UmairHanif_KHI_R_ASSIGNMENT2

Q1.R

@@ -0,0 +1,23 @@
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("C:/Users/umair.hanif/Desktop/Learning Outcomes/AR/hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))

Q10.R

@@ -0,0 +1,8 @@
+#Question 10
+repeated_visitors <- select(dataf,id) %>%
+  group_by(id) %>%
+  summarise(visits=length(id)) %>%
+  arrange(desc(visits)) %>%
+  filter(visits > 1) %>%
+  print   # printing repeated visitors along with their ids
+

Q11.R

@@ -0,0 +1,8 @@
+#Question 10
+repeated_visitors <- select(dataf,id) %>%
+  group_by(id) %>%
+  summarise(visits=length(id)) %>%
+  arrange(desc(visits)) %>%
+  filter(visits > 1) %>%
+  print   # printing repeated visitors along with their ids
+

Q12.R

@@ -0,0 +1,30 @@
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))
+
+
+dataf %>% 
+  count(id, Procedure) %>%
+  slice(which(n>1))%>%
+  filter(!is.na(Procedure))%>%
+  select(id,Procedure)

Q13.R

@@ -0,0 +1,7 @@
+#Question 13
+medianAge <- dataf %>% 
+  select(Sex,Age) %>%
+  group_by(Sex) %>%
+  summarise(median(Age, na.rm = TRUE)) %>%
+  print
+

Q14.R

@@ -0,0 +1,5 @@
+#Question 14
+dataf$TotalCharges<-as.numeric(as.character(dataf$TotalCharges))
+sum_of_charges <- sum(dataf$TotalCharges, na.rm = TRUE)
+print(sum_of_charges)
+

Q15.R

@@ -0,0 +1,10 @@
+#Question 15
+dataf$TotalCharges<-as.numeric(as.character(dataf$TotalCharges))
+consult_amount <- dataf%>%
+  select(Procedure,TotalCharges) %>%
+  group_by(Procedure) %>%
+  filter(Procedure == 'Consultation') %>%
+  summarise(sum(TotalCharges,na.rm=TRUE)) %>%
+  print
+
+

Q16.R

@@ -0,0 +1,3 @@
+#Question 16
+cor(dataf$Age,dataf$Age)
+

Q17.R

@@ -0,0 +1,35 @@
+#Question 17
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("C:/Users/umair.hanif/Desktop/Learning Outcomes/AR/hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))
+
+visits_by_age <- dataf %>%
+  select(id,Age) %>%
+  group_by(Age) %>%
+  summarize(visits=length(Age)) %>%
+  arrange(desc(visits)) %>%
+  filter(!is.na(Age)) %>%
+  print
+
+ggplot(data=visits_by_age,aes(x=as.numeric(Age),y=visits))+geom_bar(stat='identity',fill='slate blue')+ggtitle("Visits By Age")+labs(x='Age',y='Visits')
+

Q18.R

@@ -0,0 +1,3 @@
+#Question 18
+dataf$Total_Charges<-as.numeric(dataf$Total_Charges)
+sum(dataf$Total_Charges[dataf$Procedure=="X Ray" | dataf$Procedure=="Scalling"],na.rm = TRUE)

Q2.R

@@ -0,0 +1,10 @@
+#Question 2
+day_visits <-  dataf %>%
+  mutate(Day=weekdays(dataf$Date),label=TRUE) %>%
+  group_by(Day) %>%
+  summarize(visits=length(Day)) %>%
+  print
+
+ggplot(day_visits,aes(x=Day,y=visits))+geom_bar(stat="identity",fill="slateblue")+ggtitle("Visits per Weekday")+labs(x="Day",y="Visits")
+
+

Q3.R

@@ -0,0 +1,2 @@
+#Question 3
+mean(dataf$Age, na.rm = TRUE)

Q4.R

@@ -0,0 +1,7 @@
+#Question 4
+child <- filter(dataf, Age > 1 & Age < 13) %>%
+  select(-(Date:Time)) %>%
+  select(-(Sex:NextApt)) %>%
+  count() %>%
+  print
+

Q5.R

@@ -0,0 +1,31 @@
+#Question 5
+#Repeating previous code snippet
+
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("C:/Users/umair.hanif/Desktop/Learning Outcomes/AR/hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))
+
+
+dataf$Sex <- gsub("f","F",dataf$Sex)
+dataf$Sex<-gsub("\\s|-",NA,dataf$Sex)
+qplot(data=dataf, Sex, fill=Procedure)+ggtitle("Procedure vs Gender")+labs(x='Gender',y='Procedure')

Q6.R

@@ -0,0 +1,29 @@
+#Question 6
+#Repeating previous code snippet
+
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("C:/Users/umair.hanif/Desktop/Learning Outcomes/AR/hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))
+
+
+qplot(data=dataf, fill=ConsultingDoctor, as.numeric(TotalCharges))+ggtitle("Highest Earning")+labs(x='TotalCharges',y='ConsultingDoctor')

Q7.R

@@ -0,0 +1,28 @@
+#Question 7
+#Repeating previous code snippet
+
+library("ggplot2")
+library("lubridate")
+library("dplyr")
+library("tidyr")
+library("DataCombine")
+
+bufferedDataFrame <- read.csv("C:/Users/umair.hanif/Desktop/Learning Outcomes/AR/hospitaldata.csv", strip.white = T, na.strings = c("-",""," ","\t","\n",NA), stringsAsFactors = F)
+dataf <- tbl_df(bufferedDataFrame)
+View(dataf)
+glimpse(dataf)
+
+#removing character from age M
+dataf$Age <- as.numeric(gsub("[^0-9]",'',dataf$Age))
+class(dataf$Age)
+unique(dataf$Age)
+
+
+# Question #1 
+#Changing Datatypes from factor to their required formats
+names(dataf) <- gsub("\\.",'',names(dataf))
+
+#now lets play with date
+dataf$Date <- as.Date(strptime(dataf$Date, "%a, %B %d, %Y"))
+
+qplot(data=dataf, as.numeric(TotalCharges), fill=Procedure)+ggtitle("Highest Procedure")+labs(x='TotalCharges',y='Procedure')

Q8.R

@@ -0,0 +1,10 @@
+#Question 8
+hour_visits <-  dataf %>%
+  select(Time) %>%
+  mutate(Hour = hour(hm(format(strptime(dataf$Time, "%I:%M %p"), "%H:%M")))) %>%
+  group_by(Hour) %>%
+  summarize(visits=length(Hour)) %>%
+  arrange(desc(visits)) %>%
+  print     # printing 13 the highest hour, i.e. actaully 1 AM/PM in 12 hour format
+
+