R-Assignment-2/Faizan_khi_R_Assignment#2/Faizan_khi_R_Assignment2.R at 71de215a8a8aadbea79cf1b471f28b8ae6eacb93 · DataIntelligenceHub/R-Assignment-2 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
library(dplyr)
library(readr)
library(tidyr)
library(lubridate)

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)
mean(Hospital_data$Age,na.rm=TRUE)

#Q4
length(which(Hospital_data$Age <= 12 & Hospital_data$Age >=1))

#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

Hospital_data%>%
  filter(Sex=='F')%>%
  group_by(Procedure)%>%
  summarize(maxi=n())%>%
  filter(maxi==max(maxi))%>%
  print

#Q6
Hospital_data$`Total  Charges` <- as.numeric(Hospital_data$`Total  Charges`)
Hospital_data%>%
  group_by(`Consulting  Doctor`)%>%
  summarize(high=sum(`Total  Charges`, na.rm=TRUE))%>%
  filter(high==max(high))%>%
  print

#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

#Q8
Hospital_data$Time<-hour(strptime(Hospital_data$Time, "%I:%M %p" ))
Hospital_data$Time
Hospital_data %>%
  filter(!is.na(Time), Time != '-') %>%
  group_by(Time) %>%
  summarize(timeCount = n()) %>%
  filter(Time != '') %>%
  filter(timeCount == max(timeCount))


#Q10
Hospital_data%>%
  group_by(id)%>%
  summarize(repeat_id=n())%>%
  filter(repeat_id>1)%>%
  nrow()%>%
  print


#Q11
Hospital_data%>%
  group_by(id)%>%
  summarize(repeat_id=n())%>%
  filter(repeat_id>1)%>%
  print

#Q12
Hospital_data%>%
  group_by(id,Procedure)%>%
  summarize(repeat_id=n())%>%
  filter(repeat_id>1)%>%
  print

#Q13
Hospital_data%>%
  filter(Sex=='M')%>%
  select(Age)%>%
  summarize(med=median(Age,na.rm=TRUE))%>%
  print

Hospital_data%>%
  filter(Sex=='F')%>%
  select(Age)%>%
  summarize(med=median(Age,na.rm=TRUE))%>%
  print

#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`)
Hospital_data%>%
  select(`Amount  Balance`)%>%
  summarize(sum1=sum(`Amount  Balance`, na.rm=TRUE))%>%
  print

#Q15
Hospital_data%>%
filter(Procedure=='Consultation')%>%
  select(`Total  Charges`)%>%
  summarize(maxi=sum(`Total  Charges`,na.rm=TRUE) )%>%
  print

#Q17
Hospital_data %>%
  filter(!is.na(Age), Age!='-') %>%
  group_by(Age) %>%
  summarize(AgeCount=n()) %>%
  filter(Age!='') %>%
  filter(AgeCount == max(AgeCount))%>%
  print


#Q18
Hospital_data%>%
  filter(Procedure=='X Ray'| Procedure=='Scalling')%>%
  select(`Total  Charges`)%>%
  summarize(maxi=sum(`Total  Charges`,na.rm=TRUE) )%>%
  print