doug add to ggplot

PlottingInR/inst/extdata/presRaw/ggplot2.Rmd

@@ -26,6 +26,7 @@ knitr::opts_chunk$set(echo = TRUE, tidy = T)
 if(params$isSlides == "yes"){AsSlides=T}else{AsSlides=F}
 ```
 
+
 ```{r, results='asis',include=TRUE,echo=FALSE}
 if(params$isSlides != "yes"){
   cat("# Plotting in R with ggplot2
@@ -474,6 +475,18 @@ pcPlot_violin <- pcPlot+geom_violin()
 pcPlot_violin
 ```
 
+---
+## Combining geoms in the same plot
+```{r, mult_geom_ggplot2, fig.height=4.5, fig.width=8}
+
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Sex,y=Height))
+
+pcPlot_combine <- pcPlot+ geom_boxplot() + geom_jitter(width = 0.25)
+
+pcPlot_combine
+```
+
 ---
 ## There are a world of geoms 
 An overview of geoms and thier arguments can be found in the ggplot2 documentation or within the ggplot2 quick reference guides.
@@ -867,7 +880,7 @@ pcPlot + geom_point() + facet_grid(Smokes~Sex)+
 
 ---
 ## Discrete axes scales
-Similary control over discrete scales is shown below.
+Similarly control over discrete scales is shown below.
 
