setwd("C:/Users/elsem/Desktop/M2 DSBA/R Mustahq/Project")
"https://www.kaggle.com/uciml/breast-cancer-wisconsin-data"
## [1] "https://www.kaggle.com/uciml/breast-cancer-wisconsin-data"
"Attribute Information:
1) ID number
2) Diagnosis (M = malignant, B = benign)
3-32)
Ten real-valued features are computed for each cell nucleus:
a) radius (mean of distances from center to points on the perimeter)
b) texture (standard deviation of gray-scale values)
c) perimeter
d) area
e) smoothness (local variation in radius lengths)
f) compactness (perimeter^2 / area - 1.0)
g) concavity (severity of concave portions of the contour)
h) concave points (number of concave portions of the contour)
i) symmetry
j) fractal dimension (coastline approximation - 1)"
## [1] "Attribute Information:\n\n1) ID number\n2) Diagnosis (M = malignant, B = benign)\n3-32)\n\nTen real-valued features are computed for each cell nucleus:\n\na) radius (mean of distances from center to points on the perimeter)\nb) texture (standard deviation of gray-scale values)\nc) perimeter\nd) area\ne) smoothness (local variation in radius lengths)\nf) compactness (perimeter^2 / area - 1.0)\ng) concavity (severity of concave portions of the contour)\nh) concave points (number of concave portions of the contour)\ni) symmetry\nj) fractal dimension (coastline approximation - 1)"
breast_cancer = read.csv('breast_cancer.csv', sep=",")
str(breast_cancer)
