Importar base de datos

base_de_datos <- read.csv("/Users/georginamartinez/Documents/Tec/Séptimo Semestre/Analítica para negocios, de los datos a decisiones/cancer_de_mama.csv")

Entender la base de datos

summary(base_de_datos)
##   diagnosis          radius_mean      texture_mean   perimeter_mean  
##  Length:569         Min.   : 6.981   Min.   : 9.71   Min.   : 43.79  
##  Class :character   1st Qu.:11.700   1st Qu.:16.17   1st Qu.: 75.17  
##  Mode  :character   Median :13.370   Median :18.84   Median : 86.24  
##                     Mean   :14.127   Mean   :19.29   Mean   : 91.97  
##                     3rd Qu.:15.780   3rd Qu.:21.80   3rd Qu.:104.10  
##                     Max.   :28.110   Max.   :39.28   Max.   :188.50  
##    area_mean      smoothness_mean   compactness_mean  concavity_mean   
##  Min.   : 143.5   Min.   :0.05263   Min.   :0.01938   Min.   :0.00000  
##  1st Qu.: 420.3   1st Qu.:0.08637   1st Qu.:0.06492   1st Qu.:0.02956  
##  Median : 551.1   Median :0.09587   Median :0.09263   Median :0.06154  
##  Mean   : 654.9   Mean   :0.09636   Mean   :0.10434   Mean   :0.08880  
##  3rd Qu.: 782.7   3rd Qu.:0.10530   3rd Qu.:0.13040   3rd Qu.:0.13070  
##  Max.   :2501.0   Max.   :0.16340   Max.   :0.34540   Max.   :0.42680  
##  concave.points_mean symmetry_mean    fractal_dimension_mean   radius_se     
##  Min.   :0.00000     Min.   :0.1060   Min.   :0.04996        Min.   :0.1115  
##  1st Qu.:0.02031     1st Qu.:0.1619   1st Qu.:0.05770        1st Qu.:0.2324  
##  Median :0.03350     Median :0.1792   Median :0.06154        Median :0.3242  
##  Mean   :0.04892     Mean   :0.1812   Mean   :0.06280        Mean   :0.4052  
##  3rd Qu.:0.07400     3rd Qu.:0.1957   3rd Qu.:0.06612        3rd Qu.:0.4789  
##  Max.   :0.20120     Max.   :0.3040   Max.   :0.09744        Max.   :2.8730  
##    texture_se      perimeter_se       area_se        smoothness_se     
##  Min.   :0.3602   Min.   : 0.757   Min.   :  6.802   Min.   :0.001713  
##  1st Qu.:0.8339   1st Qu.: 1.606   1st Qu.: 17.850   1st Qu.:0.005169  
##  Median :1.1080   Median : 2.287   Median : 24.530   Median :0.006380  
##  Mean   :1.2169   Mean   : 2.866   Mean   : 40.337   Mean   :0.007041  
##  3rd Qu.:1.4740   3rd Qu.: 3.357   3rd Qu.: 45.190   3rd Qu.:0.008146  
##  Max.   :4.8850   Max.   :21.980   Max.   :542.200   Max.   :0.031130  
##  compactness_se      concavity_se     concave.points_se   symmetry_se      
##  Min.   :0.002252   Min.   :0.00000   Min.   :0.000000   Min.   :0.007882  
##  1st Qu.:0.013080   1st Qu.:0.01509   1st Qu.:0.007638   1st Qu.:0.015160  
##  Median :0.020450   Median :0.02589   Median :0.010930   Median :0.018730  
##  Mean   :0.025478   Mean   :0.03189   Mean   :0.011796   Mean   :0.020542  
##  3rd Qu.:0.032450   3rd Qu.:0.04205   3rd Qu.:0.014710   3rd Qu.:0.023480  
##  Max.   :0.135400   Max.   :0.39600   Max.   :0.052790   Max.   :0.078950  
##  fractal_dimension_se  radius_worst   texture_worst   perimeter_worst 
##  Min.   :0.0008948    Min.   : 7.93   Min.   :12.02   Min.   : 50.41  
##  1st Qu.:0.0022480    1st Qu.:13.01   1st Qu.:21.08   1st Qu.: 84.11  
##  Median :0.0031870    Median :14.97   Median :25.41   Median : 97.66  
##  Mean   :0.0037949    Mean   :16.27   Mean   :25.68   Mean   :107.26  
##  3rd Qu.:0.0045580    3rd Qu.:18.79   3rd Qu.:29.72   3rd Qu.:125.40  
##  Max.   :0.0298400    Max.   :36.04   Max.   :49.54   Max.   :251.20  
##    area_worst     smoothness_worst  compactness_worst concavity_worst 
##  Min.   : 185.2   Min.   :0.07117   Min.   :0.02729   Min.   :0.0000  
##  1st Qu.: 515.3   1st Qu.:0.11660   1st Qu.:0.14720   1st Qu.:0.1145  
##  Median : 686.5   Median :0.13130   Median :0.21190   Median :0.2267  
##  Mean   : 880.6   Mean   :0.13237   Mean   :0.25427   Mean   :0.2722  
##  3rd Qu.:1084.0   3rd Qu.:0.14600   3rd Qu.:0.33910   3rd Qu.:0.3829  
##  Max.   :4254.0   Max.   :0.22260   Max.   :1.05800   Max.   :1.2520  
##  concave.points_worst symmetry_worst   fractal_dimension_worst
##  Min.   :0.00000      Min.   :0.1565   Min.   :0.05504        
##  1st Qu.:0.06493      1st Qu.:0.2504   1st Qu.:0.07146        
##  Median :0.09993      Median :0.2822   Median :0.08004        
##  Mean   :0.11461      Mean   :0.2901   Mean   :0.08395        
##  3rd Qu.:0.16140      3rd Qu.:0.3179   3rd Qu.:0.09208        
##  Max.   :0.29100      Max.   :0.6638   Max.   :0.20750

