Kaggle-Based-Projects/Breast Cancer Classification .Rmd at master · g12bftd/Kaggle-Based-Projects · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
---
title: "Breast Cancer Classification"
output: pdf_document
author: Glenn Bucagu
---


```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(root.dir = "~/Desktop/Projects/6 Practical ML Projects")
```


```{r importing dataset}
dataset <- read.csv("BreastCancer.csv")
dataset
```

```{r visualizing variable relationships}
# We visualize a few variables to get an idea of what to expect

group <- c(NA, NA)
group[dataset$target == 1] <- 2
group[dataset$target == 0] <- 1

pairplot_indices <- c(1, 2, 4, 5)

pairs(x = dataset[, pairplot_indices], col = c("red", "green")[group],
      pch = c(8, 18)[group], main = "Breast Cancer Dataset Pair Plots")

# install.packages("corrplot")
library(corrplot)
corr_mat <- cor(dataset)
corrplot(corr_mat, method="color", type = "lower", tl.col="black", tl.srt = 45,
         tl.cex = 0.5)

```


```{r splitting the dataset into training and testing set}
library(caTools)
split = sample.split(dataset$target, SplitRatio = 0.75)
training_set = subset(dataset, split == TRUE)
testing_set = subset(dataset, split == FALSE)

training_set
testing_set

```

```{r feature scaling}
training_set[-31] = scale(training_set[-31])
testing_set[-31] = scale(testing_set[-31])

training_set
testing_set

```


```{r building the SVM models}
library(e1071)
svm_linear = svm(formula = target ~.,
                 data = training_set,
                 type = 'C-classification',
                 kernel = 'linear')
svm_radial = svm(formula = target ~.,
                 data = training_set,
                 type = 'C-classification',
                 kernel = 'radial')

```


```{r predicting values from testing set}
y_pred_linear <- predict(svm_linear, testing_set)
y_pred_radial <- predict(svm_radial, testing_set)

```


```{r confusion_matrices}
#install.packages("RColorBrewer")
#install.packages("gplots")
library(gplots)
library(RColorBrewer)
color_palette <- colorRampPalette(c("red", "green"))
cm_linear <- table(testing_set[, 31], y_pred_linear)
cm_radial <- table(testing_set[, 31], y_pred_radial)

cm_linear
cm_radial

```