回归分析是一种预测性的建模技术，它研究的是因变量（目标）和自变量（预测器）之间的关系。本文简单的介绍一下简单线性回归。
Simple Linear Regression
Data Preprocessing
1 读入数据集
# Importing the dataset dataset <- read.csv('studentscores.csv') #时间和得分之间的关系 Hours Scores 1 2.5 21 2 5.1 47 3 3.2 27 4 8.5 75 5 3.5 30 6 1.5 20 plot(dataset$Hours,dataset$Scores) #
如图可见符合线性回归模型，根据训练集数据进行回归函数分析，并对测试数据进行预测。
2 数据预处理
首先按照上次分享的进行数据预处理
3 训练集和测试集
将数据按照4:1拆分，每一组分别包含自变量和因变量
# Splitting the dataset into the Training set and Test set # install.packages('caTools') library(caTools) set.seed(123) split = sample.split(dataset$Scores, SplitRatio = 1/4) training_set <- subset(dataset, split == TRUE) test_set <- subset(dataset, split == FALSE) # Feature Scaling # training_set <- scale(training_set) # test_set <- scale(test_set)
4 模型拟合及预测
通过训练集进行模型拟合得到曲线，然后将测试集的X_test带入曲线中，得到预测结果y_pred，最后将预测结果y_pred与测试集中的y_test进行比较，确定预测是否准确。
# Fitting Simple Linear Regression to the Training set regressor = lm(formula = Scores ~ Hours, data = training_set) # Predicting the results y_pred <- predict(regressor, newdata = test_set)
5 结果可视化
# Visualising the Training results library(ggplot2) ggplot() + geom_point(aes(x = training_set$Hours, y = training_set$Scores), colour = 'red') + geom_line(aes(x = training_set$Hours, y = predict(regressor, newdata = training_set)), colour = 'blue') + ggtitle('Scores vs Hours (Training set)') + xlab('Hours') + ylab('Scores') # Visualising the Test results library(ggplot2) ggplot() + geom_point(aes(x = test_set$Hours, y = test_set$Scores), colour = 'red') + geom_line(aes(x = training_set$Hours, y = predict(regressor, newdata = training_set)), colour = 'blue') + ggtitle('Scores vs Hours (Test set)') + xlab('Hours') + ylab('Scores')
