Related
I have created a lollipop chart that I love. However, when the code runs to create the plot, the colors of the lines, segments, and points all change from what they were set to. Everything else runs great, so this isn't the end of the world, but I am trying to stick with a color palette throughout a report.
The colors should be this ("#9a0138", and "#000775" specifically):
But come out like this:
Any ideas?
Here is the data:
TabPercentCompliant <- structure(list(Provider_ShortName = c("ProviderA", "ProviderA", "ProviderA", "ProviderB",
"ProviderB", "ProviderB", "ProviderC", "ProviderC", "ProviderC", "ProviderD"), SubMeasureID = c("AMM2", "FUH7", "HDO", "AMM2", "FUH7", "HDO", "AMM2", "FUH7", "HDO", "AMM2"), AdaptedCompliant = c(139, 2, 117, 85, 1, 33, 36, 2, 22, 43), TotalEligible = c(238, 27, 155, 148, 10, 34, 61, 3, 24, 76), PercentCompliant = c(0.584033613445378, 0.0740740740740741, 0.754838709677419, 0.574324324324324, 0.1, 0.970588235294118, 0.590163934426229, 0.666666666666667, 0.916666666666667, 0.565789473684211 ), PercentTotalEligible = c(0.00516358587173479, 0.00058578495183546, 0.00336283953831467, 0.00321096936561659, 0.000216957389568689, 0.000737655124533542, 0.001323440076369, 6.50872168706066e-05, 0.000520697734964853, 0.00164887616072203), ClaimsAdjudicatedThrough = structure(c(19024, 19024, 19024, 19024, 19024, 19024, 19024, 19024, 19024, 19024 ), class = "Date"), AdaptedNCQAMean = c(0.57, 0.39, 0.93, 0.57, 0.39, 0.93, 0.57, 0.39, 0.93, 0.57), PerformanceLevel = c(0.0140336134453782, -0.315925925925926, -0.175161290322581, 0.00432432432432439, -0.29, 0.0405882352941176, 0.0201639344262295, 0.276666666666667, -0.0133333333333334, -0.00421052631578944)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"))
VBP_Report_Date = "2022-09-01"
And the code for the plot:
Tab_PercentCompliant %>%
filter(ClaimsAdjudicatedThrough == VBP_Report_Date) %>%
ggplot(aes(x = Provider_ShortName,
y = PercentCompliant)
) +
geom_line(aes(x = Provider_ShortName,
y = AdaptedNCQAMean,
group = SubMeasureID,
color = "#9a0138",
size = .001)
) +
geom_point(aes(color = "#000775",
size = (PercentTotalEligible)
)
) +
geom_segment(aes(x = Provider_ShortName,
xend = Provider_ShortName,
y = 0,
yend = PercentCompliant,
color = "#000775")
)+
facet_grid(cols = vars(SubMeasureID),
scales = "fixed",
space = "fixed")+
theme_classic()+
theme(legend.position = "none") +
theme(panel.spacing = unit(.5, "lines"),
panel.border = element_rect(
color = "black",
fill = NA,
linewidth = .5),
panel.grid.major.y = element_line(
color = "gray",
linewidth = .5),
axis.text.x = element_text(
angle = 65,
hjust=1),
axis.title.x = element_blank(),
axis.line = element_blank(),
strip.background = element_rect(
color = NULL,
fill = "#e1e7fa"))+
scale_y_continuous(labels = scales::percent)+
labs(title = "Test",
subtitle = "Test",
caption = "Test")
If you have an aesthetic constant, it is often easier / better to have it "outside" your aes call. If you want to have a legend for your color, then you need to keep it "inside", but you will need to manually set the colors with + scale_color/fill_manual.
I've had to cut down quite a lot in your code to make it work. I've also removed bits that are extraneous to the problem. I've removed line size = 0.001 or the line wasn't visible. I've removed the weird filter step or the plot wasn't possible.
