[Link]
org/
[Link]
[Link]
[Link]
base Binaries for base distribution. This is what you want to install R for the first time.
Download R-4.3.2 for Windows (79 megabytes, 64 bit)
[Link]
[Link]
FIRST INSTALL R
choose yes for personal library
ALSO install readxl
library("readxl")
read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
Results <- read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
Results <- read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
data <- read_excel("D:/OneDrive - Izmir Yuksek Teknoloji
Enstitusu/3_Dersler/MBG328DigitalCell/[Link]")
data <- [Link]("D:/OneDrive - Izmir Yuksek Teknoloji
Enstitusu/3_Dersler/MBG328DigitalCell/coding/[Link]")
[Link](data$Area)
[Link](n= NULL, delta=2000, sd=2000, [Link]=0.05,power=0.9)
[Link](n= 9, delta=NULL, sd=2000, [Link]=0.05,power=0.9)
#Always plot your data, two data with similar statistics can have different distribution. THIS WORKS IN
RSTUDIO
library(ggplot2) # need for R
data(anscombe)
show(anscombe)
summary(anscombe)
lm(y1~x1, data=anscombe)
lm(y2~x2, data=anscombe)
lm(y3~x3, data=anscombe)
lm(y4~x4, data=anscombe)
sapply(1:4,function(x) cor(anscombe [,x], anscombe [,x+4]))
sapply(5:8,function(x) var(anscombe [,x]))
library(ggplot2)
p1<-ggplot(anscombe) + geom_point(aes(x1,y1))
p1
p2<- ggplot(anscombe)+geom_point(aes(x2,y2))
p3<- ggplot(anscombe)+geom_point(aes(x3,y3))
p4<- ggplot(anscombe)+geom_point(aes(x4,y4))
p2
p3
p4
[Link](1) #initialize a pseudorandom number generator
data0<- rnorm(100)
plot(data0,t="p") #plotted as points
hist(data0)
qqnorm(data0, xlim=c(-3,3), ylim=c(-3,3), main="Normal Q-Q Plot",
xlab= "Theoretical Quantiles", ylab="Sample Quantiles", [Link]= TRUE)
abline(a=0,b=1,lty=2) #y=b*x+a lty is line type dashed or not
data <- [Link]
qqnorm(data$Area, xlim=c(-1000,1000), ylim=c(-1000,1000), main="Normal Q-Q Plot",
xlab= "Theoretical Quantiles", ylab="Sample Quantiles", [Link]= TRUE)
hist(data$Area)
qqnorm(book2$datax, xlim=c(-3,3), ylim=c(-3,3), main="Normal Q-Q Plot",
xlab= "Theoretical Quantiles", ylab="Sample Quantiles", [Link]= TRUE)
qqnorm(Results$Area, xlim=c(0,1000), ylim=c(0,1000), main="Normal Q-Q Plot",
xlab= "Theoretical Quantiles", ylab="Sample Quantiles", [Link]= TRUE)
abline(a=0,b=1,lty=2) #y=b*x+a lty is line type dashed or not
[Link](data0)
summary(data0)
sd(data0)
[Link](book2$datax)
[Link](data0,mu=1) #Does data0 have mean of 1?
[Link](data0,mu=0.1)
[Link](1)
data1<- rnorm(8, mean=1, sd=0.3)
data2<- rnorm(8, mean=3, sd=0.9)
plot(data1,t="p") # or data1plot <- plot(data1,t="p")
plot(data2,t="p") # or data2plot <- plot(data2,t="p")
[Link](data1, data2)
[Link](data1, data2, paired=FALSE, [Link]=FALSE)
#for non-normal data means wilcoxon
[Link](1)
data3<- rbeta(40,5,1)
data4<- rbeta(40,2,1)
[Link](data3,data4)
[Link](data3,data4, paired=TRUE)
[Link](data3,data4, paired=FALSE, [Link]=FALSE)
[Link](Results$Circ.,Results$Round)
#for non-normal data distributions kolmogorov-smirnov
[Link](data3,data4)
cdf3<- ecdf(data3) # generate cumulative distribution function cdf
cdf4<- ecdf(data4)
pdf("[Link]") # open a pdf file
plot(0,0, type="l", xlim=c(0,1), ylim=c(0,1), xlab="Circularity", ylab="Cumulative probability")
lines(cdf3,lwd=2)
lines(cdf4, col="gray", lwd=2)
legend("topleft", legend=c("data3", "data4"), bty="o", col=c("black","gray"), lwd=2, bg="white")
[Link]()
[Link](data3,data4)
cdf3<- ecdf(data3) # generate cumulative distribution function cdf
cdf4<- ecdf(data3)
pdf("[Link]") # open a pdf file
plot(0,0, type="l", xlim=c(0,1), ylim=c(0,1), xlab="Circularity", ylab="Cumulative probability")
lines(cdf3,lwd=4)
lines(cdf4, col="gray", lwd=2)
legend("topleft", legend=c("data3", "data4"), bty="o", col=c("black","gray"), lwd=2, bg="white")
[Link]()
[Link](data3,data33)
