12/6/2020
Abstract
Task 0: Loading libraries
knitr::opts_chunk$set(echo = TRUE) library(readxl) library(tidyverse)
## -- Attaching packages ------------------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4 ## v tibble 3.0.3 v dplyr 1.0.1 ## v tidyr 1.1.1 v stringr 1.4.0 ## v readr 1.3.1 v forcats 0.5.0
## -- Conflicts ---------------------------------------------------------- tidyverse_conflicts() -- ## x dplyr::filter() masks stats::filter() ## x dplyr::lag() masks stats::lag()
Task 1: Loading data
DSPN <- read_excel("C:/Users/tahma/Desktop/DSPN.xlsx")
d1 <- DSPN
head(d1)
## # A tibble: 6 x 43 ## WK_NBR WK_BEGIN_DTE WK_END_DTE NCPDP_TOKEN PHRMCY_NAME BUY_GRP_NAM NDC ## <chr> <chr> <chr> <chr> <chr> <chr> <chr> ## 1 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0007~ ## 2 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0017~ ## 3 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 1249~ ## 4 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0000~ ## 5 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0040~ ## 6 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0059~ ## # ... with 36 more variables: NDC_DESC <chr>, BRX_GRX_CD <chr>, ## # NDC_QTY_MTRC <dbl>, NDC_PKG_SZ <dbl>, NDC_CASE_PK_QTY <dbl>, MFG_NAM <chr>, ## # GCNSEQ_NBR <chr>, GCNSEQ_DESC <chr>, GCNSEQ_RTE_OF_ADMIN_DESC <chr>, ## # GCNSEQ_DSG_FORM_CD <chr>, GCNSEQ_STR_DESC <chr>, DSPN_QTY_NDC_1WK <dbl>, ## # DSPN_QTY_NDC_4WKS <dbl>, DSPN_QTY_NDC_13WKS <dbl>, ## # DSPN_QTY_NDC_26WKS <dbl>, DSPN_QTY_GCN_1WK <dbl>, DSPN_QTY_GCN_4WKS <dbl>, ## # DSPN_QTY_GCN_13WKS <dbl>, DSPN_QTY_GCN_26WKS <dbl>, ## # PURCH_QTY_NDC_1WK_MTRC <dbl>, PURCH_QTY_NDC_4WKS_MTRC <dbl>, ## # PURCH_QTY_NDC_13WKS_MTRC <dbl>, PURCH_QTY_NDC_26WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_1WK_MTRC <dbl>, PURCH_QTY_GCN_4WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_13WKS_MTRC <dbl>, PURCH_QTY_GCN_26WKS_MTRC <dbl>, ## # COGS_PRC_MTRC <dbl>, DSPN_COGS_NDC_1WK <dbl>, DSPN_COGS_NDC_4WKS <dbl>, ## # DSPN_COGS_NDC_13WKS <dbl>, DSPN_COGS_NDC_26WKS <dbl>, ## # DSPN_COGS_GCN_1WK <dbl>, DSPN_COGS_GCN_4WKS <dbl>, ## # DSPN_COGS_GCN_13WKS <dbl>, DSPN_COGS_GCN_26WKS <dbl>
Task 2: Determining Mean of Drug Prices
d2 <- d1 %>%
group_by(NDC_DESC) %>%
summarise(
mean_cogs = mean(COGS_PRC_MTRC , na.rm = T)
) %>% ungroup()
## `summarise()` ungrouping output (override with `.groups` argument)
print(d2)
## # A tibble: 74 x 2 ## NDC_DESC mean_cogs ## <chr> <dbl> ## 1 "\"ADVATE 1,801-2,400 UNIT VIAL\"" 791. ## 2 "\"ADVATE 801-1,200 UNIT VIAL\"" 1.55 ## 3 "\"ADYNOVATE 1,500 UNIT VIAL\"" 2447. ## 4 "\"HELIXATE FS 1,000 UNIT VIAL\"" 968. ## 5 "\"HELIXATE FS 2,000 UNIT VIAL\"" 1.44 ## 6 "\"KOGENATE FS 1,000 UNITS VIAL\"" 1.55 ## 7 "\"KOGENATE FS 2,000 UNIT VIAL\"" 110. ## 8 "\"KOVALTRY 2,000 UNIT KIT\"" 1.47 ## 9 "ADMELOG 100 UNIT/ML VIAL" 22.6 ## 10 "ADMELOG SOLOSTAR 100 UNIT/ML" 29.1 ## # ... with 64 more rows
Task 3 and 4: Cleaning Data
NA in COGS_PRC_MTRC is replaced with the mean of COGS_PRC and data is joined with the original data.