Tips: when defining a global aesthetic with ggplot(aes(x = ... etc), you don't need to specify this aesthetic in each geom layer (those aesthetics will be inherited)- makes a more concise / readable code.
library(ggplot2)
ggplot(TabPercentCompliant, aes(x = Provider_ShortName, y = PercentCompliant)) +
geom_line(aes(y = AdaptedNCQAMean, group = SubMeasureID),
color = "#9a0138") +
geom_point(aes(size = PercentTotalEligible), color = "#000775") +
geom_segment(aes(xend = Provider_ShortName, y = 0, yend = PercentCompliant),
color = "#000775") +
facet_grid(~SubMeasureID) +
theme(strip.background = element_rect(color = NULL, fill = "#e1e7fa"))
Here is the final code. Thanks again tjebo!
# Lollipop Chart ----------------------------------------------------------
Tab_PercentCompliant %>%
filter(ClaimsAdjudicatedThrough == VBP_Report_Date) %>%
ggplot(aes(x = Provider_ShortName,
y = PercentCompliant)
) +
geom_line(aes(y = AdaptedNCQAMean,
group = SubMeasureID),
color = "#9a0138"
) +
geom_point(aes(size = PercentTotalEligible),
color = "#000775",
) +
geom_segment(aes(xend = Provider_ShortName,
y = 0,
yend = PercentCompliant),
color = "#000775"
)+
facet_grid(cols = vars(SubMeasureID)
)+
theme_bw()+
theme(legend.position = "none",
axis.text.x = element_text(
angle = 65,
hjust=1),
axis.title.x = element_blank(),
axis.line = element_blank(),
strip.background = element_rect(
fill = "#e1e7fa"))+
scale_y_continuous(labels = scales::percent)+
labs(title = "Test",
subtitle = "Test",
caption = "Test")
I'm struggling with the map tilt. I would like help to change the tilt of the following map. Thanks!
The first map is my result, the second map is how I would like the slope to be.
library(usmap)
library (ggplot2)
read.table("NY_data.txt", header = T)->NY_data
NY1 <- plot_usmap(regions = "county", include = c("NY"), data = NY_data, values = "YEAR_2010") +
labs(title = "New York by county", subtitle = "2010") +
theme(plot.title = element_text(face="bold", size=18, hjust = 0.5),
plot.subtitle = element_text(face="bold", size=16)) +
scale_fill_continuous(low = "white", high = "#CB454A", limits=c(0, 35),
name = "Cumulative cases",
guide = guide_colourbar(barwidth = 27, barheight = 0.5,
title.position = "top"),
label = scales::comma) +
theme(legend.position = "bottom",
legend.title=element_text(size=12, face = "bold"),
legend.text=element_text(size=10))
NY1
map1
map2
I've got a rough and ready function that can be used to compare two sets of values using histograms:
I want to set the individual edge colors of each of the histograms in the top plot (much as how I set the individual sets of values used for each histogram). How could this be done?