## 'data.frame': 569 obs. of 33 variables:
## $ id : int 842302 842517 84300903 84348301 84358402 843786 844359 84458202 844981 84501001 ...
## $ diagnosis : chr "M" "M" "M" "M" ...
## $ radius_mean : num 18 20.6 19.7 11.4 20.3 ...
## $ texture_mean : num 10.4 17.8 21.2 20.4 14.3 ...
## $ perimeter_mean : num 122.8 132.9 130 77.6 135.1 ...
## $ area_mean : num 1001 1326 1203 386 1297 ...
## $ smoothness_mean : num 0.1184 0.0847 0.1096 0.1425 0.1003 ...
## $ compactness_mean : num 0.2776 0.0786 0.1599 0.2839 0.1328 ...
## $ concavity_mean : num 0.3001 0.0869 0.1974 0.2414 0.198 ...
## $ concave.points_mean : num 0.1471 0.0702 0.1279 0.1052 0.1043 ...
## $ symmetry_mean : num 0.242 0.181 0.207 0.26 0.181 ...
## $ fractal_dimension_mean : num 0.0787 0.0567 0.06 0.0974 0.0588 ...
## $ radius_se : num 1.095 0.543 0.746 0.496 0.757 ...
## $ texture_se : num 0.905 0.734 0.787 1.156 0.781 ...
## $ perimeter_se : num 8.59 3.4 4.58 3.44 5.44 ...
## $ area_se : num 153.4 74.1 94 27.2 94.4 ...
## $ smoothness_se : num 0.0064 0.00522 0.00615 0.00911 0.01149 ...
## $ compactness_se : num 0.049 0.0131 0.0401 0.0746 0.0246 ...
## $ concavity_se : num 0.0537 0.0186 0.0383 0.0566 0.0569 ...
## $ concave.points_se : num 0.0159 0.0134 0.0206 0.0187 0.0188 ...
## $ symmetry_se : num 0.03 0.0139 0.0225 0.0596 0.0176 ...
## $ fractal_dimension_se : num 0.00619 0.00353 0.00457 0.00921 0.00511 ...
## $ radius_worst : num 25.4 25 23.6 14.9 22.5 ...
## $ texture_worst : num 17.3 23.4 25.5 26.5 16.7 ...
## $ perimeter_worst : num 184.6 158.8 152.5 98.9 152.2 ...
## $ area_worst : num 2019 1956 1709 568 1575 ...
## $ smoothness_worst : num 0.162 0.124 0.144 0.21 0.137 ...
## $ compactness_worst : num 0.666 0.187 0.424 0.866 0.205 ...
## $ concavity_worst : num 0.712 0.242 0.45 0.687 0.4 ...
## $ concave.points_worst : num 0.265 0.186 0.243 0.258 0.163 ...
## $ symmetry_worst : num 0.46 0.275 0.361 0.664 0.236 ...
## $ fractal_dimension_worst: num 0.1189 0.089 0.0876 0.173 0.0768 ...
## $ X : logi NA NA NA NA NA NA ...
summary(breast_cancer)
## id diagnosis radius_mean texture_mean
## Min. : 8670 Length:569 Min. : 6.981 Min. : 9.71
## 1st Qu.: 869218 Class :character 1st Qu.:11.700 1st Qu.:16.17
## Median : 906024 Mode :character Median :13.370 Median :18.84
## Mean : 30371831 Mean :14.127 Mean :19.29
## 3rd Qu.: 8813129 3rd Qu.:15.780 3rd Qu.:21.80
## Max. :911320502 Max. :28.110 Max. :39.28
## perimeter_mean area_mean smoothness_mean compactness_mean
## Min. : 43.79 Min. : 143.5 Min. :0.05263 Min. :0.01938
## 1st Qu.: 75.17 1st Qu.: 420.3 1st Qu.:0.08637 1st Qu.:0.06492
## Median : 86.24 Median : 551.1 Median :0.09587 Median :0.09263
## Mean : 91.97 Mean : 654.9 Mean :0.09636 Mean :0.10434
## 3rd Qu.:104.10 3rd Qu.: 782.7 3rd Qu.:0.10530 3rd Qu.:0.13040
## Max. :188.50 Max. :2501.0 Max. :0.16340 Max. :0.34540
## concavity_mean concave.points_mean symmetry_mean fractal_dimension_mean
## Min. :0.00000 Min. :0.00000 Min. :0.1060 Min. :0.04996
## 1st Qu.:0.02956 1st Qu.:0.02031 1st Qu.:0.1619 1st Qu.:0.05770
## Median :0.06154 Median :0.03350 Median :0.1792 Median :0.06154
## Mean :0.08880 Mean :0.04892 Mean :0.1812 Mean :0.06280
## 3rd Qu.:0.13070 3rd Qu.:0.07400 3rd Qu.:0.1957 3rd Qu.:0.06612
## Max. :0.42680 Max. :0.20120 Max. :0.3040 Max. :0.09744
## radius_se texture_se perimeter_se area_se
## Min. :0.1115 Min. :0.3602 Min. : 0.757 Min. : 6.802
## 1st Qu.:0.2324 1st Qu.:0.8339 1st Qu.: 1.606 1st Qu.: 17.850
## Median :0.3242 Median :1.1080 Median : 2.287 Median : 24.530
## Mean :0.4052 Mean :1.2169 Mean : 2.866 Mean : 40.337
## 3rd Qu.:0.4789 3rd Qu.:1.4740 3rd Qu.: 3.357 3rd Qu.: 45.190
## Max. :2.8730 Max. :4.8850 Max. :21.980 Max. :542.200
## smoothness_se compactness_se concavity_se concave.points_se
## Min. :0.001713 Min. :0.002252 Min. :0.00000 Min. :0.000000
## 1st Qu.:0.005169 1st Qu.:0.013080 1st Qu.:0.01509 1st Qu.:0.007638
## Median :0.006380 Median :0.020450 Median :0.02589 Median :0.010930
## Mean :0.007041 Mean :0.025478 Mean :0.03189 Mean :0.011796
## 3rd Qu.:0.008146 3rd Qu.:0.032450 3rd Qu.:0.04205 3rd Qu.:0.014710
## Max. :0.031130 Max. :0.135400 Max. :0.39600 Max. :0.052790
## symmetry_se fractal_dimension_se radius_worst texture_worst
## Min. :0.007882 Min. :0.0008948 Min. : 7.93 Min. :12.02
## 1st Qu.:0.015160 1st Qu.:0.0022480 1st Qu.:13.01 1st Qu.:21.08
## Median :0.018730 Median :0.0031870 Median :14.97 Median :25.41
## Mean :0.020542 Mean :0.0037949 Mean :16.27 Mean :25.68
## 3rd Qu.:0.023480 3rd Qu.:0.0045580 3rd Qu.:18.79 3rd Qu.:29.72
## Max. :0.078950 Max. :0.0298400 Max. :36.04 Max. :49.54
## perimeter_worst area_worst smoothness_worst compactness_worst
