lab2.knit

Packages

library(tidymodels)
library(tidyverse)
library(palmerpenguins)
library(rpart)
library(skimr)
library(rpart.plot)

Data

data(penguins)
skim(penguins)

Data summary
Name	penguins
Number of rows	344
Number of columns	8
_______________________
Column type frequency:
factor	3
numeric	5
________________________
Group variables	None

Variable type: factor

skim_variable	n_missing	complete_rate	ordered	n_unique	top_counts
species	0	1.00	FALSE	3	Ade: 152, Gen: 124, Chi: 68
island	0	1.00	FALSE	3	Bis: 168, Dre: 124, Tor: 52
sex	11	0.97	FALSE	2	mal: 168, fem: 165

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
bill_length_mm	2	0.99	43.92	5.46	32.1	39.23	44.45	48.5	59.6	▃▇▇▆▁
bill_depth_mm	2	0.99	17.15	1.97	13.1	15.60	17.30	18.7	21.5	▅▅▇▇▂
flipper_length_mm	2	0.99	200.92	14.06	172.0	190.00	197.00	213.0	231.0	▂▇▃▅▂
body_mass_g	2	0.99	4201.75	801.95	2700.0	3550.00	4050.00	4750.0	6300.0	▃▇▆▃▂
year	0	1.00	2008.03	0.82	2007.0	2007.00	2008.00	2009.0	2009.0	▇▁▇▁▇

Split data

set.seed(123)
penguin_split <- initial_split(penguins)
penguin_train <- training(penguin_split)
dim(penguin_train)

## [1] 258   8

head(penguin_train)

## # A tibble: 6 × 8
##   species island bill_length_mm bill_depth_mm flipper_length_… body_mass_g sex  
##   <fct>   <fct>           <dbl>         <dbl>            <int>       <int> <fct>
## 1 Gentoo  Biscoe           44.5          14.3              216        4100 <NA> 
## 2 Adelie  Torge…           38.6          21.2              191        3800 male 
## 3 Gentoo  Biscoe           45.3          13.7              210        4300 fema…
## 4 Chinst… Dream            52.8          20                205        4550 male 
## 5 Adelie  Torge…           37.3          20.5              199        3775 male 
## 6 Chinst… Dream            43.2          16.6              187        2900 fema…
## # … with 1 more variable: year <int>

penguin_test <- testing(penguin_split)
dim(penguin_test)

## [1] 86  8

Build decision tree

tree1 <- rpart(species ~ ., penguin_train,  cp = 0.1)
rpart.plot(tree1, box.palette="RdBu", shadow.col="gray", nn=TRUE)

tree2 <- rpart(species ~ ., penguin_train,  cp = 0.5)
rpart.plot(tree2, box.palette="RdBu", shadow.col="gray", nn=TRUE)

Predict

predict(tree1, penguin_test)