import os
import datavision
import matplotlib.pyplot
import numpy
import shijian
def main():
a = numpy.random.normal(2, 2, size = 120)
b = numpy.random.normal(2, 2, size = 120)
save_histogram_comparison_matplotlib(
values_1 = a,
values_2 = b,
label_1 = "a",
label_2 = "b",
normalize = True,
label_ratio_x = "measurement",
label_y = "",
title = "comparison of a and b",
filename = "histogram_comparison_1.png"
)
def save_histogram_comparison_matplotlib(
values_1 = None,
values_2 = None,
filename = None,
directory = ".",
number_of_bins = None,
normalize = True,
label_x = "",
label_y = None,
label_ratio_x = None,
label_ratio_y = "ratio",
title = "comparison",
label_1 = "1",
label_2 = "2",
overwrite = True,
LaTeX = False,
#aspect = None,
font_size = 20,
color_1 = "#3861AA",
color_2 = "#00FF00",
color_3 = "#7FDADC",
color_edge_1 = "#3861AA", # |<---------- insert magic for these
color_edge_2 = "#00FF00", # |
alpha = 0.5,
width_line = 1
):
matplotlib.pyplot.ioff()
if LaTeX is True:
matplotlib.pyplot.rc("text", usetex = True)
matplotlib.pyplot.rc("font", family = "serif")
if number_of_bins is None:
number_of_bins_1 = datavision.propose_number_of_bins(values_1)
number_of_bins_2 = datavision.propose_number_of_bins(values_2)
number_of_bins = int((number_of_bins_1 + number_of_bins_2) / 2)
if filename is None:
if title is None:
filename = "histogram_comparison.png"
else:
filename = shijian.propose_filename(
filename = title + ".png",
overwrite = overwrite
)
else:
filename = shijian.propose_filename(
filename = filename,
overwrite = overwrite
)
values = []
values.append(values_1)
values.append(values_2)
bar_width = 0.8
figure, (axis_1, axis_2) = matplotlib.pyplot.subplots(
nrows = 2,
gridspec_kw = {"height_ratios": (2, 1)}
)
ns, bins, patches = axis_1.hist(
values,
color = [
color_1,
color_2
],
normed = normalize,
histtype = "stepfilled",
bins = number_of_bins,
alpha = alpha,
label = [label_1, label_2],
rwidth = bar_width,
linewidth = width_line,
#edgecolor = [color_edge_1, color_edge_2] <---------- magic here? dunno
)
axis_1.legend(
loc = "best"
)
bars = axis_2.bar(
bins[:-1],
ns[0] / ns[1],
alpha = 1,
linewidth = 0, #width_line
width = bins[1] - bins[0]
)
for bar in bars:
bar.set_color(color_3)
axis_1.set_xlabel(label_x, fontsize = font_size)
axis_1.set_ylabel(label_y, fontsize = font_size)
axis_2.set_xlabel(label_ratio_x, fontsize = font_size)
axis_2.set_ylabel(label_ratio_y, fontsize = font_size)
#axis_1.xticks(fontsize = font_size)
#axis_1.yticks(fontsize = font_size)
#axis_2.xticks(fontsize = font_size)
#axis_2.yticks(fontsize = font_size)
matplotlib.pyplot.suptitle(title, fontsize = font_size)
if not os.path.exists(directory):
os.makedirs(directory)
#if aspect is None:
# matplotlib.pyplot.axes().set_aspect(
# 1 / matplotlib.pyplot.axes().get_data_ratio()
# )
#else:
# matplotlib.pyplot.axes().set_aspect(aspect)
figure.tight_layout()
matplotlib.pyplot.subplots_adjust(top = 0.9)
matplotlib.pyplot.savefig(
directory + "/" + filename,
dpi = 700
)
matplotlib.pyplot.close()
if __name__ == "__main__":
main()
You may simply plot two different histograms but share the bins.
import numpy as np; np.random.seed(3)
import matplotlib.pyplot as plt
a = np.random.normal(size=(89,2))
kws = dict(histtype= "stepfilled",alpha= 0.5, linewidth = 2)
hist, edges,_ = plt.hist(a[:,0], bins = 6,color="lightseagreen", label = "A", edgecolor="k", **kws)
plt.hist(a[:,1], bins = edges,color="gold", label = "B", edgecolor="crimson", **kws)
plt.show()
Use the lists of Patches objects returned by the hist() function.
In your case, you have two datasets, so your variable patches will be a list containing two lists, each with the Patches objects used to draw the bars on your plot.
