数据挖掘：关联规则挖掘实操

课本习题：探究学生成绩和学生特征的关联规则。

clingboo

443人浏览 · 2023-03-04 15:22:46

clingboo · 2023-03-04 15:22:46 发布

课本习题：探究学生成绩和学生特征的关联规则。

一.加载程序包

#0.加载程序包

library(arules)
library(arulesViz)
library(dplyr)

二.读入数据处理数据

#1.读入数据生成R数据框 声明变量类型 关于学生类型的各变量转换为因子型变量
#as.factor()函数将其转换为因子类型

StudentsPerformance <- read.csv("machine experiment/data/StudentsPerformance.csv",
                                colClasses = c(rep("character",5),
                                               rep("numeric",3)))
StudentsPerformance <- StudentsPerformance %>%
  mutate(gender = as.factor(gender)) %>%
  mutate(race.ethnicity = as.factor(race.ethnicity)) %>%
  mutate(parental.level.of.education = 
           as.factor(parental.level.of.education)) %>%
  mutate(lunch = as.factor(lunch)) %>%
  mutate(test.preparation.course = 
           as.factor(test.preparation.course))

#2.将数学 阅读 写作每项成绩按照小于60 大于等于60且小于85 大于或等于85份划分为3组 转换为因子变量
#使用cut函数将成绩分为三个区间 cut(0,59,84,100)分为(0,60] (60,85](85,100]
#as.factor()转换为因子类型

StudentsPerformance <- StudentsPerformance %>%
  mutate(math.score = as.factor(cut(math.score,breaks=c(0,59,84,100)))) %>%
  mutate(reading.score = as.factor(cut(reading.score,breaks=c(0,59,84,100)))) %>%
  mutate(writing.score = as.factor(cut(writing.score,breaks=c(0,59,84,100))))

三.关联分析查看结果

数学成绩(0,59]

#3.设最小支持度阈值min_sup=0.1 最小置信度阈值min_conf=0.5 学生特征与数学 阅读 写作每项成绩的关联规则
#挖掘每一项成绩与学生特征的关联规则的时候不需要另外两项成绩 先处理数据得到学生特征和单项成绩的数据框

StudentsPerformance_math <- StudentsPerformance %>%
  select(-c(reading.score,writing.score))
StudentsPerformance_reading <- StudentsPerformance %>%
  select(-c(math.score,writing.score))
StudentsPerformance_writing <- StudentsPerformance %>%
  select(-c(reading.score,math.score))

#4.挖掘数学成绩小于60分跟什么有关 查看分析结果 查看提升值排行前六位的非冗余规则查看提升值排行前六位的非冗余规则 绘制提升值大于1的无冗余规则的关联规则有向图

rules_math_below60 <- apriori(StudentsPerformance_math,
                              parameter = list(supp=0.1,conf=0.5),
                              appearance = list(rhs=c('math.score=(0,59]')),
                              control =list(verbose=F))
                              
inspect(head(rules_math_below60,by='lift'))
    lhs                               rhs                 support confidence coverage  lift count
[1] {gender=female,                                                                              
     lunch=free/reduced}           => {math.score=(0,59]}   0.106     0.5608    0.189 1.742   106
[2] {lunch=free/reduced,                                                                         
     test.preparation.course=none} => {math.score=(0,59]}   0.120     0.5357    0.224 1.664   120
     
inspect(head(rules_math_below60[!is.redundant(rules_math_below60)],by="lift"))
    lhs                               rhs                 support confidence coverage  lift count
[1] {gender=female,                                                                              
     lunch=free/reduced}           => {math.score=(0,59]}   0.106     0.5608    0.189 1.742   106
[2] {lunch=free/reduced,                                                                         
     test.preparation.course=none} => {math.score=(0,59]}   0.120     0.5357    0.224 1.664   120

rules_math_below60_pruned <- rules_math_below60[!is.redundant(rules_math_below60)]
plot(head(rules_math_below60_pruned,by="lift"),method = "graph")

在这里插入图片描述

数学成绩(59,84]

