逻辑回归实现-R

英语学习：
binomial：二项式
程序步骤：
数据预处理（导入数据，选取所需数据，划分测试集和训练集），拟合模型，预测测试集，分析混淆矩阵，可视化分类器和训练集，可视化分类器和测试集。
逻辑回归的本质是得到线性回归模型，然后分类，这一点在R的编程中是体现了的，按照0.5划分，但在Python中是自动划分的
程序：

# Logistic Regression

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
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 Scaling
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(formula = Purchased ~ .,
                 family= binomial,
                 data= training_set)

# Predicting the Test set results
prob_pred=predict(classifier, type = 'response', newdata=test_set[-3])
y_pred=ifelse(prob_pred>0.5, 1, 0)

# Making the Confusion Matrix
cm = table(test_set[,3], y_pred)

# Visualising the Training set results
# install.packages(ElemStatLearn)
library(ElemStatLearn)
set = training_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.0075)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.0075)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
plot(set[, -3],
     main = 'Classifier (Training set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
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
#install.packages()
library(ElemStatLearn)
set = test_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
prob_set = predict(classifier, type = 'response', newdata = grid_set)
y_grid = ifelse(prob_set > 0.5, 1, 0)
plot(set[, -3],
     main = 'Classifier (Test set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

测试集.PNG 训练集.PNG 混淆矩阵.PNG