##        Adelie  Chinstrap     Gentoo
## 1  0.95726496 0.04273504 0.00000000
## 2  0.95726496 0.04273504 0.00000000
## 3  0.95726496 0.04273504 0.00000000
## 4  0.95726496 0.04273504 0.00000000
## 5  0.95726496 0.04273504 0.00000000
## 6  0.95726496 0.04273504 0.00000000
## 7  0.95726496 0.04273504 0.00000000
## 8  0.95726496 0.04273504 0.00000000
## 9  0.95726496 0.04273504 0.00000000
## 10 0.95726496 0.04273504 0.00000000
## 11 0.95726496 0.04273504 0.00000000
## 12 0.95726496 0.04273504 0.00000000
## 13 0.95726496 0.04273504 0.00000000
## 14 0.95726496 0.04273504 0.00000000
## 15 0.95726496 0.04273504 0.00000000
## 16 0.95726496 0.04273504 0.00000000
## 17 0.95726496 0.04273504 0.00000000
## 18 0.95726496 0.04273504 0.00000000
## 19 0.95726496 0.04273504 0.00000000
## 20 0.95726496 0.04273504 0.00000000
## 21 0.95726496 0.04273504 0.00000000
## 22 0.04545455 0.93181818 0.02272727
## 23 0.95726496 0.04273504 0.00000000
## 24 0.95726496 0.04273504 0.00000000
## 25 0.95726496 0.04273504 0.00000000
## 26 0.95726496 0.04273504 0.00000000
## 27 0.95726496 0.04273504 0.00000000
## 28 0.95726496 0.04273504 0.00000000
## 29 0.01030928 0.04123711 0.94845361
## 30 0.95726496 0.04273504 0.00000000
## 31 0.95726496 0.04273504 0.00000000
## 32 0.95726496 0.04273504 0.00000000
## 33 0.95726496 0.04273504 0.00000000
## 34 0.95726496 0.04273504 0.00000000
## 35 0.95726496 0.04273504 0.00000000
## 36 0.95726496 0.04273504 0.00000000
## 37 0.95726496 0.04273504 0.00000000
## 38 0.01030928 0.04123711 0.94845361
## 39 0.01030928 0.04123711 0.94845361
## 40 0.01030928 0.04123711 0.94845361
## 41 0.01030928 0.04123711 0.94845361
## 42 0.01030928 0.04123711 0.94845361
## 43 0.01030928 0.04123711 0.94845361
## 44 0.01030928 0.04123711 0.94845361
## 45 0.01030928 0.04123711 0.94845361
## 46 0.01030928 0.04123711 0.94845361
## 47 0.01030928 0.04123711 0.94845361
## 48 0.01030928 0.04123711 0.94845361
## 49 0.01030928 0.04123711 0.94845361
## 50 0.01030928 0.04123711 0.94845361
## 51 0.01030928 0.04123711 0.94845361
## 52 0.01030928 0.04123711 0.94845361
## 53 0.01030928 0.04123711 0.94845361
## 54 0.01030928 0.04123711 0.94845361
## 55 0.01030928 0.04123711 0.94845361
## 56 0.01030928 0.04123711 0.94845361
## 57 0.01030928 0.04123711 0.94845361
## 58 0.01030928 0.04123711 0.94845361
## 59 0.01030928 0.04123711 0.94845361
## 60 0.01030928 0.04123711 0.94845361
## 61 0.01030928 0.04123711 0.94845361
## 62 0.01030928 0.04123711 0.94845361
## 63 0.01030928 0.04123711 0.94845361
## 64 0.01030928 0.04123711 0.94845361
## 65 0.01030928 0.04123711 0.94845361
## 66 0.01030928 0.04123711 0.94845361
## 67 0.01030928 0.04123711 0.94845361
## 68 0.01030928 0.04123711 0.94845361
## 69 0.04545455 0.93181818 0.02272727
## 70 0.04545455 0.93181818 0.02272727
## 71 0.04545455 0.93181818 0.02272727
## 72 0.04545455 0.93181818 0.02272727
## 73 0.04545455 0.93181818 0.02272727
## 74 0.04545455 0.93181818 0.02272727
## 75 0.04545455 0.93181818 0.02272727
## 76 0.04545455 0.93181818 0.02272727
## 77 0.04545455 0.93181818 0.02272727
## 78 0.04545455 0.93181818 0.02272727
## 79 0.04545455 0.93181818 0.02272727
## 80 0.04545455 0.93181818 0.02272727
## 81 0.04545455 0.93181818 0.02272727
## 82 0.04545455 0.93181818 0.02272727
## 83 0.04545455 0.93181818 0.02272727
## 84 0.01030928 0.04123711 0.94845361
## 85 0.95726496 0.04273504 0.00000000
## 86 0.04545455 0.93181818 0.02272727

t_pred <- predict(tree1, penguin_test, type = "class")
t_pred

##         1         2         3         4         5         6         7         8 
##    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie 
##         9        10        11        12        13        14        15        16 
##    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie    Adelie 
##        17        18        19        20        21        22        23        24 
##    Adelie    Adelie    Adelie    Adelie    Adelie Chinstrap    Adelie    Adelie 
##        25        26        27        28        29        30        31        32 
##    Adelie    Adelie    Adelie    Adelie    Gentoo    Adelie    Adelie    Adelie 
##        33        34        35        36        37        38        39        40 
##    Adelie    Adelie    Adelie    Adelie    Adelie    Gentoo    Gentoo    Gentoo 
##        41        42        43        44        45        46        47        48 
##    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo 
##        49        50        51        52        53        54        55        56 
##    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo 
##        57        58        59        60        61        62        63        64 
##    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo    Gentoo 
##        65        66        67        68        69        70        71        72 
##    Gentoo    Gentoo    Gentoo    Gentoo Chinstrap Chinstrap Chinstrap Chinstrap 
##        73        74        75        76        77        78        79        80 
## Chinstrap Chinstrap Chinstrap Chinstrap Chinstrap Chinstrap Chinstrap Chinstrap 
##        81        82        83        84        85        86 
## Chinstrap Chinstrap Chinstrap    Gentoo    Adelie Chinstrap 
## Levels: Adelie Chinstrap Gentoo

Accuracy

confMat <- table(penguin_test$species,t_pred)
confMat

##            t_pred
##             Adelie Chinstrap Gentoo
##   Adelie        35         1      1
##   Chinstrap      1        16      1
##   Gentoo         0         0     31