Crear arbol de decisión

library(rpart.plot)
## Loading required package: rpart
arbol <- rpart(formula = diagnosis ~., data = base_de_datos)
arbol
## n= 569 
## 
## node), split, n, loss, yval, (yprob)
##       * denotes terminal node
## 
##  1) root 569 212 B (0.62741652 0.37258348)  
##    2) radius_worst< 16.795 379  33 B (0.91292876 0.08707124)  
##      4) concave.points_worst< 0.1358 333   5 B (0.98498498 0.01501502) *
##      5) concave.points_worst>=0.1358 46  18 M (0.39130435 0.60869565)  
##       10) texture_worst< 25.67 19   4 B (0.78947368 0.21052632) *
##       11) texture_worst>=25.67 27   3 M (0.11111111 0.88888889) *
##    3) radius_worst>=16.795 190  11 M (0.05789474 0.94210526) *
rpart.plot(arbol)

prp(arbol, extra=7, prefix="fracción\n")

# install.packages("ggplot")
library("ggplot2")

library("tidyverse")
## ── Attaching packages
## ───────────────────────────────────────
## tidyverse 1.3.2 ──
## ✔ tibble  3.1.8     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.1
## ✔ readr   2.1.2     ✔ forcats 0.5.2
## ✔ purrr   0.3.4     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
ggplot(data=base_de_datos, mapping = aes(radius_worst, concave.points_worst)) + geom_point(aes(color = diagnosis)) + theme_bw()

Conclusiones

En este análisis pudimos realizar un árbol de decisión que nos permitiera conocer si el cáncer es benigno o maligno y como resultado podemos ver que solo con iniciar a hacer el estudio para detectarlo ya se tiene una probabilidad de 37% y después se analiza si el radio es mayor a 17, se tiene un 94% de que sea maligno si es menor es un 9% que sea benigno, además de eso tenemos los puntos concavos si son mayor a 0.14 es un 61% maligno por lo contrario si es menor a 0.14 es un 2% que sea benigno, ahora por último es la textura es mayor a 26 es un 89% maligno y si es menor un 21% benigno.

Después tenemos la gráfica que nos muestra que entre menor sea el radio y menor los puntos concavos el diagnóstico sera Benigno y entre mayor sea el radio y mayor los puntos concavos el diagnóstico sera Maligno.

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