cancer de mama
Robie
2026-02-18
library(readr)
# install.packages("rpart")
library(rpart)
# install.packages("rpart.plot")
library(rpart.plot)## Warning: package 'rpart.plot' was built under R version 4.4.3data <- read_csv("C:/Users/robie/Downloads/cancer_de_mama.csv")## Rows: 569 Columns: 31
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): diagnosis
## dbl (30): radius_mean, texture_mean, perimeter_mean, area_mean, smoothness_m...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.# install.packages("rpart")
library(rpart)
# install.packages("rpart.plot")
library(rpart.plot)Entender la base de datos
summary(data)## 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. :0.20750str(data)## spc_tbl_ [569 × 31] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ diagnosis : chr [1:569] "M" "M" "M" "M" ...
## $ radius_mean : num [1:569] 18 20.6 19.7 11.4 20.3 ...
## $ texture_mean : num [1:569] 10.4 17.8 21.2 20.4 14.3 ...
## $ perimeter_mean : num [1:569] 122.8 132.9 130 77.6 135.1 ...
## $ area_mean : num [1:569] 1001 1326 1203 386 1297 ...
## $ smoothness_mean : num [1:569] 0.1184 0.0847 0.1096 0.1425 0.1003 ...
## $ compactness_mean : num [1:569] 0.2776 0.0786 0.1599 0.2839 0.1328 ...
## $ concavity_mean : num [1:569] 0.3001 0.0869 0.1974 0.2414 0.198 ...
## $ concave points_mean : num [1:569] 0.1471 0.0702 0.1279 0.1052 0.1043 ...
## $ symmetry_mean : num [1:569] 0.242 0.181 0.207 0.26 0.181 ...
## $ fractal_dimension_mean : num [1:569] 0.0787 0.0567 0.06 0.0974 0.0588 ...
## $ radius_se : num [1:569] 1.095 0.543 0.746 0.496 0.757 ...
## $ texture_se : num [1:569] 0.905 0.734 0.787 1.156 0.781 ...
## $ perimeter_se : num [1:569] 8.59 3.4 4.58 3.44 5.44 ...
## $ area_se : num [1:569] 153.4 74.1 94 27.2 94.4 ...
## $ smoothness_se : num [1:569] 0.0064 0.00522 0.00615 0.00911 0.01149 ...
## $ compactness_se : num [1:569] 0.049 0.0131 0.0401 0.0746 0.0246 ...
## $ concavity_se : num [1:569] 0.0537 0.0186 0.0383 0.0566 0.0569 ...
## $ concave points_se : num [1:569] 0.0159 0.0134 0.0206 0.0187 0.0188 ...
## $ symmetry_se : num [1:569] 0.03 0.0139 0.0225 0.0596 0.0176 ...
## $ fractal_dimension_se : num [1:569] 0.00619 0.00353 0.00457 0.00921 0.00511 ...
## $ radius_worst : num [1:569] 25.4 25 23.6 14.9 22.5 ...
## $ texture_worst : num [1:569] 17.3 23.4 25.5 26.5 16.7 ...
## $ perimeter_worst : num [1:569] 184.6 158.8 152.5 98.9 152.2 ...
## $ area_worst : num [1:569] 2019 1956 1709 568 1575 ...
## $ smoothness_worst : num [1:569] 0.162 0.124 0.144 0.21 0.137 ...
## $ compactness_worst : num [1:569] 0.666 0.187 0.424 0.866 0.205 ...
## $ concavity_worst : num [1:569] 0.712 0.242 0.45 0.687 0.4 ...
## $ concave points_worst : num [1:569] 0.265 0.186 0.243 0.258 0.163 ...
## $ symmetry_worst : num [1:569] 0.46 0.275 0.361 0.664 0.236 ...
## $ fractal_dimension_worst: num [1:569] 0.1189 0.089 0.0876 0.173 0.0768 ...
## - attr(*, "spec")=
## .. cols(
## .. diagnosis = col_character(),
## .. radius_mean = col_double(),
## .. texture_mean = col_double(),
## .. perimeter_mean = col_double(),
## .. area_mean = col_double(),
## .. smoothness_mean = col_double(),
## .. compactness_mean = col_double(),
## .. concavity_mean = col_double(),
## .. `concave points_mean` = col_double(),
## .. symmetry_mean = col_double(),
## .. fractal_dimension_mean = col_double(),
## .. radius_se = col_double(),
## .. texture_se = col_double(),
## .. perimeter_se = col_double(),
## .. area_se = col_double(),
## .. smoothness_se = col_double(),
## .. compactness_se = col_double(),
## .. concavity_se = col_double(),
## .. `concave points_se` = col_double(),
## .. symmetry_se = col_double(),
## .. fractal_dimension_se = col_double(),
## .. radius_worst = col_double(),
## .. texture_worst = col_double(),
## .. perimeter_worst = col_double(),
## .. area_worst = col_double(),
## .. smoothness_worst = col_double(),
## .. compactness_worst = col_double(),
## .. concavity_worst = col_double(),
## .. `concave points_worst` = col_double(),
## .. symmetry_worst = col_double(),
## .. fractal_dimension_worst = col_double()
## .. )
## - attr(*, "problems")=<externalptr>head(data)## # A tibble: 6 × 31
## diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 M 18.0 10.4 123. 1001 0.118
## 2 M 20.6 17.8 133. 1326 0.0847
## 3 M 19.7 21.2 130 1203 0.110
## 4 M 11.4 20.4 77.6 386. 0.142
## 5 M 20.3 14.3 135. 1297 0.100
## 6 M 12.4 15.7 82.6 477. 0.128
## # ℹ 25 more variables: compactness_mean <dbl>, concavity_mean <dbl>,
## # `concave points_mean` <dbl>, symmetry_mean <dbl>,
## # fractal_dimension_mean <dbl>, radius_se <dbl>, texture_se <dbl>,
## # perimeter_se <dbl>, area_se <dbl>, smoothness_se <dbl>,
## # compactness_se <dbl>, concavity_se <dbl>, `concave points_se` <dbl>,
## # symmetry_se <dbl>, fractal_dimension_se <dbl>, radius_worst <dbl>,
## # texture_worst <dbl>, perimeter_worst <dbl>, area_worst <dbl>, …Crear árbol de decisión
# convertir variable objetivo a factor
data$diagnosis <- as.factor(data$diagnosis)
# árbol usando TODAS las columnas
arbol <- rpart(diagnosis ~ ., data=data)
rpart.plot(arbol)
prp(arbol, extra=7, prefix="Probabilidad\n")
Conclusiones
El árbol de decisión indica que variables como el radio medio, el perímetro y el área del tumor son las más relevantes para distinguir entre los distintos diagnósticos. A partir de estas características, el modelo divide la información en distintos conjuntos hasta determinar si el tumor corresponde a un caso benigno o maligno.
Este enfoque permite identificar con mayor claridad qué atributos influyen más en la clasificación y ayuda a reconocer patrones presentes en los pacientes. En términos generales, el modelo funciona como una herramienta de apoyo que facilita el análisis y permite obtener una clasificación de manera rápida y sencilla.
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