Linux Day 2017 a Pisa

R is a language and environment for statistical computing and graphics. It is a GNU project which is similar to the S language and environment which was developed at Bell Laboratories (formerly AT&T, now Lucent Technologies) by John Chambers and colleagues. R can be considered as a different implementation of S. There are some important differences, but much code written for S runs unaltered under R.

R provides a wide variety of statistical (linear and nonlinear modelling, classical statistical tests, time-series analysis, classification, clustering, …) and graphical techniques, and is highly extensible.

https://www.r-project.org/about.html

RStudio is an integrated development environment (IDE) for R. It includes a console, syntax-highlighting editor that supports direct code execution, as well as tools for plotting, history, debugging and workspace management.

RStudio is available in open source and commercial editions and runs on the desktop (Windows, Mac, and Linux) or in a browser connected to RStudio Server or RStudio Server Pro (Debian/Ubuntu, RedHat/CentOS, and SUSE Linux).

https://www.rstudio.com/products/rstudio/

• Vectors

• Data Frames

• Libraries

  • magrittr
  • dplyr
  • ggplot2
  • rmarkdown

(v <- c(1, 2, 3, 4, 5))

[1] 1 2 3 4 5

(v1 <- 1:5)

[1] 1 2 3 4 5

(v2 <- seq(from=1, to=5, by=1))

[1] 1 2 3 4 5

(v3 <- rep(1:2, times=3))

[1] 1 2 1 2 1 2

(v4 <- rep(1:2, each=3))

[1] 1 1 1 2 2 2

v5 <- rnorm(3)
v5

[1]  1.019617 -1.726204 -1.382875

v5[2]

[1] -1.726204

v5[-2]

[1]  1.019617 -1.382875

v5

[1]  1.019617 -1.726204 -1.382875

v5[2:3]

[1] -1.726204 -1.382875

v5[-(2:3)]

[1] 1.019617

v5

[1]  1.019617 -1.726204 -1.382875

v5[c(1, 2)]

[1]  1.019617 -1.726204

v5[-c(1,2)]

[1] -1.382875

v5

[1]  1.019617 -1.726204 -1.382875

v5[v5 < 0]

[1] -1.726204 -1.382875

fruits <- c("apple", "pear", "apple")
fruits[fruits == "apple"]

[1] "apple" "apple"

t <- seq(from = as.Date("2017-01-01"), 
         to = as.Date("2017-12-31"), 
         by = "days")
t[1:3]

[1] "2017-01-01" "2017-01-02" "2017-01-03"

t2 <- seq(from = as.Date("2017-01-01"), 
          to = as.Date("2017-12-31"), 
          by = "months")
t2[1:3]

[1] "2017-01-01" "2017-02-01" "2017-03-01"

df <- data.frame(
        Fruit=c("apple","pear","melon"),
        kg=c(100, 250, 560),
        PrUn=c(2.0, 4.5, 1.2)
      )
df

  Fruit  kg PrUn
1 apple 100  2.0
2  pear 250  4.5
3 melon 560  1.2

Read

• df <- read.table(“file.txt”)
• df <- read.csv(“file.csv”)
• df <- read.csv(file.choose())
• df <- read.excel(file.choose(), sheet = “Sheet1”)

Write

• write.table(df, “file.txt”)
• write.csv(df, “file.csv”)

df['tot'] <- df['kg'] * df['PrUn']
df

  Fruit  kg PrUn  tot
1 apple 100  2.0  200
2  pear 250  4.5 1125
3 melon 560  1.2  672

df$tot <- df$kg * df$PrUn
df

  Fruit  kg PrUn  tot
1 apple 100  2.0  200
2  pear 250  4.5 1125
3 melon 560  1.2  672

df['tot'] <- NULL
df

  Fruit  kg PrUn
1 apple 100  2.0
2  pear 250  4.5
3 melon 560  1.2

df$tot <- NULL
df

  Fruit  kg PrUn
1 apple 100  2.0
2  pear 250  4.5
3 melon 560  1.2

df

  Fruit  kg PrUn
1 apple 100  2.0
2  pear 250  4.5
3 melon 560  1.2

dim(df)

[1] 3 3

names(df)

[1] "Fruit" "kg"    "PrUn" 

df

  Fruit  kg PrUn
1 apple 100  2.0
2  pear 250  4.5
3 melon 560  1.2

str(df)