cdf3<- ecdf(data3) # generate cumulative distribution function cdf
cdf33<- ecdf(data33)
pdf("[Link]") # open a pdf file
plot(0,0, type="l", xlim=c(0,1), ylim=c(0,1), xlab="Circularity", ylab="Cumulative probability")
lines(cdf3,lwd=4)
lines(cdf33, col="gray", lwd=2)
legend("topleft", legend=c("data3", "data33"), bty="o", col=c("black","gray"), lwd=2, bg="white")
[Link]()
cdf1<- ecdf(data1) # generate cumulative distribution function cdf
cdf2<- ecdf(data2)
pdf("[Link]") # open a pdf file
plot(0,0, type="l", xlim=c(0,3), ylim=c(0,3), xlab="Circularity", ylab="Cumulative probability")
lines(cdf1,lwd=2)
lines(cdf2, col="gray", lwd=2)
legend("topleft", legend=c("data1", "data2"), bty="o", col=c("black","gray"), lwd=2, bg="white")
[Link]()
#for percent comparison
data5<-matrix(c(18,460,57,466), byrow=TRUE,2,2)
rownames(data5)=c("ctrl","rnai")
colnames(data5)=c("mitosis","interphase")
data5
[Link](data5)
data55<-matrix(c(18,460,17,466), byrow=TRUE,2,2)
rownames(data55)=c("ctrl","rnai")
colnames(data55)=c("mitosis","interphase")
data55
[Link](data55)
data6 <- [Link] (
signal=c(3, 3, 2, 3, 3, 2, 3, 3, 2, 3, 3, 2, 3, 3, 2, 3, 3, 2, 3, 3, 2,
3, 3, 2, 3, 3, 2, 3, 3, 2),
condition = factor(rep(c("ctrl","sirna1","sirna2"),10)))
data6 # to see the data
data6_av <- aov(signal ~ condition, data6)
summary(data6_av)
-----
TELLS US THERE IS A SIGNIFICANT DIFFERENCE THAT DEPENDS ON THE "condition" VARIABLE
Df Sum Sq Mean Sq F value Pr(>F)
condition 2 6.667 3.333 3.45e+31 <2e-16 ***
Residuals 27 0.000 0.000
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
-----
data6_tukey <- TukeyHSD(data6_av) #HSD Honestly significant difference
data6_tukey
TESTS ALL THE PAIRWISE COMBINATIONS
------Bütün data alt alta olunca ok ama kendisi çoklu sütun okumadı------
value <- read_excel("E:/_Rprogramming/[Link]")
View(value)
library(readxl)
group <- read_excel("E:/_Rprogramming/[Link]")
View(group)
dpo <- [Link](v=value, g=group) #burada x ve y birleşiyor, excellerden birinde x diğerinde y var tüm
veriler altalta
View(dpo)
dpo_av<- aov(value~group,dpo)
summary(dpo_av)
dpo_tukey<- TukeyHSD(dpo_av)
dpo_tukey
plot(data6_tukey) # bu anlaşılmıyor çünkü değerleri yuvarlamıştım
plot(dpo_tukey) # bu anlaşılır
data6 <- [Link] (
signal=c(294.9, 287.6, 195.2, 290.3, 309.7, 201.2, 291.1, 322.7, 203.7, 325.7, 301.7, 205.5, 302.2, 310.1,
196.4, 303.8, 297.5, 211.8, 297.1, 298.2, 209.8,
287.9, 292.5, 201.3, 311.9, 312.2, 191.5, 294.8, 284.8, 195.9),
condition = factor(rep(c("ctrl","sirna1","sirna2"),10)))
data6 # to see the data
plot(data6_tukey)
[Link]::[Link](data6$signal,data6$condition)
data7 <- [Link]( response=c(6,9.7, 5.8,
6,8.8,6.5,5.7,8.5,5.9,5.6,9.2,6,5.9,8.5,5.6,5.9,9,6.1,6.3,9.1,5.9,6,9.3,5,6.5,9,6,5.7,9.3,6.3),
treatment=factor(rep(c("vehicle", "drug1","drug2"),10)))
> [Link](data6$signal)
> [Link](data7$response)
data7
#for non-normal use Kruskal-Wallis instead of Anova
[Link](response~treatment,data7)
#for non-normal use Dunn-Holland-Wolfe test for pairwise testing within group like Tukey after Anova,
Dunn after Kruskal
[Link]("[Link]")
[Link]::[Link](data7$response,data7$treatment)
-------------------
data600 <- [Link] (
signal=c(3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3),
condition = factor(rep(c("ctrlx","sirna1x","sirna2x"),10)))
data600 # to see the data
data600_av <- aov(signal ~ condition, data600)
summary(data600_av)
-----
TELLS US THERE IS A SIGNIFICANT DIFFERENCE THAT DEPENDS ON THE "condition" VARIABLE
Df Sum Sq Mean Sq F value Pr(>F)
condition 2 6.667 3.333 3.45e+31 <2e-16 ***
Residuals 27 0.000 0.000
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
-----
plot(data600_tukey)
TESTS ALL THE PAIRWISE COMBINATIONS
data7 <-
[Link]( response=c(1826,1968,1961,5418,4711,3403,1394,1362,1856,2592,3200,3796,1102,906,1008,9
