+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
library(dplyr)
+
## Warning: package 'dplyr' was built under R version 3.3.3
+
##
+## Attaching package: 'dplyr'
+
## The following objects are masked from 'package:stats':
+##
+## filter, lag
+
## The following objects are masked from 'package:base':
+##
+## intersect, setdiff, setequal, union
+
library(readr)
+
## Warning: package 'readr' was built under R version 3.3.3
+
library(tidyr)
+
## Warning: package 'tidyr' was built under R version 3.3.3
+
library(lubridate)
+
## Warning: package 'lubridate' was built under R version 3.3.3
+
##
+## Attaching package: 'lubridate'
+
## The following object is masked from 'package:base':
+##
+## date
+
Hospital_data <- read.csv("E:/DIH/RWork/Assignment/hospitaldata.csv",header = TRUE, stringsAsFactors = FALSE)
+#Q1
+#View(Hospital_data)
+names(Hospital_data) <- gsub("\\." ," ", names(Hospital_data))
+#View(Hospital_data)
+
+#Q3
+Hospital_data$Age<-gsub("M" ,"", Hospital_data$Age)
+Hospital_data$Age <- as.numeric(Hospital_data$Age)
+
## Warning: NAs introduced by coercion
+
mean(Hospital_data$Age,na.rm=TRUE)
+
## [1] 32.57216
+
#Q4
+length(which(Hospital_data$Age <= 12 & Hospital_data$Age >=1))
+
## [1] 24
+
#Q5
+Hospital_data$Sex<-gsub("f" ,"F", Hospital_data$Sex)
+Hospital_data%>%
+ filter(Sex=='M')%>%
+ group_by(Procedure)%>%
+ summarize(maxi=n())%>%
+ filter(maxi==max(maxi))%>%
+ print
+
## # A tibble: 1 × 2
+## Procedure maxi
+## <chr> <int>
+## 1 Consultation 37
+
Hospital_data%>%
+ filter(Sex=='F')%>%
+ group_by(Procedure)%>%
+ summarize(maxi=n())%>%
+ filter(maxi==max(maxi))%>%
+ print
+
## # A tibble: 1 × 2
+## Procedure maxi
+## <chr> <int>
+## 1 Consultation 46
+
#Q6
+Hospital_data$`Total Charges` <- as.numeric(Hospital_data$`Total Charges`)
+
## Warning: NAs introduced by coercion
+
Hospital_data%>%
+ group_by(`Consulting Doctor`)%>%
+ summarize(high=sum(`Total Charges`, na.rm=TRUE))%>%
+ filter(high==max(high))%>%
+ print
+
## # A tibble: 1 × 2
+## `Consulting Doctor` high
+## <chr> <dbl>
+## 1 Dr Alaf Khan 513050
+
#Q7
+Hospital_data$`Total Charges` <- as.numeric(Hospital_data$`Total Charges`)
+Hospital_data%>%
+ group_by(Procedure)%>%
+ summarize(high=sum(`Total Charges`, na.rm=TRUE))%>%
+ filter(high==max(high))%>%
+ print
+
## # A tibble: 1 × 2
+## Procedure high
+## <chr> <dbl>
+## 1 Orthodontics 240000
+
#Q8
+Hospital_data$Time<-hour(strptime(Hospital_data$Time, "%I:%M %p" ))
+Hospital_data$Time
+
## [1] NA 10 12 13 14 15 15 15 15 17 17 17 13 15 18 23 12 20 20 12 14 14 12
+## [24] 13 13 NA 20 NA 12 13 14 15 17 17 15 18 NA NA 15 16 16 10 14 14 11 15
+## [47] 20 16 18 21 NA 13 18 18 11 11 13 15 18 21 12 14 17 NA 11 NA NA NA 10
+## [70] 13 13 12 13 13 16 13 13 14 13 NA NA 12 15 17 NA NA NA NA 18 21 NA 13
+## [93] 13 17 17 18 17 18 18 14 14 13 13 18 12 13 13 16 20 16 16 19 19 13 13
