Update M5-epidemiology.Rmd

notebooks/module5-epidemi/M5-epidemiology.Rmd

@@ -3,7 +3,7 @@
 
 *by Dr Jason Wong*
 
-*Date: 16-11-2022 (Updated 21-11-2022)*
+*Date: 6-11-2023*
 
 [The RMarkdown notebook to run your own code can be downloaded here](https://github.com/StatBiomed/BMDS-book/raw/main/notebooks/module5-epidemi/M5-epidemiology.Rmd)
 
@@ -451,39 +451,39 @@ hist(pubmed$Publication.Year)
 
 <!-- #Create a vector containing only the text -->
 <!-- gtext <- HMRF$Project.Title -->
-<!-- # Create a corpus   -->
+<!-- # Create a corpus -->
 <!-- gdocs <- Corpus(VectorSource(gtext)) -->
 <!-- gdocs <- gdocs %>% -->
 <!--   tm_map(removePunctuation) %>% -->
 <!--   tm_map(stripWhitespace) -->
 <!-- gdocs <- tm_map(gdocs, content_transformer(tolower)) -->
 <!-- gdocs <- tm_map(gdocs, removeWords, stopwords("english")) -->
 
-<!-- gdtm <- TermDocumentMatrix(gdocs)  -->
-<!-- gmatrix <- as.matrix(gdtm)  -->
-<!-- gwords <- sort(rowSums(gmatrix),decreasing=TRUE)  -->
+<!-- gdtm <- TermDocumentMatrix(gdocs) -->
+<!-- gmatrix <- as.matrix(gdtm) -->
+<!-- gwords <- sort(rowSums(gmatrix),decreasing=TRUE) -->
 <!-- gdf <- data.frame(word = names(gwords),freq=gwords) -->
 
-<!-- set.seed(1235) # for reproducibility  -->
+<!-- set.seed(1235) # for reproducibility -->
 <!-- gp<-ggwordcloud(words = gdf$word, freq = gdf$freq, min.freq = 1,max.words=200, random.order=FALSE, rot.per=0.35,            colors=brewer.pal(8, "Dark2")) -->
 <!-- #gp -->
 
 <!-- #Create a vector containing only the text -->
 <!-- pmtext <- pubmed$Title -->
-<!-- # Create a corpus   -->
+<!-- # Create a corpus -->
 <!-- pmdocs <- Corpus(VectorSource(pmtext)) -->
 <!-- pmdocs <- pmdocs %>% -->
 <!--   tm_map(removePunctuation) %>% -->
 <!--   tm_map(stripWhitespace) -->
 <!-- pmdocs <- tm_map(pmdocs, content_transformer(tolower)) -->
 <!-- pmdocs <- tm_map(pmdocs, removeWords, stopwords("english")) -->
 
-<!-- pmdtm <- TermDocumentMatrix(pmdocs)  -->
-<!-- pmmatrix <- as.matrix(pmdtm)  -->
-<!-- pmwords <- sort(rowSums(pmmatrix),decreasing=TRUE)  -->
+<!-- pmdtm <- TermDocumentMatrix(pmdocs) -->
+<!-- pmmatrix <- as.matrix(pmdtm) -->
+<!-- pmwords <- sort(rowSums(pmmatrix),decreasing=TRUE) -->
 <!-- pmdf <- data.frame(word = names(pmwords),freq=pmwords) -->
 
-<!-- set.seed(1235) # for reproducibility  -->
+<!-- set.seed(1235) # for reproducibility -->
 <!-- pm<-ggwordcloud(words = pmdf$word, freq = pmdf$freq, min.freq = 1,max.words=200, random.order=FALSE, rot.per=0.35,            colors=brewer.pal(8, "Dark2")) -->
 <!-- grid.arrange(arrangeGrob(pm, top = 'Pubmed'),arrangeGrob(gp, top = 'Grants'),nrow=2,heights=c(6,6)) -->
 
@@ -528,6 +528,6 @@ grid.arrange(gp,ginc,gmor,pinc, pmor, ncol=3)
 
 ```
 
-## 5. Task (to be completed in Tutotial 2 by 3:00pm and shared with other tutorial group)
+## 5. Open disucssion
 
-As a group, discuss what cancer type you think is most worthy of funding in Hong Kong. Prepare 2-3 PowerPoint/Google Slides summarising your decision. Include some points and figures supporting your final conclusion. If possible also include suggestions of what other data/analyses can be performed and/or other cancer types that are also in need of funding in Hong Kong.
+As a group discuss what cancer type would be most worthy of funding in Hong Kong. Statistics and figures should be used to support your decision. If possible also discuss other data/analyses that can be performed and/or other diseases that are also in need of funding in Hong Kong.