#5.挖掘数学成绩大于等于60分小于85跟什么有关 查看分析结果 查看提升值排行前六位的非冗余规则 绘制提升值大于1的无冗余规则的关联规则有向图

> rules_math_60to85 <- apriori(StudentsPerformance_math,
+                               parameter = list(supp=0.1,conf=0.5),
+                               appearance = list(rhs=c('math.score=(59,84]')),
+                               control =list(verbose=F))
+ 
> inspect(head(rules_math_60to85,by='lift'))
    lhs                                    rhs                  support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                           
     lunch=standard}                    => {math.score=(59,84]}   0.110     0.6587    0.167 1.176   110
[2] {gender=male,                                                                                      
     lunch=standard}                    => {math.score=(59,84]}   0.196     0.6203    0.316 1.108   196
[3] {race.ethnicity=group D}            => {math.score=(59,84]}   0.162     0.6183    0.262 1.104   162
[4] {lunch=standard,                                                                                   
     test.preparation.course=completed} => {math.score=(59,84]}   0.140     0.6167    0.227 1.101   140
[5] {gender=male,                                                                                      
     lunch=standard,                                                                                   
     test.preparation.course=none}      => {math.score=(59,84]}   0.125     0.6158    0.203 1.100   125
[6] {lunch=standard}                    => {math.score=(59,84]}   0.393     0.6093    0.645 1.088   393

> inspect(head(rules_math_60to85[!is.redundant(rules_math_60to85)],by="lift"))
    lhs                                    rhs                  support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                           
     lunch=standard}                    => {math.score=(59,84]}   0.110     0.6587    0.167 1.176   110
[2] {gender=male,                                                                                      
     lunch=standard}                    => {math.score=(59,84]}   0.196     0.6203    0.316 1.108   196
[3] {race.ethnicity=group D}            => {math.score=(59,84]}   0.162     0.6183    0.262 1.104   162
[4] {lunch=standard,                                                                                   
     test.preparation.course=completed} => {math.score=(59,84]}   0.140     0.6167    0.227 1.101   140
[5] {lunch=standard}                    => {math.score=(59,84]}   0.393     0.6093    0.645 1.088   393
[6] {gender=male,                                                                                      
     test.preparation.course=completed} => {math.score=(59,84]}   0.105     0.6034    0.174 1.078   105
     
> rules_math_60to85_pruned <- rules_math_60to85[!is.redundant(rules_math_60to85)]
> plot(head(rules_math_60to85_pruned,by="lift"),method = "graph")

在这里插入图片描述
数学成绩(85,100]

#6.挖掘数学成绩大于85跟什么有关 查看分析结果 查看提升值排行前六位的非冗余规则 绘制提升值大于1的无冗余规则的关联规则有向图
> rules_math_above85 <- apriori(StudentsPerformance_math,
+                               parameter = list(supp=0.1,conf=0.5),
+                               appearance = list(rhs=c('math.score=(84,100]')),
+                               control =list(verbose=F))
> inspect(head(rules_math_above85,by='lift'))
> inspect(head(rules_math_above85[!is.redundant(rules_math_above85)],by="lift"))
> rules_math_above85_pruned <- rules_math_above85[!is.redundant(rules_math_above85)]
> plot(head(rules_math_above85_pruned,by="lift"),method = "graph")
Error in plot.rules(head(rules_math_above85_pruned, by = "lift"), method = "graph") : 
  x contains 0 rules!

阅读成绩(0,59]

> rules_reading_below60 <- apriori(StudentsPerformance_reading,
+                               parameter = list(supp=0.1,conf=0.5),
+                               appearance = list(rhs=c('reading.score=(0,59]')),
+                               control =list(verbose=F))
> inspect(head(rules_reading_below60,by='lift'))
> inspect(head(rules_reading_below60[!is.redundant(rules_reading_below60)],by="lift"))
> rules_reading_below60_pruned <- rules_reading_below60[!is.redundant(rules_reading_below60)]
> plot(head(rules_reading_below60_pruned,by="lift"),method = "graph")
Error in plot.rules(head(rules_reading_below60_pruned, by = "lift"), method = "graph") : 
  x contains 0 rules!

