Data Science with R Naive Bayes Clasification

相似文件 换一批

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Data Science with R Naive Bayes Clasification

The required packages for this chapter include:

• library(rattle) # weather and normVarNames()
• library(randomForest) # na.roughfix()
• library(e1071) # naiveBayes()
• library(ROCR) # prediction()
  

As we work through this chapter, new R commands will be introduced. Be sure to review the command’s documentation and understand what the command does. You can ask for help using
the ? command as in:
?read.csv
We can obtain documentation on a particular package using the help= option of library():
library(help=rattle)
This chapter is intended to be hands on. To learn effectively, you are encouraged to have R running (e.g., RStudio) and to run all the commands as they appear here. Check that you get the same output, and you understand the output. Try some variations.

本帖隐藏的内容

Data Science with R Naive Bayes Clasification.rar (188.79 KB) 本附件包括：

• Data Science with R Naive Bayes Clasification.pdf

2015-6-13 07:50:26 上传

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏2 回帖

关键词：Data Science Science cation Bayes ATION

1. ## ----module, echo=FALSE, results="asis"----------------------------------
   
2. Module <- "BayesO"
   
3. cat(paste0("\\newcommand{\\Module}{", Module, "}"))
   
4. 
   
5. 
   
6. ## ----setup, child="mycourse.Rnw"-----------------------------------------
   
7. 
   
8. ## ----setup_options, include=FALSE----------------------------------------
   
9. library(knitr)
   
10. library(xtable)
    
11. 
    
12. opts_chunk$set(cache=FALSE)
    
13. 
    
14. opts_chunk$set(out.width='0.8\\textwidth')
    
15. opts_chunk$set(fig.align='center')
    
16. 
    
17. opts_chunk$set(src.top=NULL)
    
18. opts_chunk$set(src.bot=NULL)
    
19. opts_chunk$set(out.lines=4)
    
20. opts_chunk$set(out.truncate=80)
    
21. 
    
22. opts_chunk$set(fig.path=sprintf("figures/%s/", Module))
    
23. opts_chunk$set(cache.path=sprintf("cache/%s/", Module))
    
24. opts_chunk$set(bib.file=paste0(Module, ".bib"))
    
25. 
    
26. # Leave code as I have formatted it.
    
27. 
    
28. opts_chunk$set(tidy=FALSE)
    
29. 
    
30. # Hooks
    
31. 
    
32. # Allow auto crop of base graphics plots when crop=TRUE.
    
33. 
    
34. knit_hooks$set(crop=hook_pdfcrop)
    
35. 
    
36. # Truncate long lines and long output
    
37. 
    
38. hook_output <- knit_hooks$get("output")
    
39. hook_source <- knit_hooks$get("source")
    
40. knit_hooks$set(output=function(x, options)
    
41. {
    
42.   if (options$results != "asis")
    
43.   {
    
44.     # Split string into separate lines.
    
45.     x <- unlist(stringr::str_split(x, "\n"))
    
46.     # Trim to the number of lines specified.
    
47.     if (!is.null(n <- options$out.lines))
    
48.     {
    
49.       if (length(x) > n)
    
50.       {
    
51.         # Truncate the output.
    
52.         x <- c(head(x, n), "....\n")
    
53.       }
    
54.     }
    
55.     # Truncate each line to length specified.
    
56.     if (!is.null(m <- options$out.truncate))
    
57.     {
    
58.       len <- nchar(x)
    
59.       x[len>m] <- paste0(substr(x[len>m], 0, m-3), "...")
    
60.     }
    
61.     # Paste lines back together.
    
62.     x <- paste(x, collapse="\n")
    
63.     # Replace ' = ' with '=' - my preference. Hopefully won't
    
64.     # affect things inappropriately.
    
65.     x <- gsub(" = ", "=", x)
    
66.   }
    
67.   hook_output(x, options)
    
68. },
    
69. source=function(x, options)
    
70. {
    
71.   # Split string into separate lines.
    