d3 <- inner_join(d1, d2, by = 'NDC_DESC') %>%
mutate(
COGS_PRC_MTRC = ifelse(is.na(COGS_PRC_MTRC) == T,
mean_cogs, COGS_PRC_MTRC)
)
head(d3)
## # A tibble: 6 x 44 ## WK_NBR WK_BEGIN_DTE WK_END_DTE NCPDP_TOKEN PHRMCY_NAME BUY_GRP_NAM NDC ## <chr> <chr> <chr> <chr> <chr> <chr> <chr> ## 1 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0007~ ## 2 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0017~ ## 3 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 1249~ ## 4 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0000~ ## 5 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0040~ ## 6 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0059~ ## # ... with 37 more variables: NDC_DESC <chr>, BRX_GRX_CD <chr>, ## # NDC_QTY_MTRC <dbl>, NDC_PKG_SZ <dbl>, NDC_CASE_PK_QTY <dbl>, MFG_NAM <chr>, ## # GCNSEQ_NBR <chr>, GCNSEQ_DESC <chr>, GCNSEQ_RTE_OF_ADMIN_DESC <chr>, ## # GCNSEQ_DSG_FORM_CD <chr>, GCNSEQ_STR_DESC <chr>, DSPN_QTY_NDC_1WK <dbl>, ## # DSPN_QTY_NDC_4WKS <dbl>, DSPN_QTY_NDC_13WKS <dbl>, ## # DSPN_QTY_NDC_26WKS <dbl>, DSPN_QTY_GCN_1WK <dbl>, DSPN_QTY_GCN_4WKS <dbl>, ## # DSPN_QTY_GCN_13WKS <dbl>, DSPN_QTY_GCN_26WKS <dbl>, ## # PURCH_QTY_NDC_1WK_MTRC <dbl>, PURCH_QTY_NDC_4WKS_MTRC <dbl>, ## # PURCH_QTY_NDC_13WKS_MTRC <dbl>, PURCH_QTY_NDC_26WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_1WK_MTRC <dbl>, PURCH_QTY_GCN_4WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_13WKS_MTRC <dbl>, PURCH_QTY_GCN_26WKS_MTRC <dbl>, ## # COGS_PRC_MTRC <dbl>, DSPN_COGS_NDC_1WK <dbl>, DSPN_COGS_NDC_4WKS <dbl>, ## # DSPN_COGS_NDC_13WKS <dbl>, DSPN_COGS_NDC_26WKS <dbl>, ## # DSPN_COGS_GCN_1WK <dbl>, DSPN_COGS_GCN_4WKS <dbl>, ## # DSPN_COGS_GCN_13WKS <dbl>, DSPN_COGS_GCN_26WKS <dbl>, mean_cogs <dbl>
Task 5: Determining Business logic
Purchase quantity should not be negative, as the negative value signifies the return from customers.
d4 <- d3 %>%
filter(PURCH_QTY_NDC_1WK_MTRC>=0,
PURCH_QTY_NDC_4WKS_MTRC>=0,
PURCH_QTY_NDC_13WKS_MTRC>=0,
PURCH_QTY_NDC_26WKS_MTRC>=0)
head(d4)
## # A tibble: 6 x 44 ## WK_NBR WK_BEGIN_DTE WK_END_DTE NCPDP_TOKEN PHRMCY_NAME BUY_GRP_NAM NDC ## <chr> <chr> <chr> <chr> <chr> <chr> <chr> ## 1 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0007~ ## 2 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0017~ ## 3 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 1249~ ## 4 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0000~ ## 5 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0040~ ## 6 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0059~ ## # ... with 37 more variables: NDC_DESC <chr>, BRX_GRX_CD <chr>, ## # NDC_QTY_MTRC <dbl>, NDC_PKG_SZ <dbl>, NDC_CASE_PK_QTY <dbl>, MFG_NAM <chr>, ## # GCNSEQ_NBR <chr>, GCNSEQ_DESC <chr>, GCNSEQ_RTE_OF_ADMIN_DESC <chr>, ## # GCNSEQ_DSG_FORM_CD <chr>, GCNSEQ_STR_DESC <chr>, DSPN_QTY_NDC_1WK <dbl>, ## # DSPN_QTY_NDC_4WKS <dbl>, DSPN_QTY_NDC_13WKS <dbl>, ## # DSPN_QTY_NDC_26WKS <dbl>, DSPN_QTY_GCN_1WK <dbl>, DSPN_QTY_GCN_4WKS <dbl>, ## # DSPN_QTY_GCN_13WKS <dbl>, DSPN_QTY_GCN_26WKS <dbl>, ## # PURCH_QTY_NDC_1WK_MTRC <dbl>, PURCH_QTY_NDC_4WKS_MTRC <dbl>, ## # PURCH_QTY_NDC_13WKS_MTRC <dbl>, PURCH_QTY_NDC_26WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_1WK_MTRC <dbl>, PURCH_QTY_GCN_4WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_13WKS_MTRC <dbl>, PURCH_QTY_GCN_26WKS_MTRC <dbl>, ## # COGS_PRC_MTRC <dbl>, DSPN_COGS_NDC_1WK <dbl>, DSPN_COGS_NDC_4WKS <dbl>, ## # DSPN_COGS_NDC_13WKS <dbl>, DSPN_COGS_NDC_26WKS <dbl>, ## # DSPN_COGS_GCN_1WK <dbl>, DSPN_COGS_GCN_4WKS <dbl>, ## # DSPN_COGS_GCN_13WKS <dbl>, DSPN_COGS_GCN_26WKS <dbl>, mean_cogs <dbl>
Task 6: Defining Leakage
leakage is defined as difference between Dispense qty and Purchase qty.