09,796,992,874,777,762,1130,1191,967,751,930,980,717,657,724,619,681,706,1718,1919,1371),
+ treatment=factor(rep(c("ccECM", "glass","TGF"),12)))
> View(data7)
> #for non-normal use Kruskal-Wallis instead of Anova
> [Link](response~treatment,data7)
library(readxl)
library(ggplot2)
library(cowplot)
df <- read_excel("C:/Users/fatih/OneDrive/Documents/[Link]",
sheet = "testforplot1")
df <- read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]",
sheet = "testforplot1")
("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
base_plot <- ggplot(df, aes(x = 1, color = factor(replicate))) +
labs(x = "",
y = "",
color = "Legend") +
theme_bw() +
theme([Link].x = element_blank(),
[Link] = element_blank())
plot_area <- base_plot +
geom_point(aes(y =Area), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "Area") +
guides(color = FALSE)
plot_circ <- base_plot +
geom_point(aes(y = Circ.), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "Circ.") +
guides(color = FALSE)
plot_ar <- base_plot +
geom_point(aes(y = AR), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "AR") +
guides(color = FALSE)
plot_round <- base_plot +
geom_point(aes(y = Round), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "Round") +
guides(color = FALSE)
plot_solidity <- base_plot +
geom_point(aes(y = Solidity), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "Solidity")
combined_plot <- plot_grid(plot_area, plot_circ, plot_ar,
plot_round, plot_solidity, ncol = 5)
combined_plot
------------------------------------- -----------------------------------------
base_plot <- ggplot(my_data_long, aes(x = 1, color = factor(replicate))) +
labs(x = "",
y = "",
color = "Legend") +
theme_bw() +
theme([Link].x = element_blank(),
[Link] = element_blank())
plot_cond1 <- base_plot +
geom_point(aes(y =cond1), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "cond1") +
guides(color = FALSE)
plot_cond2 <- base_plot +
geom_point(aes(y =cond2), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "Cond2") +
guides(color = FALSE)
plot_cond3 <- base_plot +
geom_point(aes(y = cond3), position = position_jitterdodge([Link] = 1), size = 1) +
labs(y = "cond3") +
guides(color = FALSE)
combined_plot <- plot_grid(plot_cond1, plot_cond2, plot_cond3, ncol = 4)
combined_plot
# Install and load the tidyverse package if not already installed
if (!requireNamespace("tidyverse", quietly = TRUE)) {
[Link]("tidyverse")
# Load the tidyverse package
library(tidyverse)
library("readxl")
my_data <- read_excel("C:\\Users\\devrim-okvur\\Desktop\\[Link]")
# Assuming your data frame is named 'my_data'
# Replace 'my_data' with the actual name of your data frame
# Reshape the data from wide to long format
my_data_long <- my_data %>%
gather(key = "cond", value = "Measurements", -replicate)
# Sort the data based on Experimental Repeat Number and Condition
my_data_long <- my_data_long %>%
arrange(replicate, cond)
# Print the resulting data frame
print(my_data_long)
# Install and load the writexl package if not already installed
if (!requireNamespace("writexl", quietly = TRUE)) {
[Link]("writexl")
}
# Load the writexl package
library(writexl)
library(openxlsx)
# Specify the file path where you want to save the Excel file
excel_file_path <- "C:\\Users\\devrim-okvur\\Desktop\\my_data_long.xlsx"
# Write the data frame to an Excel file
write_xlsx(my_data_long, excel_file_path)
# Print a message indicating where the file has been saved
cat("Data has been exported to:", excel_file_path, "\n")
# Specify the file path where you want to save the CSV file
csv_file_path <- "path/to/your/folder/my_data_long.csv"
# Write the data frame to a CSV file
[Link](my_data_long, csv_file_path, [Link] = FALSE)
# Print a message indicating where the file has been saved
cat("Data has been exported to:", csv_file_path, "\n")
