Statystyki opisowe

Wybieranie danych

data("airquality")
data("CO2")
DT::datatable(airquality, filter ='top', options = list(scrollX=TRUE))

DT::datatable(CO2, filter ='top', options = list(scrollX=TRUE))

Podstawowe statystyki

str(CO2)

## Classes 'nfnGroupedData', 'nfGroupedData', 'groupedData' and 'data.frame':   84 obs. of  5 variables:
##  $ Plant    : Ord.factor w/ 12 levels "Qn1"<"Qn2"<"Qn3"<..: 1 1 1 1 1 1 1 2 2 2 ...
##  $ Type     : Factor w/ 2 levels "Quebec","Mississippi": 1 1 1 1 1 1 1 1 1 1 ...
##  $ Treatment: Factor w/ 2 levels "nonchilled","chilled": 1 1 1 1 1 1 1 1 1 1 ...
##  $ conc     : num  95 175 250 350 500 675 1000 95 175 250 ...
##  $ uptake   : num  16 30.4 34.8 37.2 35.3 39.2 39.7 13.6 27.3 37.1 ...
##  - attr(*, "formula")=Class 'formula'  language uptake ~ conc | Plant
##   .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##  - attr(*, "outer")=Class 'formula'  language ~Treatment * Type
##   .. ..- attr(*, ".Environment")=<environment: R_EmptyEnv> 
##  - attr(*, "labels")=List of 2
##   ..$ x: chr "Ambient carbon dioxide concentration"
##   ..$ y: chr "CO2 uptake rate"
##  - attr(*, "units")=List of 2
##   ..$ x: chr "(uL/L)"
##   ..$ y: chr "(umol/m^2 s)"

summary(CO2)

##      Plant             Type         Treatment       conc          uptake     
##  Qn1    : 7   Quebec     :42   nonchilled:42   Min.   :  95   Min.   : 7.70  
##  Qn2    : 7   Mississippi:42   chilled   :42   1st Qu.: 175   1st Qu.:17.90  
##  Qn3    : 7                                    Median : 350   Median :28.30  
##  Qc1    : 7                                    Mean   : 435   Mean   :27.21  
##  Qc3    : 7                                    3rd Qu.: 675   3rd Qu.:37.12  
##  Qc2    : 7                                    Max.   :1000   Max.   :45.50  
##  (Other):42

names(CO2)

## [1] "Plant"     "Type"      "Treatment" "conc"      "uptake"

unique(CO2$Plant)

##  [1] Qn1 Qn2 Qn3 Qc1 Qc2 Qc3 Mn1 Mn2 Mn3 Mc1 Mc2 Mc3
## 12 Levels: Qn1 < Qn2 < Qn3 < Qc1 < Qc3 < Qc2 < Mn3 < Mn2 < Mn1 < ... < Mc1

unique(CO2$Type)

## [1] Quebec      Mississippi
## Levels: Quebec Mississippi

unique(CO2$Treatment)

## [1] nonchilled chilled   
## Levels: nonchilled chilled

length(CO2)

## [1] 5

nazwa <- names(CO2)

Wykresy poszczegónych kolumn

Airquality

# Wykresy poszczególnych kolumn(pomijamy miesiące i dni)
airquality_1 <- airquality[,-6]
airquality_1 <- airquality_1[,-5]

par(mfrow=c(3,2))
for (i in 1:length(airquality_1)) {
  
  plot(airquality_1[,i],ylab=nazwa[i])
}

par(mfrow=c(1,1))

CO2

par(mfrow=c(3,2))
for (i in 1:length(CO2)) {
  
  plot(CO2[,i],ylab=nazwa[i])
}

par(mfrow=c(1,1))

CO2_mean <- subset(CO2,select=4:5)

sapply(CO2_mean, mean, na.rm=TRUE)

##     conc   uptake 
## 435.0000  27.2131

library(Hmisc)
describe(airquality)