## Min. : 50.41 Min. : 185.2 Min. :0.07117 Min. :0.02729
## 1st Qu.: 84.11 1st Qu.: 515.3 1st Qu.:0.11660 1st Qu.:0.14720
## Median : 97.66 Median : 686.5 Median :0.13130 Median :0.21190
## Mean :107.26 Mean : 880.6 Mean :0.13237 Mean :0.25427
## 3rd Qu.:125.40 3rd Qu.:1084.0 3rd Qu.:0.14600 3rd Qu.:0.33910
## Max. :251.20 Max. :4254.0 Max. :0.22260 Max. :1.05800
## concavity_worst concave.points_worst symmetry_worst fractal_dimension_worst
## Min. :0.0000 Min. :0.00000 Min. :0.1565 Min. :0.05504
## 1st Qu.:0.1145 1st Qu.:0.06493 1st Qu.:0.2504 1st Qu.:0.07146
## Median :0.2267 Median :0.09993 Median :0.2822 Median :0.08004
## Mean :0.2722 Mean :0.11461 Mean :0.2901 Mean :0.08395
## 3rd Qu.:0.3829 3rd Qu.:0.16140 3rd Qu.:0.3179 3rd Qu.:0.09208
## Max. :1.2520 Max. :0.29100 Max. :0.6638 Max. :0.20750
## X
## Mode:logical
## NA's:569
##
##
##
##
breast_cancer = breast_cancer%>%select(-id,-X)
breast_cancer %>% apply(2, is.na) %>% apply(2,sum)
## diagnosis radius_mean texture_mean
## 0 0 0
## perimeter_mean area_mean smoothness_mean
## 0 0 0
## compactness_mean concavity_mean concave.points_mean
## 0 0 0
## symmetry_mean fractal_dimension_mean radius_se
## 0 0 0
## texture_se perimeter_se area_se
## 0 0 0
## smoothness_se compactness_se concavity_se
## 0 0 0
## concave.points_se symmetry_se fractal_dimension_se
## 0 0 0
## radius_worst texture_worst perimeter_worst
## 0 0 0
## area_worst smoothness_worst compactness_worst
## 0 0 0
## concavity_worst concave.points_worst symmetry_worst
## 0 0 0
## fractal_dimension_worst
## 0
table(breast_cancer$diagnosis)
##
## B M
## 357 212
#encode = function(x){if (x=="M"){return(1)} else{return(0)}}
#breast_cancer$diagnosis = unlist(lapply(breast_cancer$diagnosis,encode))
#table(breast_cancer$diagnosis)
for (col in colnames(breast_cancer)[-1])
{
boxplot(breast_cancer[,col] ~ breast_cancer$diagnosis, xlab = 'Malignant or Benign', ylab = col, main = paste(col,' x ', 'diagnosis') )
}
intrain = createDataPartition(y = breast_cancer$diagnosis, p = 0.8, list = FALSE)
training <- breast_cancer[intrain, ]
testing <- breast_cancer[-intrain, ]
#Train a logistic regression
model <- train(diagnosis ~ . , data = training, method = 'glm')
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
vip(model)
predictions <- predict(model, testing)
#plot tree
plot(model$finalModel)
## Warning in sqrt(crit * p * (1 - hh)/hh): production de NaN
## Warning in sqrt(crit * p * (1 - hh)/hh): production de NaN
confusionMatrix(factor(predictions), factor(testing$diagnosis))
## Confusion Matrix and Statistics
##
## Reference
## Prediction B M
## B 68 2
## M 3 40
##
## Accuracy : 0.9558
## 95% CI : (0.8998, 0.9855)
## No Information Rate : 0.6283
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.9057
##
## Mcnemar's Test P-Value : 1
##
## Sensitivity : 0.9577
## Specificity : 0.9524
## Pos Pred Value : 0.9714
## Neg Pred Value : 0.9302
## Prevalence : 0.6283
## Detection Rate : 0.6018
## Detection Prevalence : 0.6195
## Balanced Accuracy : 0.9551
##
## 'Positive' Class : B
##
#Train a DT
model <- train(diagnosis ~ . , data = training, method = 'rpart')
vip(model)
predictions <- predict(model, testing)
#plot tree
plot(model$finalModel, uniform=TRUE,
main="Classification Tree")
text(model$finalModel, use.n=TRUE, all=TRUE, cex=.6)
confusionMatrix(factor(predictions), factor(testing$diagnosis))
## Confusion Matrix and Statistics
##
## Reference
## Prediction B M
## B 64 8
## M 7 34
##
## Accuracy : 0.8673
## 95% CI : (0.7905, 0.9238)
## No Information Rate : 0.6283
## P-Value [Acc > NIR] : 1.435e-08
##
## Kappa : 0.7144
##
## Mcnemar's Test P-Value : 1
##
## Sensitivity : 0.9014
## Specificity : 0.8095
## Pos Pred Value : 0.8889
## Neg Pred Value : 0.8293
## Prevalence : 0.6283
## Detection Rate : 0.5664
## Detection Prevalence : 0.6372
## Balanced Accuracy : 0.8555
##
## 'Positive' Class : B
##
#Train a rf
model <- train(diagnosis ~ . , data = training, method = 'rf')
vip(model)
predictions <- predict(model, testing)
#plot tree
plot(model$finalModel)
confusionMatrix(factor(predictions), factor(testing$diagnosis))
## Confusion Matrix and Statistics
##
## Reference
## Prediction B M
## B 70 2
## M 1 40
##
## Accuracy : 0.9735
## 95% CI : (0.9244, 0.9945)
## No Information Rate : 0.6283
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.9429
##
## Mcnemar's Test P-Value : 1
##
## Sensitivity : 0.9859
## Specificity : 0.9524
## Pos Pred Value : 0.9722
## Neg Pred Value : 0.9756
## Prevalence : 0.6283
## Detection Rate : 0.6195
## Detection Prevalence : 0.6372
## Balanced Accuracy : 0.9691
##
## 'Positive' Class : B
##
#$overall["Accuracy"]