friendly · lfpdroubi · May 21, 2025
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -55,7 +55,10 @@ Suggests:
     gridExtra,
     vcd,
     MASS,
-    forcats
+    forcats,
+    emojifont,
+    waffle,
+    PieGlyph
 License: GPL
 LazyLoad: yes
 LazyData: yes

diff --git a/man/Arbuthnot.Rd b/man/Arbuthnot.Rd
@@ -61,7 +61,7 @@ Campbell, R. B., Arbuthnot and the Human Sex Ratio (2001).
 \emph{Human Biology}, 73:4, 605-610.
 %\url{http://www.math.uni.edu/~campbell/arbuth.html}
 
-Creighton, C. (1965). A History of Epidemics in Britain, 2nd edition, vol. 1 and 2. 
+Creighton, C. (1965). A History of Epidemics in Britain, 2nd edition, vol. 1 and 2.
     NY: Barnes and Noble.
 
 S. Zabell (1976). Arbuthnot, Heberden, and the \emph{Bills of Mortality}.
@@ -78,5 +78,26 @@ lines(Arb.smooth$x, Arb.smooth$y, col="blue", lwd=2)
 
 # plot the total christenings to observe the anomalie in 1704
 with(Arbuthnot, plot(Year,Total, type='b', ylab="Total Christenings"))
+
+###########################################################################
+# Challenge 03: Dr. John Russell
+# github.com/drjohnrussell/30DayChartChallenge/blob/main/2025/Challenge03.R
+###########################################################################
+
+if (require("PieGlyph")) {
+  require(ggplot2)
+  Arbuthnot |>
+  transform(total=`Males` + `Females`) |>
+  ggplot(aes(x=Year, y=total)) +
+  geom_pie_glyph(slices=c("Males","Females"),
+                 color="black",radius=0.4) +
+  scale_fill_manual(values=c("lightblue","pink")) +
+  theme_minimal() +
+  theme(legend.position="bottom") +
+  labs(fill="Gender",
+       title="John Arbuthnot's Data on Male and Female Baptisms in London",
+       x="Year",
+       y="Total Baptisms")
+}
 }
 \keyword{datasets}
diff --git a/man/Cholera.Rd b/man/Cholera.Rd
@@ -40,7 +40,7 @@ Farr's table.
 }
 \details{
 The supply of \code{water} was classified as \dQuote{Thames, between Battersea and Waterloo Bridges}
-(central London), 
+(central London),
 \dQuote{New River, Rivers Lea and Ravensbourne}, and \dQuote{Thames, at Kew and Hammersmith}
 (western London).
 The factor levels use abbreviations for these.
@@ -49,7 +49,7 @@ The data frame is sorted by increasing elevation above the high water mark.
 }
 \source{
 Bingham P., Verlander, N. Q., Cheal M. J. (2004).
-John Snow, William Farr and the 1849 outbreak of cholera that affected London: 
+John Snow, William Farr and the 1849 outbreak of cholera that affected London:
 a reworking of the data highlights the importance of the water supply.
 \emph{Public Health}, 118(6), 387-394, Table 2.
 (The data was kindly supplied by Neville Verlander, including additional variables
@@ -67,7 +67,7 @@ The relevant tables are at pages clii -- clvii.
 data(Cholera)
 
 # plot cholera deaths vs. elevation
-plot(cholera_drate ~ elevation, data=Cholera, 
+plot(cholera_drate ~ elevation, data=Cholera,
 	pch=16, cex.lab=1.2, cex=1.2,
 	xlab="Elevation above high water mark (ft)",
 	ylab="Deaths from cholera in 1849 per 10,000")
@@ -81,15 +81,15 @@ lines(mort ~ elev, lwd=2, col="blue")
 
 if(require("car", quietly=TRUE)) {
 # show separate regression lines for each water supply
-  scatterplot(cholera_drate ~ elevation | water, data=Cholera, 
+  scatterplot(cholera_drate ~ elevation | water, data=Cholera,
               smooth=FALSE, pch=15:17,
               id=list(n=2, labels=sub(",.*", "", Cholera$district)),
               col=c("red", "darkgreen", "blue"),
               legend=list(coords="topleft", title="Water supply"),
               xlab="Elevation above high water mark (ft)",
               ylab="Deaths from cholera in 1849 per 10,000")
-  
-  scatterplot(cholera_drate ~ poor_rate | water, data=Cholera, 
+
+  scatterplot(cholera_drate ~ poor_rate | water, data=Cholera,
               smooth=FALSE, pch=15:17,
               id=list(n=2, labels=sub(",.*", "", Cholera$district)),
               col=c("red", "darkgreen", "blue"),
@@ -99,7 +99,7 @@ if(require("car", quietly=TRUE)) {
   }
 