+## [116] 16 18 12 13 14 18 20 10 12 12 14 14 14 10 9 18 19 12 16 17 18 19 12
+## [139] 11 15 19 NA 14 15 19 11 16 18 16 17 18 18 18 11 14 NA 13 14 19 22 13
+## [162] 18 19 22 NA 15 16 17 13 13 14 15 21 15 16 11 12 NA 22 12 NA 15 20 17
+## [185] 18 NA 19 19 12 15 19 NA 11 12 13 16 17 14 NA 13 17 19 NA 15 NA 19 14
+## [208] 21 20 22 16 18 12 19 12 9 NA NA 15 18 10 23
+
Hospital_data %>%
+ filter(!is.na(Time), Time != '-') %>%
+ group_by(Time) %>%
+ summarize(timeCount = n()) %>%
+ filter(Time != '') %>%
+ filter(timeCount == max(timeCount))
+
## # A tibble: 1 × 2
+## Time timeCount
+## <int> <int>
+## 1 13 29
+
#Q10
+Hospital_data%>%
+ group_by(id)%>%
+ summarize(repeat_id=n())%>%
+ filter(repeat_id>1)%>%
+ nrow()%>%
+ print
+
## [1] 37
+
#Q11
+Hospital_data%>%
+ group_by(id)%>%
+ summarize(repeat_id=n())%>%
+ filter(repeat_id>1)%>%
+ print
+
## # A tibble: 37 × 2
+## id repeat_id
+## <int> <int>
+## 1 1 12
+## 2 4 2
+## 3 12 2
+## 4 13 2
+## 5 17 4
+## 6 20 2
+## 7 25 2
+## 8 40 2
+## 9 45 3
+## 10 46 5
+## # ... with 27 more rows
+
#Q12
+Hospital_data%>%
+ group_by(id,Procedure)%>%
+ summarize(repeat_id=n())%>%
+ filter(repeat_id>1)%>%
+ print
+
## Source: local data frame [24 x 3]
+## Groups: id [23]
+##
+## id Procedure repeat_id
+## <int> <chr> <int>
+## 1 1 Pharmacy 10
+## 2 12 22 Unit Bridge 2
+## 3 13 Consultation 2
+## 4 17 Consultation 2
+## 5 17 RCT (4 teeth) Bridge (9 teeth) 2
+## 6 20 Consultation 2
+## 7 25 Consultation 2
+## 8 45 R.P.D + Crown 2
+## 9 46 Dressing 4
+## 10 63 Consultation 2
+## # ... with 14 more rows
+
#Q13
+Hospital_data%>%
+ filter(Sex=='M')%>%
+ select(Age)%>%
+ summarize(med=median(Age,na.rm=TRUE))%>%
+ print
+
## med
+## 1 29
+
Hospital_data%>%
+ filter(Sex=='F')%>%
+ select(Age)%>%
+ summarize(med=median(Age,na.rm=TRUE))%>%
+ print
+
## med
+## 1 30
+
#Q14
+Hospital_data$`Amount Balance`<-gsub("," ,"",Hospital_data$`Amount Balance` ,fixed=TRUE)
+Hospital_data$`Amount Balance`<-gsub(".00" ,"", Hospital_data$`Amount Balance`,fixed=TRUE)
+Hospital_data$`Amount Balance` <- as.numeric(Hospital_data$`Amount Balance`)
+
## Warning: NAs introduced by coercion
+
Hospital_data%>%
+ select(`Amount Balance`)%>%
+ summarize(sum1=sum(`Amount Balance`, na.rm=TRUE))%>%
+ print
+
## sum1
+## 1 222500
+
#Q15
+Hospital_data%>%
+filter(Procedure=='Consultation')%>%
+ select(`Total Charges`)%>%
+ summarize(maxi=sum(`Total Charges`,na.rm=TRUE) )%>%
+ print
+
## maxi
+## 1 83950
+
#Q17
+Hospital_data %>%
+ filter(!is.na(Age), Age!='-') %>%
+ group_by(Age) %>%
+ summarize(AgeCount=n()) %>%
+ filter(Age!='') %>%
+ filter(AgeCount == max(AgeCount))%>%
+ print
+
## # A tibble: 1 × 2
+## Age AgeCount
+## <dbl> <int>
+## 1 30 20
+
#Q18
+Hospital_data%>%
+ filter(Procedure=='X Ray'| Procedure=='Scalling')%>%
+ select(`Total Charges`)%>%
+ summarize(maxi=sum(`Total Charges`,na.rm=TRUE) )%>%
+ print
+
## maxi
+## 1 22300
+
+
+
+
+