阅读成绩(59,84]

> rules_reading_60to85 <- apriori(StudentsPerformance_reading,
+                              parameter = list(supp=0.1,conf=0.5),
+                              appearance = list(rhs=c('reading.score=(59,84]')),
+                              control =list(verbose=F))
> inspect(head(rules_reading_60to85,by='lift'))
    lhs                                    rhs                     support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                              
     lunch=standard}                    => {reading.score=(59,84]}   0.113     0.6766    0.167 1.135   113
[2] {gender=female,                                                                                       
     race.ethnicity=group C}            => {reading.score=(59,84]}   0.118     0.6556    0.180 1.100   118
[3] {gender=male,                                                                                         
     test.preparation.course=completed} => {reading.score=(59,84]}   0.113     0.6494    0.174 1.090   113
[4] {race.ethnicity=group C,                                                                              
     lunch=standard}                    => {reading.score=(59,84]}   0.133     0.6488    0.205 1.089   133
[5] {gender=female,                                                                                       
     lunch=standard,                                                                                      
     test.preparation.course=none}      => {reading.score=(59,84]}   0.139     0.6465    0.215 1.085   139
[6] {race.ethnicity=group C,                                                                              
     test.preparation.course=none}      => {reading.score=(59,84]}   0.130     0.6436    0.202 1.080   130
> inspect(head(rules_reading_60to85[!is.redundant(rules_reading_60to85)],by="lift"))
    lhs                                    rhs                     support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                              
     lunch=standard}                    => {reading.score=(59,84]}   0.113     0.6766    0.167 1.135   113
[2] {gender=female,                                                                                       
     race.ethnicity=group C}            => {reading.score=(59,84]}   0.118     0.6556    0.180 1.100   118
[3] {gender=male,                                                                                         
     test.preparation.course=completed} => {reading.score=(59,84]}   0.113     0.6494    0.174 1.090   113
[4] {race.ethnicity=group C,                                                                              
     lunch=standard}                    => {reading.score=(59,84]}   0.133     0.6488    0.205 1.089   133
[5] {gender=female,                                                                                       
     lunch=standard,                                                                                      
     test.preparation.course=none}      => {reading.score=(59,84]}   0.139     0.6465    0.215 1.085   139
[6] {race.ethnicity=group C,                                                                              
     test.preparation.course=none}      => {reading.score=(59,84]}   0.130     0.6436    0.202 1.080   130
> rules_reading_60to85_pruned <- rules_reading_60to85[!is.redundant(rules_reading_60to85)]
> plot(head(rules_reading_60to85_pruned,by="lift"),method = "graph")

在这里插入图片描述 阅读成绩(84,100]

> rules_reading_above85 <- apriori(StudentsPerformance_reading,
+                               parameter = list(supp=0.1,conf=0.5),
+                               appearance = list(rhs=c('reading.score=(84,100]')),
+                               control =list(verbose=F))
> inspect(head(rules_reading_above85,by='lift'))
> inspect(head(rules_reading_above85[!is.redundant(rules_reading_above85)],by="lift"))
> rules_reading_above85_pruned <- rules_reading_above85[!is.redundant(rules_reading_above85)]
> plot(head(rules_reading_above85_pruned,by="lift"),method = "graph")
Error in plot.rules(head(rules_reading_above85_pruned, by = "lift"), method = "graph") : 
  x contains 0 rules!

写作成绩(0,59]

> rules_writing_below60 <- apriori(StudentsPerformance_writing,
+                                  parameter = list(supp=0.1,conf=0.5),
+                                  appearance = list(rhs=c('writing.score=(0,59]')),
+                                  control =list(verbose=F))
+ 
> inspect(head(rules_writing_below60,by='lift'))
    lhs                               rhs                    support confidence coverage  lift count
[1] {lunch=free/reduced,                                                                            
     test.preparation.course=none} => {writing.score=(0,59]}   0.115     0.5134    0.224 1.827   115
     
> inspect(head(rules_writing_below60[!is.redundant(rules_writing_below60)],by="lift"))
    lhs                               rhs                    support confidence coverage  lift count
[1] {lunch=free/reduced,                                                                            
     test.preparation.course=none} => {writing.score=(0,59]}   0.115     0.5134    0.224 1.827   115
     
> rules_writing_below60_pruned <- rules_writing_below60[!is.redundant(rules_writing_below60)]
> plot(head(rules_writing_below60_pruned,by="lift"),method = "graph")

在这里插入图片描述

写作成绩(59,84]

> rules_writing_60to85 <- apriori(StudentsPerformance_writing,
+                                 parameter = list(supp=0.1,conf=0.5),
+                                 appearance = list(rhs=c('writing.score=(59,84]')),
+                                 control =list(verbose=F))

