-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathLogistic Regression.R
107 lines (68 loc) · 3.37 KB
/
Logistic Regression.R
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
95
96
97
98
99
100
101
102
103
104
105
106
107
# To create a Logistic Regression, Sigmoid Function is need.
# Sigmoid Functin,
# p = 1 / ( 1 + e^-y)
# Formula of Logistic Regression,
# ln ( p / (1 - p) ) = b0 + b1 * x
# ---------------------------------------------------- Importing Data ----------------------------------------- #
dataset = read.csv("Social_Network_Ad.csv")
# Selecting particular columns
dataset = dataset[, 3:5]
# ---------------------------------- Splitting the dataset into Training and Test Set ------------------------- #
library(caTools)
set.seed(123)
split = sample.split(dataset$Purchased, SplitRatio = 0.75)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)
# --------------------------------------------------- Feature Scalling ----------------------------------------- #
training_set[, 1:2] = scale(training_set[, 1:2])
test_set[, 1:2] = scale((test_set[, 1:2]))
# ---------------------------------- Fitting Logistic Regression to the Training Set --------------------------- #
classifier = glm(Purchased ~ ., family = binomial, data = training_set)
summary(classifier)
# -------------------------------------------- Predicting the Test Set result ---------------------------------- #
prob_pred = predict(classifier, type = "response", newdata = test_set[-3])
prob_pred
# Making Vector probability prediction
y_pred = ifelse(prob_pred > 0.5, 1, 0)
y_pred
# ------------------------------------------------- Confusion Matrix ------------------------------------------- #
cm = table(test_set[, 3], y_pred)
cm
# --------------------------------------- Visualising the Training Set results --------------------------------- #
# Download from the site, it will be in zip from and then install.
library(ElemStatLearn)
set = training_set
train1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
train2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(train1, train2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
# Plotting
plot(set[, -3],
main = 'Logistic Regression (Training set)',
xlab = 'Age', ylab = 'Estimated Salary',
xlim = range(train1), ylim = range(train2))
# Regression Line
contour(train1, train2, matrix(as.numeric(y_grid), length(train1), length(train2)), add = TRUE)
# Giving Colors
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))
# ------------------------------------------- Visualising the Test Set results --------------------------------- #
set = test_set
test1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
test2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(test1, test2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
# Plotting
plot(set[, -3],
main = 'Logistic Regression (Test set)',
xlab = 'Age', ylab = 'Estimated Salary',
xlim = range(test1), ylim = range(test2))
# Regression Line
contour(test1, test2, matrix(as.numeric(y_grid), length(test1), length(test2)), add = TRUE)
# Giving Colour
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))