 # fit a logistic regression model a la Bingham etal.
-fit <- glm( cbind(cholera_deaths, popn) ~ 
+fit <- glm( cbind(cholera_deaths, popn) ~
             water + elevation + poor_rate + annual_deaths +
             pop_dens + persons_house,
             data=Cholera, family=binomial)
@@ -113,5 +113,50 @@ if (require(effects)) {
   plot(eff)
 }
 
+###########################################################################
+# Challenge 01: Dr. John Russell
+# github.com/drjohnrussell/30DayChartChallenge/blob/main/2025/Challenge01.R
+# Hint: It works better if emojifont package is installed!
+###########################################################################
+
+if (require("emojifont")) {
+  load.fontawesome()
+}
+
+require(ggplot2)
+plot1 <- Cholera |>
+  ggplot(aes(x=elevation, y=cholera_drate,color=water)) +
+  geom_point() +
+  theme_bw() +
+  labs(y="Cholera Death Rate per 10000 citizens (log)",
+       x="Elevation (log)",
+       color="Water Source") +
+  theme(legend.position="bottom") +
+  scale_y_log10() +
+  scale_x_log10() +
+  scale_color_brewer(palette="Dark2")
+
+plot1
+
+if (require("waffle")) {
+  day1 <- Cholera |>
+    transform(newcholeradeaths = cholera_deaths/40) |>
+    sort_by(~water) |>
+    ggplot(aes(fill=water,values=newcholeradeaths)) +
+    geom_waffle(radius=grid::unit(0.4,"npc"),
+                size=.25) +
+    theme_void() +
+    labs(title="Deaths from Cholera in London in 1849",
+         subtitle="40 Deaths per Square",
+         caption="Data from William Farr's initial report, where he concluded
+         elevation \nwas the factor in the spread of plague",
+         fill="Water Source") +
+    scale_fill_brewer(palette="Dark2") +
+    theme(legend.position="bottom",
+          panel.background=element_rect(color="white"))
+
+day1
+}
+
 }
 \keyword{datasets}
diff --git a/man/Galton.Rd b/man/Galton.Rd
@@ -35,8 +35,8 @@ Galton, F. (1886). Regression Towards Mediocrity in Hereditary Stature
  \emph{Journal of the Anthropological Institute}, 15, 246-263
 }
 \references{
-Friendly, M. & Denis, D. (2005). The early origins and development of the scatterplot. 
-\emph{Journal of the History of the Behavioral Sciences}, 
+Friendly, M. & Denis, D. (2005). The early origins and development of the scatterplot.
+\emph{Journal of the History of the Behavioral Sciences},
 41, 103-130.
 
 Galton, F. (1869). \emph{Hereditary Genius: An Inquiry into its Laws and Consequences}.
@@ -46,21 +46,21 @@ Hanley, J. A. (2004). "Transmuting" Women into Men: Galton's Family Data on Huma
 \emph{The American Statistician}, 58, 237-243.
 See: \url{http://www.medicine.mcgill.ca/epidemiology/hanley/galton/} for source materials.
 
-Stigler, S. M. (1986). 
+Stigler, S. M. (1986).
 \emph{The History of Statistics: The Measurement of Uncertainty before 1900}.
 Cambridge, MA: Harvard University Press, Table 8.1
 
-Wachsmuth, A. W., Wilkinson L., Dallal G. E. (2003). 
-Galton's bend: A previously undiscovered nonlinearity in Galton's family stature regression data. 
-\emph{The American Statistician}, 57, 190-192. 
+Wachsmuth, A. W., Wilkinson L., Dallal G. E. (2003).
+Galton's bend: A previously undiscovered nonlinearity in Galton's family stature regression data.
+\emph{The American Statistician}, 57, 190-192.
 %\url{http://staff.ustc.edu.cn/~zwp/teach/Reg/galton.pdf}
 \doi{10.1198/0003130031874}
 
 }
 \seealso{
   \code{link{GaltonFamilies}},
 	\code{\link{PearsonLee}},
-	\code{galton} in the \pkg{psych} % \code{\link[psych]{galton}} 
+	\code{galton} in the \pkg{psych} % \code{\link[psych]{galton}}
 	}
 
