The tools and Programming languages used by Data Scientist in the United States of America (Project 3 Part)

survey_tib <- survey_tib %>% 
 filter((`Q3_In which country do you currently reside?`=='United States of America')&(`Q6_Select the title most similar to your current role (or most recent title if retired): - Selected Choice`=='Data Scientist'))
#write.csv(survey_tib,"C:/Users/newma/OneDrive/Desktop/MSDS Fall 2021/DATA 607 - Data Acquisition and Mgt/Project 3/surv.csv", row.names = FALSE)

survey_tib <- survey_tib %>% 
  select(starts_with(c("Q1_","Q2_","Q3_","Q6_","Q7_","Q13","Q16","Q21","Q33")))
#names(survey_tib)

surv_dataset <- survey_tib %>% select(starts_with(c("Q1_","Q2_","Q3_","Q7_","Q33")),-contains("OTHER_TEXT")) %>%
pivot_longer(starts_with("Q33"),names_to="Dataset",values_to="Dataset_type")

surv_dataset_tib<-surv_dataset %>% 
  count(surv_dataset$Dataset_type) %>%
  rename("DataSource" = "surv_dataset$Dataset_type","Count"="n")%>%
  arrange(desc(Count))

#write.csv(surv_dataset,"C:/Users/newma/OneDrive/Desktop/MSDS Fall 2021/DATA 607 - Data Acquisition and Mgt/Project 3/tibviz.csv", row.names = FALSE)

surv_dataset_tib<-surv_dataset_tib[-c(1),]
surv_dataset_tib2<-surv_dataset_tib %>% 
  mutate(proportion = round((surv_dataset_tib$Count /sum(surv_dataset_tib$Count))*100,2))

surv_dataset_tib2 %>% ggplot(aes(reorder(DataSource,proportion),proportion)) +
  geom_col(fill="#06272C")+coord_flip()+geom_text(aes(label=proportion),color="red") +labs(x="Data Sources")+theme_bw()

kbl(surv_dataset_tib2)%>%
  kable_styling() %>% kable_paper("hover", full_width = F)

surv_viz_tool<- survey_tib %>% select(starts_with(c("Q1_","Q2_","Q3_","Q7_","Q21")),-contains("OTHER_TEXT")) %>%
pivot_longer(starts_with("Q21"),names_to="ToolName",values_to="Tool")

surv_viz_tool_tib <- surv_viz_tool %>%
  count(surv_viz_tool$Tool) %>% rename("VisualTools" = "surv_viz_tool$Tool","Count"="n")%>%
  arrange(desc(Count))

surv_viz_tool_tib <- surv_viz_tool_tib[-c(1),]
surv_viz_tool_tib2<-surv_viz_tool_tib %>%
  mutate(proportion = round((Count /sum(Count))*100,2))%>% arrange(desc(proportion))
  
surv_viz_tool_tib2 %>% ggplot(aes(reorder(VisualTools,proportion),proportion)) +
  geom_col()+coord_flip()+geom_col(fill="#A7ADBE")+
  geom_text(aes(label=proportion),color="red") +labs(x="Visual Tools")+theme_bw()

kbl(surv_viz_tool_tib2) %>%
  kable_styling() %>% kable_paper("hover", full_width = F)

ide_tool<- survey_tib %>% 
  select(starts_with(c("Q1_","Q2_","Q3_","Q7_","Q13")),-contains("OTHER_TEXT")) %>%
pivot_longer(starts_with("Q13"),names_to="IDEName",values_to="IDEUsed")
#write.csv(surv_viz_tool,"C:/Users/newma/OneDrive/Desktop/MSDS Fall 2021/DATA 607 - Data Acquisition and Mgt/Project 3/survviz.csv", row.names = FALSE)

ide_tool_tib <- ide_tool %>%
  count(ide_tool$IDEUsed) %>% rename("IDE" = "ide_tool$IDEUsed","Count"="n")%>%
  arrange(desc(Count))

ide_tool_tib<-ide_tool_tib[-c(1),]
ide_tool_tib2<-ide_tool_tib %>%
  mutate(proportion = round((Count /sum(Count))*100,2))%>%arrange(desc(proportion))

ide_tool_tib2 %>% ggplot(aes(reorder(IDE,proportion),proportion)) +
  geom_col(fill="#18213A")+coord_flip()+
  geom_text(aes(label=proportion),color="red")+
  labs(x="IDE")+theme_bw()

kbl(ide_tool_tib2)%>%
  kable_styling() %>% kable_paper("hover", full_width = F)

lang_tool<- survey_tib %>% 
  select(starts_with(c("Q1_","Q2_","Q3_","Q7_","Q16")),-contains("OTHER_TEXT")) %>%
pivot_longer(starts_with("Q16"),names_to="LangName",values_to="LangUsed")

#write.csv(surv_viz_tool,"C:/Users/newma/OneDrive/Desktop/MSDS Fall 2021/DATA 607 - Data Acquisition and Mgt/Project 3/survviz.csv", row.names = FALSE)

Lang_tool_tib <- lang_tool %>%
  count(lang_tool$LangUsed) %>% rename("Language" = "lang_tool$LangUsed","Count"="n")%>%
  arrange(desc(Count))

Lang_tool_tib<-Lang_tool_tib[-c(1),]
Lang_tool_tib2<-Lang_tool_tib %>%
  mutate(proportion = round((Count /sum(Count))*100,2))%>%arrange(desc(proportion))

Lang_tool_tib2 %>% ggplot(aes(reorder(Language,proportion),proportion)) +
  geom_col(fill='#633974')+coord_flip()+
  geom_text(aes(label=proportion),color="green")+ labs(x="Language")+theme_bw()

kbl(Lang_tool_tib2) %>%
  kable_styling() %>% kable_paper("hover", full_width = F)