INTERVIEW

Question 1

001030(42010): syntax error line 3 at position 14 unexpected ‘(’

If this error message popped up, I would go to line 3 of my code and look 14 placeholders over. This is where the parenthesis is that I do not need. Since it says unexpected, I know that I have to delete it.

#QUESTION 2

sales = read.csv("https://raw.githubusercontent.com/connormckee1323/Interview/main/sales.csv", header= TRUE)
sample_dx = read.csv("https://raw.githubusercontent.com/connormckee1323/Interview/main/sample_dx.csv",  header=TRUE)

# Convert DATE column to Date format
library(zoo)

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

 sales$DATE <- as.Date(sales$DATE)
 
 # Create a new column with the quarter information for each observation
 sales$QUARTER <- quarter(sales$DATE)
 
 # Calculate quarterly totals by INDICATION
 totals <- aggregate(TOTAL_TRX ~ INDICATION + QUARTER, sales, sum)
 
 
 
 # Plot quarterly trends for each INDICATION
 library(ggplot2)
 ggplot(totals, aes(x = QUARTER, y = TOTAL_TRX)) + 
   geom_line(aes(color = INDICATION)) + 
   geom_line(aes(x = QUARTER, y = TOTAL_TRX, color = INDICATION)) + 
   geom_line(aes(x = QUARTER, y = TOTAL_TRX, color = INDICATION)) + 
   geom_line(aes(x = QUARTER, y = TOTAL_TRX, color = INDICATION)) + 
   geom_point(aes(x = QUARTER, y = TOTAL_TRX, color = INDICATION))

   labs(x = "Quarter", y = "Total TRX", color = "INDICATION") +
   theme_classic()

## NULL

QUESTION 3

sample_dx$group <- ifelse(sample_dx$claim_code %in% c("C83.0", "C83.00", "C83.01", "C83.02", "C83.03"), "A", 
                         ifelse(sample_dx$claim_code %in% c("C91", "C91.1", "C91.10", "C91.11", "C91.12"), "B", 
                                ifelse(sample_dx$claim_code %in% c("C95.10", "C95.90"), "C", "Other")))

library(dplyr)

## 
## 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

# Convert service_date to a date format
sample_dx$service_date <- as.Date(sample_dx$service_date, "%m/%d/%Y")

# Create a new column with the month of service_date
sample_dx$service_month <- format(sample_dx$service_date, "%Y-%m")

# Group the data by patient_id and service_month, and count the number of occurrences of each group
group_counts <- sample_dx %>%
  group_by(patient_id, service_month) %>%
  summarize(
    group_a_count = sum(group == "A"),
    group_b_count = sum(group == "B"),
    group_c_count = sum(group == "C")
  ) %>%
  ungroup()

## `summarise()` has grouped output by 'patient_id'. You can override using the
## `.groups` argument.

# Identify the patients with group A and B in the same month
ab_patients <- group_counts %>%
  filter(group_a_count > 0 & group_b_count > 0) %>%
  pull(patient_id)

# Identify the patients with group A and C in the same month
ac_patients <- group_counts %>%
  filter(group_a_count > 0 & group_c_count > 0) %>%
  pull(patient_id)

# Identify the patients with group B and C in the same month
bc_patients <- group_counts %>%
  filter(group_b_count > 0 & group_c_count > 0) %>%
  pull(patient_id)

# Print the results
cat("Patients with group A and B in the same month:", ab_patients, "\n")

## Patients with group A and B in the same month: 24321378 44938854 54792674 91611815 92208622 92208622 95998814 116677814 211436602 211866978 226661383 226661383 245078195 262784446 364485857 415411270 428329273 469983145 476104679 477492718 478406690 497266313 499062785 559816850 560182995 572701858 574216057 602544578 624660413 664471435 664471435 668668377 677614248 677614248 683898193 699289592 739096758 750954404 751373650 821493499 870789126 883766629 1010667933 1013619094 1048169483 1078909035 1078909035 1156189250 1164373445 1164373445 1164373445 1204094164 1208471804 1209559306 1225898360 1231475243 1821452168 1834319705 1834319705 2085570418 2137618095 3731302758

cat("Patients with group A and C in the same month:", ac_patients, "\n")

## Patients with group A and C in the same month:

cat("Patients with group B and C in the same month:", bc_patients, "\n")

## Patients with group B and C in the same month: 54792674 90325967 260829988 399520205 496573704 561411274 567747008 638501844 719344277 727802087 740207043 825058508 828674993 843170598 843170598 864681159 879426584 972279881 1029954027 1031050675 1041227631 1240168147 1876707717 1876707717 2539354081 4109239709 5391985006

From our output we see 89 patients have two groups within the same month.