> inspect(head(rules_writing_60to85,by='lift'))
    lhs                                    rhs                     support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                              
     lunch=standard}                    => {writing.score=(59,84]}   0.113     0.6766    0.167 1.159   113
[2] {gender=female,                                                                                       
     lunch=standard,                                                                                      
     test.preparation.course=none}      => {writing.score=(59,84]}   0.144     0.6698    0.215 1.147   144
[3] {gender=female,                                                                                       
     lunch=standard}                    => {writing.score=(59,84]}   0.213     0.6474    0.329 1.109   213
[4] {race.ethnicity=group D}            => {writing.score=(59,84]}   0.168     0.6412    0.262 1.098   168
[5] {gender=male,                                                                                         
     test.preparation.course=completed} => {writing.score=(59,84]}   0.110     0.6322    0.174 1.083   110
[6] {test.preparation.course=completed} => {writing.score=(59,84]}   0.224     0.6257    0.358 1.071   224

> inspect(head(rules_writing_60to85[!is.redundant(rules_writing_60to85)],by="lift"))
    lhs                                    rhs                     support confidence coverage  lift count
[1] {race.ethnicity=group D,                                                                              
     lunch=standard}                    => {writing.score=(59,84]}   0.113     0.6766    0.167 1.159   113
[2] {gender=female,                                                                                       
     lunch=standard,                                                                                      
     test.preparation.course=none}      => {writing.score=(59,84]}   0.144     0.6698    0.215 1.147   144
[3] {gender=female,                                                                                       
     lunch=standard}                    => {writing.score=(59,84]}   0.213     0.6474    0.329 1.109   213
[4] {race.ethnicity=group D}            => {writing.score=(59,84]}   0.168     0.6412    0.262 1.098   168
[5] {gender=male,                                                                                         
     test.preparation.course=completed} => {writing.score=(59,84]}   0.110     0.6322    0.174 1.083   110
[6] {test.preparation.course=completed} => {writing.score=(59,84]}   0.224     0.6257    0.358 1.071   224

> rules_writing_60to85_pruned <- rules_writing_60to85[!is.redundant(rules_writing_60to85)]
> plot(head(rules_writing_60to85_pruned,by="lift"),method = "graph")

在这里插入图片描述

写作成绩(84,100]

> rules_writing_60to85_pruned <- rules_writing_60to85[!is.redundant(rules_writing_60to85)]
> plot(head(rules_writing_60to85_pruned,by="lift"),method = "graph")
> rules_writing_above85 <- apriori(StudentsPerformance_writing,
+                                  parameter = list(supp=0.1,conf=0.5),
+                                  appearance = list(rhs=c('writing.score=(84,100]')),
+                                  control =list(verbose=F))
> inspect(head(rules_writing_above85,by='lift'))
> inspect(head(rules_writing_above85[!is.redundant(rules_writing_above85)],by="lift"))
> rules_writing_above85_pruned <- rules_writing_above85[!is.redundant(rules_writing_above85)]
> plot(head(rules_writing_above85_pruned,by="lift"),method = "graph")
Error in plot.rules(head(rules_writing_above85_pruned, by = "lift"), method = "graph") : 
  x contains 0 rules!

永洪数据分析社区

永洪科技，致力于打造全球领先的数据技术厂商，具备从数据应用方案咨询、BI、AIGC智能分析、数字孪生、数据资产、数据治理、数据实施的端到端大数据价值服务能力。

更多推荐

销售数据分析方法、如何写好一个专题分析报告、Hive大数据知识体系教程、大数据分析平台总体架构方案……| 本周精华...

▲点击上方卡片关注我，回复“8”，加入数据分析·领地，一起学习数据分析，持续更新数据分析学习路径相关资料~（精彩数据观点、学习资料、数据课程分享、读书会、分享会等你一起来乘风破浪~）回复“小飞象”，领取数据分析知识大礼包。关注微信公众号：木木自由，更多产品、运营与数据分析干货以及经验分享【数据分析-领地】知识星球，每周会产生大量精华内容，每周将整理《数据分析-领地：一周星球内参》，让你不错过任何一

永洪数据分析社区

Web报表软件的集成方案

报表开发只是应用程序中的一部分，而非全部，因此Web报表软件的集成性就显得非常重要了。　传统的Web报表软件无一例外地都提供了一个独立的报表服务器。采用独立服务器时的，应用结构如下图：　采用独立服务器的不便：• 独立的报表服务器，与应用程序的沟通是通过网络协议，严重降低性能；• 无法享受应用服务器的各项优势功能，包括集群能力、连接池的管理...