# Assuming your data frame is named 'my_data_long'
# Replace 'my_data_long' with the actual name of your data frame
# Install and load the ggplot2 package if not already installed
if (!requireNamespace("ggplot2", quietly = TRUE)) {
[Link]("ggplot2")
library(ggplot2)
# Scatter plot with ggplot2
ggplot(my_data_long, aes(x = replicate, y = Measurements, color = cond)) +
geom_point(position = position_jitter(width = 0.2, height = 0), alpha = 0.6, size = 2) +
geom_smooth(method = "lm", se = FALSE, color = "black") +
labs(title = "SuperPlotsofData", x = "replicate", y = "Measurements") +
theme_minimal() +
theme([Link]="right") +
scale_color_manual(values = c("blue", "green", "red")) # Customize colors based on your needs
xxxxxxxxxxxxxxxxx
# Assuming your data frame is named 'my_data_long'
# Replace 'my_data_long' with the actual name of your data frame
# Install and load the ggplot2 package if not already installed
if (!requireNamespace("ggplot2", quietly = TRUE)) {
[Link]("ggplot2")
library(ggplot2)
# Scatter plot with ggplot2
ggplot(my_data_long, aes(x = cond, y = Measurements, color = factor(replicate))) +
geom_point(position = position_jitter(width = 0.2, height = 0), alpha = 0.6, size = 2) +
geom_smooth(aes(group = factor(replicate)), method = "lm", se = FALSE, color = "black") +
labs(title = "SuperPlotsofData", x = "Condition", y = "Measurements") +
theme_minimal() +
theme([Link]="right") +
scale_color_manual(values = c("1" = "magenta", "2" = "green", "3" = "red")) # Customize colors based
on your needs
Absolutely! You can achieve similar visualizations in Python using the `matplotlib` and `seaborn`
libraries. Here's an example using `seaborn`:
```python
import seaborn as sns
import [Link] as plt
# Assuming your DataFrame is named 'my_data_long'
# Replace 'my_data_long' with the actual name of your DataFrame
# Scatter plot with seaborn
[Link](style="whitegrid")
[Link](figsize=(10, 6))
# Adjust the palette and markers based on your preferences
[Link](data=my_data_long, x="Condition", y="Measurements",
hue="Experimental_Repeat_Number",
palette={"1": "blue", "2": "green", "3": "red"},
marker='o', alpha=0.6, s=80)
# Add a linear regression line
[Link](data=my_data_long, x="Condition", y="Measurements", scatter=False, color='black')
# Set plot labels and title
[Link]("SuperPlotsofData")
[Link]("Condition")
[Link]("Measurements")
# Show the legend
[Link](title="Experimental Repeat Number")
# Show the plot
[Link]()
```
In this Python code:
- `seaborn` is used for creating the scatter plot and regression line.
- The `hue` parameter is used to differentiate replicates (Experimental Repeat Number) using different
colors.
- `regplot` is used to add a linear regression line.
- Adjust the palette (`palette`) and markers (`marker`) based on your preferences.
Make sure to install the necessary libraries by running `pip install seaborn matplotlib` if you haven't
already.
Feel free to customize the code based on your specific needs and preferences.
import seaborn as sns
import [Link] as plt
# Assuming your DataFrame is named 'my_data_long'
# Replace 'my_data_long' with the actual name of your DataFrame
# Scatter plot with seaborn
[Link](style="whitegrid")
[Link](figsize=(10, 6))
# Adjust the palette and markers based on your preferences
[Link](data=my_data_long, x="Condition", y="Measurements",
hue="Experimental_Repeat_Number",
palette={"1": "blue", "2": "green", "3": "red"},
marker='o', alpha=0.6, s=80)
# Add a linear regression line
[Link](data=my_data_long, x="Condition", y="Measurements", scatter=False, color='black')
# Set plot labels and title
[Link]("SuperPlotsofData")
[Link]("Condition")
[Link]("Measurements")
# Show the legend
[Link](title="Experimental Repeat Number")
# Show the plot
[Link]()