If Dispense is more than Purchase that signifies pharmacy is buying from outside the contract.
If Purchase is more then it signifies normal business.
d5 <- d4 %>%
mutate(
Leakage_Variable_for_1Wk = DSPN_QTY_NDC_1WK - PURCH_QTY_NDC_1WK_MTRC,
Leakage_Variable_for_4Wk = DSPN_QTY_NDC_4WKS - PURCH_QTY_NDC_4WKS_MTRC,
Leakage_Variable_for_13Wk = DSPN_QTY_NDC_13WKS - PURCH_QTY_NDC_13WKS_MTRC,
Leakage_Variable_for_26Wk = DSPN_QTY_NDC_26WKS - PURCH_QTY_NDC_26WKS_MTRC
)
head(d5)
## # A tibble: 6 x 48 ## WK_NBR WK_BEGIN_DTE WK_END_DTE NCPDP_TOKEN PHRMCY_NAME BUY_GRP_NAM NDC ## <chr> <chr> <chr> <chr> <chr> <chr> <chr> ## 1 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0007~ ## 2 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0017~ ## 3 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 1249~ ## 4 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0000~ ## 5 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0040~ ## 6 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0059~ ## # ... with 41 more variables: NDC_DESC <chr>, BRX_GRX_CD <chr>, ## # NDC_QTY_MTRC <dbl>, NDC_PKG_SZ <dbl>, NDC_CASE_PK_QTY <dbl>, MFG_NAM <chr>, ## # GCNSEQ_NBR <chr>, GCNSEQ_DESC <chr>, GCNSEQ_RTE_OF_ADMIN_DESC <chr>, ## # GCNSEQ_DSG_FORM_CD <chr>, GCNSEQ_STR_DESC <chr>, DSPN_QTY_NDC_1WK <dbl>, ## # DSPN_QTY_NDC_4WKS <dbl>, DSPN_QTY_NDC_13WKS <dbl>, ## # DSPN_QTY_NDC_26WKS <dbl>, DSPN_QTY_GCN_1WK <dbl>, DSPN_QTY_GCN_4WKS <dbl>, ## # DSPN_QTY_GCN_13WKS <dbl>, DSPN_QTY_GCN_26WKS <dbl>, ## # PURCH_QTY_NDC_1WK_MTRC <dbl>, PURCH_QTY_NDC_4WKS_MTRC <dbl>, ## # PURCH_QTY_NDC_13WKS_MTRC <dbl>, PURCH_QTY_NDC_26WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_1WK_MTRC <dbl>, PURCH_QTY_GCN_4WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_13WKS_MTRC <dbl>, PURCH_QTY_GCN_26WKS_MTRC <dbl>, ## # COGS_PRC_MTRC <dbl>, DSPN_COGS_NDC_1WK <dbl>, DSPN_COGS_NDC_4WKS <dbl>, ## # DSPN_COGS_NDC_13WKS <dbl>, DSPN_COGS_NDC_26WKS <dbl>, ## # DSPN_COGS_GCN_1WK <dbl>, DSPN_COGS_GCN_4WKS <dbl>, ## # DSPN_COGS_GCN_13WKS <dbl>, DSPN_COGS_GCN_26WKS <dbl>, mean_cogs <dbl>, ## # Leakage_Variable_for_1Wk <dbl>, Leakage_Variable_for_4Wk <dbl>, ## # Leakage_Variable_for_13Wk <dbl>, Leakage_Variable_for_26Wk <dbl>
Task 7: Computing Leakage Per Week
d6 <- d5 %>%
mutate(Leakage_perWk_for_4Wk = Leakage_Variable_for_4Wk/4,
Leakage_perWk_for_13Wk = Leakage_Variable_for_13Wk/13,
Leakage_perWk_for_26Wk = Leakage_Variable_for_26Wk/26)
head(d6)