 \examples{
@@ -76,7 +76,7 @@ data(Galton)
 # sunflower plot with regression line and data ellipses and lowess smooth
 ###########################################################################
 
-with(Galton, 
+with(Galton,
 	{
 	sunflowerplot(parent,child, xlim=c(62,74), ylim=c(62,74))
 	reg <- lm(child ~ parent)
@@ -87,5 +87,25 @@ with(Galton,
 		}
   })
 
+###########################################################################
+# Challenge 02: Dr. John Russell
+# github.com/drjohnrussell/30DayChartChallenge/blob/main/2025/Challenge02.R
+###########################################################################
+
+
+require(ggplot2)
+
+Galton |>
+  ggplot(aes(x=parent,y=child)) +
+  geom_point(position="jitter") +
+  geom_density2d_filled(alpha=.6,show.legend=FALSE,bins=9) +
+  theme_minimal() +
+  geom_smooth(method="loess",se=FALSE,color="red") +
+  geom_smooth(method="lm",se=FALSE) +
+  labs(title="Galton's Height Data",
+       x="Parent Height (inches)",
+       y="Child Height (inches)") +
+  scale_fill_brewer(type="seq")
+
 }
 \keyword{datasets}
diff --git a/man/PearsonLee.Rd b/man/PearsonLee.Rd
@@ -36,16 +36,16 @@ Pearson, K. and Lee, A. (1896). Mathematical contributions to the theory
 of evolution. On telegony in man, etc. \emph{Proceedings of the Royal Society of
 London}, 60 , 273-283.
 
-Pearson, K. and Lee, A. (1903). 
+Pearson, K. and Lee, A. (1903).
 On the laws of inheritance in man: I. Inheritance of physical characters. \emph{Biometrika}, 2(4), 357-462.
 (Tables XXII, p. 415; XXV, p. 417; XXVIII, p. 419 and XXXI, p. 421.)
 
 
 }
 \references{
-Wachsmuth, A.W., Wilkinson L., Dallal G.E. (2003). 
-Galton's bend: A previously undiscovered nonlinearity in Galton's family stature regression data. 
-\emph{The American Statistician}, 57, 190-192. 
+Wachsmuth, A.W., Wilkinson L., Dallal G.E. (2003).
+Galton's bend: A previously undiscovered nonlinearity in Galton's family stature regression data.
+\emph{The American Statistician}, 57, 190-192.
 %\url{http://staff.ustc.edu.cn/~zwp/teach/Reg/galton.pdf}
 \doi{10.1198/0003130031874}
 }
@@ -58,13 +58,13 @@ Galton's bend: A previously undiscovered nonlinearity in Galton's family stature
 data(PearsonLee)
 str(PearsonLee)
 
-with(PearsonLee, 
+with(PearsonLee,
     {
     lim <- c(55,80)
     xv <- seq(55,80, .5)
     sunflowerplot(parent,child, number=frequency, xlim=lim, ylim=lim, seg.col="gray", size=.1)
     abline(lm(child ~ parent, weights=frequency), col="blue", lwd=2)
-    lines(xv, predict(loess(child ~ parent, weights=frequency), data.frame(parent=xv)), 
+    lines(xv, predict(loess(child ~ parent, weights=frequency), data.frame(parent=xv)),
           col="blue", lwd=2)
     # NB: dataEllipse doesn't take frequency into account
     if(require(car)) {
@@ -106,5 +106,21 @@ ggplot(PearsonLee, aes(x = child, y = parent, weight=frequency)) +
    theme(legend.position = c(0.14, 0.885),
         legend.background = element_rect(fill = 'white'))
 
+###########################################################################
+# Challenge 02: Dr. John Russell
+# github.com/drjohnrussell/30DayChartChallenge/blob/main/2025/Challenge02.R
+###########################################################################
+
+PearsonLee |>
+  ggplot(aes(x=parent,y=child)) +
+  geom_point() +
+  theme_minimal() +
+  geom_smooth(aes(weight=frequency), method="lm", se=FALSE, color="red",size=2) +
+  geom_smooth(aes(weight = frequency), method="lm", se=FALSE) +
+  facet_grid(par ~ chl) +
+  labs(title="Pearson and Lee's Data on Parent and Child",
+       x="Parent Height (inches)",
+       y="Child Height (inches)")
+
 }
 \keyword{datasets}