 ```{r scaleDiscrete_ggplot2, facet_grid_smokesBySex_scaleDisceteX, fig.height=5, fig.width=9}
 pcPlot <- ggplot(data=patients_clean,aes(x=Sex,y=Height))
@@ -1107,6 +1120,21 @@ pcPlot + geom_point(size=4,alpha=0.8)+
                          name="Body Mass Index")
 ```
 
+---
+
+## Conditional scales and colors
+
+We can also use an ifelse conditional statement to apply discrete color cutoffs for groups of data points that aren't represented by categorical variables in the data set. 
+
+```{r, conditional_colors_scales, fig.height=4, fig.width=9}
+pcPlot <- ggplot(data=patients_clean,
+                 aes(x=Height,y=Weight,shape=Sex, colour=ifelse(BMI > 30, "high",
+                                                                ifelse(BMI < 25, "low", "middle"))))
+pcPlot + geom_point(size=4,alpha=0.8) + 
+  scale_shape_discrete(name="Gender") +
+  scale_color_manual(name = "BMI category", values=c("red", "blue", "grey"))
+```
+
 ---
 ```{r, results='asis',include=TRUE,echo=FALSE}
 if(params$isSlides == "yes"){
@@ -1155,6 +1183,7 @@ By default a "loess" smooth line is plotted by stat_smooth. Other methods availa
 pcPlot <- ggplot(data=patients_clean,
         mapping=aes(x=Weight,y=Height))
 pcPlot+geom_point()+stat_smooth(method="lm")
+
 ```
 
 ---
@@ -1166,7 +1195,7 @@ If color by Sex is an aesthetic mapping then two smooth lines are drawn, one for
 ```{r, stat_smoothlmgroups_ggplot2, fig.height=4, fig.width=9}
 pcPlot <- ggplot(data=patients_clean,
         mapping=aes(x=Weight,y=Height,colour=Sex))
-pcPlot+geom_point()+stat_smooth(method="lm")
+pcPlot+geom_point()+stat_smooth(aes(x=Weight,y=Height), method="lm")
 ```
 
 ---
@@ -1176,11 +1205,38 @@ This behavior can be overridden by specifying an aes within the stat_smooth() fu
 ```{r, stat_smoothlmgroupsOverridden_ggplot2, fig.height=4, fig.width=9}
 pcPlot <- ggplot(data=patients_clean,
         mapping=aes(x=Weight,y=Height,colour=Sex))
-pcPlot+geom_point()+stat_smooth(aes(x=Weight,y=Height),method="lm",
+pcPlot+geom_point()+
+  stat_smooth(aes(x=Weight,y=Height),method="lm",
                                 inherit.aes = F)
 ```
 
 ---
+
+## Marginal plots with ggEtxtra
+Plots for either the X or Y axis variables can easily be added to the margins of the plot to display the distributions of variables. By default this is a line. The groupColour and groupFill arguments carry over the colour aesthetic of the main plot.  
+
+```{r, marginal_ggplot, fig.height=4, fig.width=9, message = F}
+library(ggExtra)
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Weight,y=Height,colour=Sex)) + geom_point()
+ggMarginal(pcPlot, groupColour = TRUE, groupFill = TRUE)
+```
+
+---
+
+## Marginal plots with ggEtxtra
+We can easily turn this into a histogram and only display either X or Y axis.  
+
+```{r, marginal_ggplot2, fig.height=4, fig.width=9, message = F}
+
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Weight,y=Height,colour=Sex)) + geom_point()
+ggMarginal(pcPlot, groupColour = TRUE, groupFill = TRUE, type = "histogram", margins = "x")
+```
+
+
+---
+
 ## Summary statistics
 Another useful method is stat_summary() which allows for a custom statistical function to be performed and then visualized.
 
@@ -1189,10 +1245,107 @@ The fun parameter specifies a function to apply to the y variables for every val
 ```{r, stat_summary_ggplot2, fig.height=3.5, fig.width=9}
 pcPlot <- ggplot(data=patients_clean,
         mapping=aes(x=Sex,y=Height)) + geom_jitter()
-pcPlot + stat_summary(fun=quantile, geom="point",
+pcPlot + 
+  stat_summary(fun=quantile, geom="point",
                     colour="purple", size=8)
 ```
 
+---
+
+## Displaying fitted line statistics
+The ggpubr package has many handy functions to make publication quality graphics by displaying statistics. Here we add the equation and the R squared value for the line of best fit
+
+
+```{r, line_eqn, fig.height=3, fig.width=8}
+library(ggpubr)
+
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Weight,y=Height)) +
+  geom_point() + 
+  stat_smooth(method="lm", formula = y ~ x)  
+pcPlot +
+  stat_regline_equation(label.y = 185, aes(label = paste("Eqn: ", after_stat(eq.label))), formula = y ~ x) +
+  stat_regline_equation(label.y = 183, aes(label = after_stat(rr.label)), formula = y ~ x)
+```
+
+---
+
+## Displaying fitted line statistics
+By giving subsets of the data to the stat_regline_equation() function, we can display statistics for each group that we make a line of best fit 
+
+```{r, line_eqn_groups, fig.height=3, fig.width=8}
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Weight,y=Height,colour=Sex)) +geom_point()+ stat_smooth(aes(x=Weight,y=Height), method="lm", formula = y ~ x) 
+pcPlot +
+  stat_regline_equation(data = patients_clean[patients_clean$Sex == "Male", ], 
+                        label.y = 183, aes(label = after_stat(rr.label)), formula = y ~ x) + 
+  stat_regline_equation(data = patients_clean[patients_clean$Sex == "Female", ], 
+                        label.x = 80, label.y = 160, aes(label = after_stat(rr.label)), formula = y ~ x)  
+
+```
+---
+
+## Displaying stats on the plot
+The ggpubr package also has useful functions that allows the display p-values on plots when combined with the rstatix package. 
+
+Here we use rstatix to create a data frame with relevant statistics for our desired comparison, and then we add x and y position information. [Check out](https://rpkgs.datanovia.com/rstatix/) the the many other functions rstatix has to add information to this table (adhusted p, otehr stats tests, etc.)
+
+```{r, add_p1, message = F}
+library(rstatix)
+# https://rpkgs.datanovia.com/rstatix/
+
+stat.test <- t_test(patients_clean, Height ~ Sex) 
+stat.test <- add_xy_position(stat.test, x = "Sex", dodge = 0.8)
+
+data.frame(stat.test)
+```
+---
+
+## Displaying stats on the plot
+This data frame can then be used in the stat_pvalue_manual() function from ggpubr to add the pvalue. 
+
+```{r, add_p2, fig.height=4, fig.width=8}
+
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Sex,y=Height)) + 
+  geom_boxplot()
+
+# don't inherit aesthetic to make this work 
+pcPlot + stat_pvalue_manual(stat.test, label = "p", inherit.aes = F) + scale_y_continuous(expand = expansion(mult = 0.1))
+
+```
+
+---
+
+## Displaying stats for grouped data
+
+By grouping the dataframe, we can look for differences between smokers within sex. We also add an adjusted p-value. 
+```{r, grouped_p1}
+
+grouped_data <- group_by(patients_clean, Sex)
+stat.test <- t_test(grouped_data, formula = Height ~ Smokes) 
+stat.test <- adjust_pvalue(stat.test, method = "BH") 
+stat.test <- add_xy_position(stat.test, x = "Sex", dodge = 0.8)
+
+data.frame(stat.test)
+```
+
+---
+
+## Displaying stats for grouped data
+
+We can also modify the label of the p-values by putting the column used for the p-value inside curly brackets {} within a string. 
+```{r, grouped_p2, fig.height=4, fig.width=8}
+
+pcPlot <- ggplot(data=patients_clean,
+        mapping=aes(x=Sex ,y=Height, fill = Smokes)) + 
+  geom_boxplot() 
+
+# don't inherit aesthetic to make this work 
+pcPlot + stat_pvalue_manual(stat.test, label = "p = {p.adj}", inherit.aes = F) + scale_y_continuous(expand = expansion(mult = 0.1))
+```
+
+
 ---
 ```{r, results='asis',include=TRUE,echo=FALSE}
 if(params$isSlides == "yes"){