72.   x <- unlist(stringr::str_split(x, "\n"))
    
73.   # Trim to the number of lines specified.
    
74.   if (!is.null(n <- options$src.top))
    
75.   {
    
76.     if (length(x) > n)
    
77.     {
    
78.       # Truncate the output.
    
79.       if (is.null(m <-options$src.bot)) m <- 0
    
80.       x <- c(head(x, n+1), "\n....\n", tail(x, m+2))
    
81.    }
    
82.   }
    
83.   # Paste lines back together.
    
84.   x <- paste(x, collapse="\n")
    
85.   hook_source(x, options)
    
86. })
    
87. 
    
88. # Optionally allow R Code chunks to be environments so we can refer to them.
    
89. 
    
90. knit_hooks$set(rcode=function(before, options, envir)
    
91. {
    
92.   if (before)
    
93.     sprintf('\\begin{rcode}\\label{%s}\\hfill{}', options$label)
    
94.   else
    
95.     '\\end{rcode}'
    
96. })
    
97. 
    
98. 
    
99. 
    
100. ## ----load_packages, message=FALSE----------------------------------------
     
101. library(rattle)       # weather and normVarNames()
     
102. library(randomForest) # na.roughfix()
     
103. library(e1071)        # naiveBayes()
     
104. library(ROCR)         # prediction()
     
105. 
     
106. 
     
107. ## ----common_intro, child='documentation.Rnw', eval=TRUE------------------
     
108. 
     
109. 
     
110. ## ----help_library, eval=FALSE, tidy=FALSE--------------------------------
     
111. ## ?read.csv
     
112. 
     
113. 
     
114. ## ----help_package, eval=FALSE--------------------------------------------
     
115. ## library(help=rattle)
     
116. 
     
117. 
     
118. ## ----record_start_time, echo=FALSE---------------------------------------
     
119. start.time <- proc.time()
     
120. 
     
121. 
     
122. ## ----generate_bib, echo=FALSE, message=FALSE, warning=FALSE--------------
     
123. # Write all packages in the current session to a bib file
     
124. if (is.null(opts_chunk$get("bib.file"))) opts_chunk$set(bib.file="Course.bib")
     
125. write_bib(sub("^.*/", "", grep("^/", searchpaths(), value=TRUE)),
     
126.           file=opts_chunk$get("bib.file"))
     
127. system(paste("cat extra.bib >>", opts_chunk$get("bib.file")))
     
128. # Fix up specific issues.
     
129. # R-randomForest
     
130. system(paste("perl -pi -e 's|Fortran original by Leo Breiman",
     
131.              "and Adele Cutler and R port by|Leo Breiman and",
     
132.              "Adele Cutler and|'", opts_chunk$get("bib.file")))
     
133. # R-C50
     
134. system(paste("perl -pi -e 's|. C code for C5.0 by R. Quinlan|",
     
135.              " and J. Ross Quinlan|'", opts_chunk$get("bib.file")))
     
136. # R-caret
     
137. system(paste("perl -pi -e 's|. Contributions from|",
     
138.              " and|'", opts_chunk$get("bib.file")))
     
139. # Me
     
140. system(paste("perl -pi -e 's|Graham Williams|",
     
141.              "Graham J Williams|'", opts_chunk$get("bib.file")))
     
142. 
     
143. 
     
144. 
     
145. 
     
146. ## ----bayes_prepare_data_weather, message=FALSE---------------------------
     
147. library(rattle)                # Normalise names normVarNames() and weather dataset.
     
148. library(randomForest)        # Impute missing using na.roughfix().
     
149. 
     
150. dsname     <- "weather"
     
151. ds         <- get(dsname)
     
152. names(ds)  <- normVarNames(names(ds))
     
153. vars       <- names(ds)
     
154. target     <- "rain_tomorrow"
     
155. risk       <- "risk_mm"
     
156. id         <- c("date", "location")
     
157. 
     