## airquality 
## 
##  6  Variables      153  Observations
## --------------------------------------------------------------------------------
## Ozone 
##        n  missing distinct     Info     Mean      Gmd      .05      .10 
##      116       37       67    0.999    42.13    35.28     7.75    11.00 
##      .25      .50      .75      .90      .95 
##    18.00    31.50    63.25    87.00   108.50 
## 
## lowest :   1   4   6   7   8, highest: 115 118 122 135 168
## --------------------------------------------------------------------------------
## Solar.R 
##        n  missing distinct     Info     Mean      Gmd      .05      .10 
##      146        7      117        1    185.9    102.7    24.25    47.50 
##      .25      .50      .75      .90      .95 
##   115.75   205.00   258.75   288.50   311.50 
## 
## lowest :   7   8  13  14  19, highest: 320 322 323 332 334
## --------------------------------------------------------------------------------
## Wind 
##        n  missing distinct     Info     Mean      Gmd      .05      .10 
##      153        0       31    0.997    9.958    3.964     4.60     5.82 
##      .25      .50      .75      .90      .95 
##     7.40     9.70    11.50    14.90    15.50 
## 
## lowest :  1.7  2.3  2.8  3.4  4.0, highest: 16.1 16.6 18.4 20.1 20.7
## --------------------------------------------------------------------------------
## Temp 
##        n  missing distinct     Info     Mean      Gmd      .05      .10 
##      153        0       40    0.999    77.88    10.74     60.2     64.2 
##      .25      .50      .75      .90      .95 
##     72.0     79.0     85.0     90.0     92.0 
## 
## lowest : 56 57 58 59 61, highest: 92 93 94 96 97
## --------------------------------------------------------------------------------
## Month 
##        n  missing distinct     Info     Mean      Gmd 
##      153        0        5     0.96    6.993    1.608 
## 
## lowest : 5 6 7 8 9, highest: 5 6 7 8 9
##                                         
## Value          5     6     7     8     9
## Frequency     31    30    31    31    30
## Proportion 0.203 0.196 0.203 0.203 0.196
## --------------------------------------------------------------------------------
## Day 
##        n  missing distinct     Info     Mean      Gmd      .05      .10 
##      153        0       31    0.999     15.8    10.26      2.0      4.0 
##      .25      .50      .75      .90      .95 
##      8.0     16.0     23.0     28.0     29.4 
## 
## lowest :  1  2  3  4  5, highest: 27 28 29 30 31
## --------------------------------------------------------------------------------

library(pastecs)
stat.desc(airquality)

##                     Ozone      Solar.R         Wind         Temp        Month
## nbr.val       116.0000000 1.460000e+02  153.0000000 1.530000e+02  153.0000000
## nbr.null        0.0000000 0.000000e+00    0.0000000 0.000000e+00    0.0000000
## nbr.na         37.0000000 7.000000e+00    0.0000000 0.000000e+00    0.0000000
## min             1.0000000 7.000000e+00    1.7000000 5.600000e+01    5.0000000
## max           168.0000000 3.340000e+02   20.7000000 9.700000e+01    9.0000000
## range         167.0000000 3.270000e+02   19.0000000 4.100000e+01    4.0000000
## sum          4887.0000000 2.714600e+04 1523.5000000 1.191600e+04 1070.0000000
## median         31.5000000 2.050000e+02    9.7000000 7.900000e+01    7.0000000
## mean           42.1293103 1.859315e+02    9.9575163 7.788235e+01    6.9934641
## SE.mean         3.0628482 7.453288e+00    0.2848178 7.652217e-01    0.1145191
## CI.mean.0.95    6.0669128 1.473112e+01    0.5627128 1.511844e+00    0.2262546
## var          1088.2005247 8.110519e+03   12.4115385 8.959133e+01    2.0065359
## std.dev        32.9878845 9.005842e+01    3.5230014 9.465270e+00    1.4165225
## coef.var        0.7830151 4.843634e-01    0.3538032 1.215329e-01    0.2025495
##                       Day
## nbr.val       153.0000000
## nbr.null        0.0000000
## nbr.na          0.0000000
## min             1.0000000
## max            31.0000000
## range          30.0000000
## sum          2418.0000000
## median         16.0000000
## mean           15.8039216
## SE.mean         0.7166540
## CI.mean.0.95    1.4158889
## var            78.5797214
## std.dev         8.8645204
## coef.var        0.5609064

Histogramy i Barrploty

# Histogramy
hist(airquality$Temp, col = "green")

hist(airquality$Solar.R, col = "yellow")

# Histogram z ustalonymi przerwami
hist(airquality$Temp,breaks = seq(50,100,0.5),col ="purple",main = "Wartości temperatury z pakietu 'airquality'")

b <- density(airquality$Temp)
plot(b)

# Barrploty
barplot(CO2$conc, col = "red", main = "Dane z kolumny 'conc'")

barplot(CO2$uptake,col = "lightblue",main = "Dane z kolumny 'uptake'")

ggpubr

ggboxplot

library(ggpubr)
ggboxplot(CO2, y = "uptake", width = 0.5)

ggboxplot(CO2, y = "uptake",x="Plant",color="Plant", width = 0.5)

gghistogram

gghistogram(CO2, x = "uptake", bins = 10,add = "mean")

gghistogram(CO2, x = "uptake", add ="mean",fill = "lightgreen",rug=T)

ggdensity

ggdensity(CO2, x = "uptake",
   add = "mean", rug = TRUE,
   color = "Type", fill = "Type",
   palette = c("#00AFBB", "#E7B800"))

ggdotchar

Wykres skumulowany i QQplot

# Wykres skumulowany
ggecdf(CO2, x = "uptake", color = "darkred")

# QQ plots
ggqqplot(CO2, x = "uptake", color = "green")