'data.frame':   3 obs. of  3 variables:
 $ Fruit: Factor w/ 3 levels "apple","melon",..: 1 3 2
 $ kg   : num  100 250 560
 $ PrUn : num  2 4.5 1.2

df1 <- data.frame(a=sample(x=1:100), b=rnorm(100))

head(df1, 2)

   a          b
1 40 -0.9167949
2 70  0.7531830

tail(df1, 2)

     a          b
99  73  0.5667689
100 42 -0.1077406

summary(df1)

       a                b           
 Min.   :  1.00   Min.   :-2.11038  
 1st Qu.: 25.75   1st Qu.:-0.70474  
 Median : 50.50   Median :-0.10633  
 Mean   : 50.50   Mean   :-0.07583  
 3rd Qu.: 75.25   3rd Qu.: 0.53946  
 Max.   :100.00   Max.   : 2.97220  

lr <- lm(formula = a ~ b, data = df1)
lr

Call:
lm(formula = a ~ b, data = df1)

Coefficients:
(Intercept)            b  
     50.750        3.297  

v <- c(22, 3, 2, 5, 6, 77, 8, 11, 9, 7, 57)

sqrt(mean(v^2))

[1] 30.22792

library(magrittr)

v^2 %>% mean() %>% sqrt()

[1] 30.22792

• select() select columns
• filter() filter rows
• summarise() summarise values
• arrange() re-order or arrange rows
• mutate() create new columns
• group_by() group data

library(dplyr)
df_a <- data.frame(year = rep(2013:2017,each=12),
          month = rep(1:12, times=5),
          num = sample(1:20),
          weight = runif(n = 60, min = 1.0,
                    max = 10.0))
head(df_a, 4)

  year month num   weight
1 2013     1  20 6.249453
2 2013     2  18 4.340047
3 2013     3  12 4.000076
4 2013     4  10 7.860788

df_a_select <- select(df_a,
                      year, num, weight)
head(df_a_select)

  year num   weight
1 2013  20 6.249453
2 2013  18 4.340047
3 2013  12 4.000076
4 2013  10 7.860788
5 2013  14 1.957468
6 2013   6 9.132897

df_a_filter <- filter(df_a, 
                      month == 2, num > 3)
head(df_a_filter)

  year month num   weight
1 2013     2  18 4.340047
2 2014     2  15 8.910923
3 2015     2   6 3.393272
4 2016     2  13 8.434680
5 2017     2   9 1.946008

df_a_summarise <- summarise(df_a, 
                        avg_n=mean(num),
                        avg_w=mean(weight))
head(df_a_summarise)

  avg_n    avg_w
1  10.5 5.630199

df_a_arrange <- arrange(df_a, desc(num))
head(df_a_arrange)

  year month num   weight
1 2013     1  20 6.249453
2 2014     9  20 6.409159
3 2016     5  20 9.276693
4 2014     1  19 1.851002
5 2015     9  19 1.687055
6 2017     5  19 9.145018

df_a_mutate <- mutate(df_a, tot=num*weight)
head(df_a_mutate)

  year month num   weight       tot
1 2013     1  20 6.249453 124.98906
2 2013     2  18 4.340047  78.12085
3 2013     3  12 4.000076  48.00091
4 2013     4  10 7.860788  78.60788
5 2013     5  14 1.957468  27.40455
6 2013     6   6 9.132897  54.79738

df_a_gr <- df_a %>% 
           group_by(year) %>%
           summarise(avg_n=mean(num), 
                     avg_w=mean(weight))
head(df_a_gr)

# A tibble: 5 x 3
   year     avg_n    avg_w
  <int>     <dbl>    <dbl>
1  2013 10.083333 4.946174
2  2014 12.416667 5.868181
3  2015  9.916667 4.284383
4  2016 10.333333 6.556034
5  2017  9.750000 6.496225

df_a_gr <- df_a %>% 
           group_by(year) %>%
           summarise_all(funs(mean))
head(df_a_gr)

# A tibble: 5 x 4
   year month       num   weight
  <int> <dbl>     <dbl>    <dbl>
1  2013   6.5 10.083333 4.946174
2  2014   6.5 12.416667 5.868181
3  2015   6.5  9.916667 4.284383
4  2016   6.5 10.333333 6.556034
5  2017   6.5  9.750000 6.496225

start=as.Date("2017-01-01")
df9 <- data.frame(date=seq(from=start,to=start+99,by="days"),
                  descr=sample(x=c("cat","dog","mouse"),100, replace=T),
                  val=sample(x=1:30,size=100,replace=T))
head(df9, 4)

        date descr val
1 2017-01-01 mouse  20
2 2017-01-02 mouse  20
3 2017-01-03 mouse   2
4 2017-01-04 mouse  22

g   <- ggplot(df9, aes(descr, val))

gg  <- ggplot(df9, aes(x=val))

gg2 <- ggplot(df9, aes(x=val, fill=descr))

gg3 <- ggplot(df9, aes(x=descr, y=val, fill=descr))

“Analizzare i dati con R”

Author: Alessandra Santi

E-mail: santi.info@gmail.com

License: CC-BY-SA