158. ignore     <- union(id, if (exists("risk")) risk)
     
159. vars       <- setdiff(vars, ignore)
     
160. 
     
161. inputs     <- setdiff(vars, target)
     
162. numi       <- which(sapply(ds[inputs], is.numeric))
     
163. numc       <- names(numi)
     
164. cati       <- which(sapply(ds[inputs], is.factor))
     
165. catc       <- names(cati)
     
166. 
     
167. ds[numc]   <- na.roughfix(ds[numc]) # Impute missing values, roughly.
     
168. ds[target] <- as.factor(ds[[target]])        # Ensure the target is categoric.
     
169. 
     
170. nobs       <- nrow(ds)
     
171. 
     
172. form       <- formula(paste(target, "~ ."))
     
173. 
     
174. set.seed(42)
     
175. 
     
176. train      <- sample(nobs, 0.7*nobs)
     
177. test       <- setdiff(seq_len(nobs), train)
     
178. actual     <- ds[test, target]
     
179. risks      <- ds[test, risk]
     
180. 
     
181. 
     
182. ## ----check_dataset, out.lines=5------------------------------------------
     
183. dim(ds)
     
184. names(ds)
     
185. head(ds)
     
186. tail(ds)
     
187. str(ds)
     
188. summary(ds)
     
189. 
     
190. 
     
191. ## ----build_nb_model, out.lines=26----------------------------------------
     
192. library(e1071)
     
193. model      <- naiveBayes(form, data=ds[train, vars])
     
194. model
     
195. 
     
196. 
     
197. ## ----evaluate_nb_model, message=FALSE, out.lines=NULL--------------------
     
198. classes    <- predict(model, ds[test, vars], type="class")
     
199. acc        <- sum(classes == actual, na.rm=TRUE)/length(actual)
     
200. err        <- sum(classes != actual, na.rm=TRUE)/length(actual)
     
201. predicted  <- predict(model, ds[test, vars], type="raw")[,2]
     
202. pred       <- prediction(predicted, ds[test, target])
     
203. ate        <- attr(performance(pred, "auc"), "y.values")[[1]]
     
204. riskchart(predicted, actual, risks)
     
205. round(table(actual, classes, dnn=c("Actual", "Predicted"))/length(actual), 2)
     
206. 
     
207. 
     
208. ## ----common_outtro, child="finale.Rnw", eval=TRUE------------------------
     
209. 
     
210. 
     
211. ## ----syinfo, child="sysinfo.Rnw", eval=TRUE------------------------------
     
212. 
     
213. ## ----echo=FALSE, message=FALSE-------------------------------------------
     
214. require(Hmisc)
     
215. pkg <- "knitr"
     
216. pkg.version <- installed.packages()[pkg, 'Version']
     
217. pkg.date <- installed.packages(fields="Date")[pkg, 'Date']
     
218. pkg.info <- paste(pkg, pkg.version, pkg.date)
     
219. 
     
220. rev <- system("bzr revno", intern=TRUE)
     
221. cpu <- system(paste("cat /proc/cpuinfo | grep 'model name' |",
     
222.                     "head -n 1 | cut -d':' -f2"), intern=TRUE)
     
223. ram <- system("cat /proc/meminfo | grep MemTotal: | awk '{print $2}'",
     
224.               intern=TRUE)
     
225. ram <- paste0(round(as.integer(ram)/1e6, 1), "GB")
     
226. user <- Sys.getenv("LOGNAME")
     
227. node <- Sys.info()[["nodename"]]
     
228. user.node <- paste0(user, "@", node)
     
229. gcc.version <- system("g++ -v 2>&1 | grep 'gcc version' | cut -d' ' -f1-3",
     
230.                       intern=TRUE)
     
231. os <- system("lsb_release -d | cut -d: -f2 | sed 's/^[ \t]*//'", intern=TRUE)

复制代码

感谢分享

en
好像还不错你发的

kankan

看看！

看看，谢谢！

ccccccccccccccccccccccccccccccccc