#Loading the data set
response<-read_excel("Kaggle_Data_Set.xlsx", sheet = 2)

# Viewing the first 10 rows of response 
kable(head(response,10),'html') %>%
 kable_styling() %>%
 scroll_box(width = "800px", height = "700px")

#Adding a Respondent column to the data frame
responses<-tibble::rowid_to_column(response,"Respondent")

# Creating a new data frame called tools
tools <- responses

# Adding a new column to tools which splits the WorkToolsSelect column at the commas and unnests the new column
tools <- tools  %>% 
         mutate(work_tools = strsplit(as.character(WorkToolsSelect), ","))%>%
         unnest(work_tools)

# Viewing the first 10 rows of tools 
kable( head(tools,10),'html') %>%
 kable_styling() %>%
 scroll_box(width = "800px", height = "700px")

# Creating a new data frame
tool_count <- tools

# Grouping the data by work_tools, calculate the number of responses in each group
tool_count <- tool_count  %>% 
              group_by(work_tools)  %>% 
              summarize(responses=n())

# Sorting tool_count so that the most popular tools are at the top
tool_count<-tool_count[order(tool_count$responses,decreasing = T),]

# Printing the first 6 results
kable( head(tool_count,6),'html') %>%
 kable_styling() %>%
 scroll_box(width = "800px", height = "300px")

# Creating a bar chart of the work_tools column. 

# Arranging the bars so that the tallest are on the far left
pl<-ggplot(tool_count,aes(x=reorder(work_tools,-responses),y=responses,na.rm="T")) + 
           geom_bar(stat = 'identity',fill='tan2') 

#Rotating the bar labels on x-axis by 90 degrees
pl2<-pl + theme(axis.text.x=element_text(angle=90, hjust=1))
pl2+xlab('Work Tools')+ ylab('Total Responses')+ggtitle('Bar Chart of Work Tools Used')

# Creating a new data frame called debate_tools
debate_tools <- responses

# Creating a new column called language_preference, based on the following conditions 
#"R" if WorkToolsSelect contains "R" but not "Python".
#"Python" if WorkToolsSelect contains "Python" but not "R".
#"Both" if WorkToolsSelect contains both "R" and "Python".
#"Neither" if WorkToolsSelect contains neither "R" nor "Python".

debate_tools <- debate_tools  %>% 
          mutate(language_preference = case_when(
                                       grepl('R',WorkToolsSelect)== T & grepl('Python',WorkToolsSelect)== T~'Both',
                                       grepl('R',WorkToolsSelect)== T & grepl('Python',WorkToolsSelect)!= T ~ 'R',
                                       grepl('R',WorkToolsSelect)!=T & grepl('Python',WorkToolsSelect)==T ~ 'Python',
                                       grepl('R',WorkToolsSelect)!=T & grepl('Python',WorkToolsSelect)!=T ~ 'Neither'))

# Printing the first 10 rows of debate_tools
kable( head(debate_tools,10),'html') %>%
 kable_styling() %>%
 scroll_box(width = "800px", height = "600px")

# Creating a new data frame
debate_plot <- debate_tools

# Grouping by language preference and calculate number of responses
debate_plot <- debate_plot  %>% 
               group_by(language_preference)  %>% 
               summarise(language_preference_response=n())

# Removing the row for users of "Neither"
    debate_plot<-filter(debate_plot, language_preference != 'Neither')
    
#Viewing debate_plot
kable(debate_plot,'html') %>%
 kable_styling() %>%
 scroll_box(width = "700px", height = "200px")

# Creating a bar chart
pl<-ggplot(debate_plot,aes(x=language_preference,y=language_preference_response))+ 
    geom_bar(stat = 'identity',fill='tan4')+xlab("Languages Preferred")+ylab('Count')+ggtitle('Languages Preferred by Respondent')
print(pl)

# Creating a new data frame
recommendations <- debate_tools

# Grouping by language_preference and LanguageRecommendationSelect
recommendations <- recommendations  %>%     
                   group_by(language_preference,LanguageRecommendationSelect)%>%
                   summarise(count_recommendation_language=n())

# Removing empty NA's and include the top recommendations
recommendations<-recommendations%>%
filter(!is.na(LanguageRecommendationSelect))%>%
arrange(desc(count_recommendation_language))%>% 
mutate(row_number(language_preference))%>% 
filter(row_number() <=4)

# Creating a faceted bar plot
ggplot(recommendations, aes(x=LanguageRecommendationSelect,y=count_recommendation_language,fill=count_recommendation_language))+
geom_bar(stat='identity')+
facet_wrap(~language_preference)+
xlab('Language Recommended')+ylab('Count')+
theme(axis.text.x=element_text(angle=90, hjust=1),legend.position = 'none')