012	Distant	8.1	7587	87543781
+2012	Unknown/unstaged	2.2	1993	87543781
+2012	Blank(s)	0.0	0	87543781
+2013	In situ	0.0	0	88197699
+2013	Localized	15.2	14381	88197699
+2013	Regional	13.3	12537	88197699
+2013	Distant	8.1	7700	88197699
+2013	Unknown/unstaged	2.2	2056	88197699
+2013	Blank(s)	0.0	0	88197699
+2014	In situ	0.0	0	88887637
+2014	Localized	15.2	14808	88887637
+2014	Regional	13.2	12741	88887637
+2014	Distant	8.2	8005	88887637
+2014	Unknown/unstaged	2.2	2183	88887637
+2014	Blank(s)	0.0	0	88887637