You can easily set the properties on all of these objects using the setp() function. For example:
a = np.random.normal(size=(100,))
b = np.random.normal(size=(100,))
c,d,e = plt.hist([a,b], color=['r','g'])
plt.setp(e[0], edgecolor='k', lw=2)
plt.setp(e[1], edgecolor='b', lw=3)
I'm trying to convert a distribution into a pseudo-uniform distribution. Using the spd R package, it is easy and it works as expected.
library(spd)
x <- c(rnorm(100,-1,0.7),rnorm(100,3,1))
fit<-spdfit(x,upper=0.9,lower=0.1,tailfit="GPD", kernelfit="epanech")
uniformX = pspd(x,fit)
I want to generalize extreme value modeling to include threshold uncertainity. So I used the evmix package.
library(evmix)
x <- c(rnorm(100,-1,0.7),rnorm(100,3,1))
fit = fgkg(x, phiul = FALSE, phiur = FALSE, std.err = FALSE)
pgkg(x,fit$lambda, fit$ul, fit$sigmaul, fit$xil, fit$phiul, fit$ur,
fit$sigmaur, fit$xir, fit$phiur)
Im messing up somewhere.
Please check out the help for pgkg function:
help(pgkg)
which gives the syntax:
pgkg(q, kerncentres, lambda = NULL, ul = as.vector(quantile(kerncentres,
0.1)), sigmaul = sqrt(6 * var(kerncentres))/pi, xil = 0, phiul = TRUE,
ur = as.vector(quantile(kerncentres, 0.9)), sigmaur = sqrt(6 *
var(kerncentres))/pi, xir = 0, phiur = TRUE, bw = NULL,
kernel = "gaussian", lower.tail = TRUE)
You have missed the kernel centres (the data), which is always needed for kernel density estimators. Here is the corrected code:
library(evmix)
x <- c(rnorm(100,-1,0.7),rnorm(100,3,1))
fit = fgkg(x, phiul = FALSE, phiur = FALSE, std.err = FALSE)
prob = pgkg(x, x, fit$lambda, fit$ul, fit$sigmaul, fit$xil, fit$phiul,
fit$ur, fit$sigmaur, fit$xir, fit$phiur)
hist(prob) % now uniform as expected
I have the code below that is a combination of two boxplots and dot plots in one. It is a representation of barring density in 4 different species. The grey depicts the males and the tan the females.
data<-read.csv("C:/Users/Jeremy/Documents/A_Trogon rufus/Black-and-White/BARDATA_boxplots_M.csv")
datF<-read.csv("C:/Users/Jeremy/Documents/A_Trogon rufus/FEMALES_BW&Morphom.csv")
cleandataM<-subset(data, data$Age=="Adult" & data$White!="NA", select=(OTU:Density))
cleandatF<-subset(datF, datF$Age=="Adult", select=(OTU:Density))
dataM<- as.data.frame(cleandataM)
dataF<- as.data.frame(cleandatF)
library(ggplot2)
ggplot(dataM, aes(factor(OTU), Density))+
geom_boxplot(data=dataF,aes(factor(OTU),Density), fill="AntiqueWhite")+
geom_boxplot(fill="lightgrey", alpha=0.5)+
geom_point(data=dataF,position = position_jitter(width = 0.1), colour="tan")+
geom_point(data=dataM, position = position_jitter(width = 0.1), color="DimGrey")+ scale_x_discrete(name="",limits=order)+
scale_y_continuous(name="Bar Density (bars/cm)")+
theme(panel.background = element_blank(),panel.grid.minor=element_blank(),
panel.grid.major=element_blank(),axis.line = element_line(colour = "black"),
axis.title.y = element_text(colour="black", size=14),
axis.text.y = element_text(colour="black", size=12),
axis.text.x = element_text(colour="black", size=14))
This works just fine.
However, when I try to add a legend as:
legend("topright", inset=.01, bty="n", cex=.75, title="Sex",
c("Male", "Female"), fill=c("lightgrey", "black")
It returns the following Error:
Error in strwidth(legend, units = "user", cex = cex, font = text.font) :
plot.new has not been called yet
Please, is there someone who could suggest how to correct this?