Solution: Help Patients

# We use the 'patients' dataset in this exercise
library(dplyr)
print(head(patients))
print('----------The details of the dataset: -----')
print(str(patients))
print('--------- The result: ----------')
# First we define the average BMI for females and males by ignoring the null values
avg_f =  mean(patients[patients$gender=='Female',]$BMI,na.rm = TRUE) # Average BMI for female patients
avg_m =  mean(patients[patients$gender=='Male',]$BMI,na.rm = TRUE)   # Average BMI for male patients
result <- patients %>% mutate(BMI = ifelse(is.na(BMI)&gender=='Female',avg_f,BMI))%>% #  Impute null values with female average
  mutate(BMI = ifelse(is.na(BMI)&gender=='Male',avg_m,BMI))%>%  #  Impute null values with male average
  mutate(fasting_glucose=as.double(fasting_glucose))%>%     # Convert the character data type into double data type
  mutate(glucose_diff = abs((fasting_glucose - mean(fasting_glucose))/sd(fasting_glucose)))%>%  #  Calculate the Z-score for each fasting glucose value and create a new column
  mutate(avg_bp = (high_bp + low_bp)/2)%>%  # Create a new column for the average blood pressure
  mutate(in_danger= ifelse(avg_bp>=100,TRUE,FALSE))%>%  # Create a binary column stating that the patient is in danger if the average blood pressure is over 110
  select(c(id,gender,BMI,fasting_glucose,glucose_diff,avg_bp,in_danger))%>% # Select the columns desired by the managers.
  filter(glucose_diff >= 2 & BMI >= 25 & in_danger == TRUE)  # Filter the patients that carry danger in the given measurements.
print(result)   # Check the patients who are in danger
print('-------- The number of rows: -------')
result<- result%>%nrow()  # Find the number of patients who needs to be care.
print(result)