## # A tibble: 6 x 51 ## WK_NBR WK_BEGIN_DTE WK_END_DTE NCPDP_TOKEN PHRMCY_NAME BUY_GRP_NAM NDC ## <chr> <chr> <chr> <chr> <chr> <chr> <chr> ## 1 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0007~ ## 2 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0017~ ## 3 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 1249~ ## 4 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0000~ ## 5 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0040~ ## 6 201836 2018-09-02 2018-09-08 4410677998~ PHARMACY 1~ SPURS 0059~ ## # ... with 44 more variables: NDC_DESC <chr>, BRX_GRX_CD <chr>, ## # NDC_QTY_MTRC <dbl>, NDC_PKG_SZ <dbl>, NDC_CASE_PK_QTY <dbl>, MFG_NAM <chr>, ## # GCNSEQ_NBR <chr>, GCNSEQ_DESC <chr>, GCNSEQ_RTE_OF_ADMIN_DESC <chr>, ## # GCNSEQ_DSG_FORM_CD <chr>, GCNSEQ_STR_DESC <chr>, DSPN_QTY_NDC_1WK <dbl>, ## # DSPN_QTY_NDC_4WKS <dbl>, DSPN_QTY_NDC_13WKS <dbl>, ## # DSPN_QTY_NDC_26WKS <dbl>, DSPN_QTY_GCN_1WK <dbl>, DSPN_QTY_GCN_4WKS <dbl>, ## # DSPN_QTY_GCN_13WKS <dbl>, DSPN_QTY_GCN_26WKS <dbl>, ## # PURCH_QTY_NDC_1WK_MTRC <dbl>, PURCH_QTY_NDC_4WKS_MTRC <dbl>, ## # PURCH_QTY_NDC_13WKS_MTRC <dbl>, PURCH_QTY_NDC_26WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_1WK_MTRC <dbl>, PURCH_QTY_GCN_4WKS_MTRC <dbl>, ## # PURCH_QTY_GCN_13WKS_MTRC <dbl>, PURCH_QTY_GCN_26WKS_MTRC <dbl>, ## # COGS_PRC_MTRC <dbl>, DSPN_COGS_NDC_1WK <dbl>, DSPN_COGS_NDC_4WKS <dbl>, ## # DSPN_COGS_NDC_13WKS <dbl>, DSPN_COGS_NDC_26WKS <dbl>, ## # DSPN_COGS_GCN_1WK <dbl>, DSPN_COGS_GCN_4WKS <dbl>, ## # DSPN_COGS_GCN_13WKS <dbl>, DSPN_COGS_GCN_26WKS <dbl>, mean_cogs <dbl>, ## # Leakage_Variable_for_1Wk <dbl>, Leakage_Variable_for_4Wk <dbl>, ## # Leakage_Variable_for_13Wk <dbl>, Leakage_Variable_for_26Wk <dbl>, ## # Leakage_perWk_for_4Wk <dbl>, Leakage_perWk_for_13Wk <dbl>, ## # Leakage_perWk_for_26Wk <dbl>
Task 8: Comparing Means
a) weekly average shows very less leakage maybe because of very less data to compare.
b) monthly average is maximum which might be because of selling inventory
c) Quarter data is best for analysing as inventory selling should have averaged out and report will be generated in a quarter not after half year,
d7 <- d6 %>% summarise(
Mean_1Wk = mean(Leakage_Variable_for_1Wk),
Mean_4Wk = mean(Leakage_perWk_for_4Wk),
Mean_13Wk= mean(Leakage_perWk_for_13Wk),
Mean_26Wk = mean(Leakage_perWk_for_26Wk))
head(d7)
## # A tibble: 1 x 4 ## Mean_1Wk Mean_4Wk Mean_13Wk Mean_26Wk ## <dbl> <dbl> <dbl> <dbl> ## 1 0.140 4.49 3.80 2.91
Task 9: Mapping Leakage for 13 weeks throughout the Pharmacies and Buying Groups
d8 <- d5 %>% select(PHRMCY_NAME, BUY_GRP_NAM, NDC_DESC, BRX_GRX_CD,
MFG_NAM, Leakage_Variable_for_13Wk, COGS_PRC_MTRC)
head(d8)
## # A tibble: 6 x 7 ## PHRMCY_NAME BUY_GRP_NAM NDC_DESC BRX_GRX_CD MFG_NAM Leakage_Variabl~ ## <chr> <chr> <chr> <chr> <chr> <dbl> ## 1 PHARMACY 1~ SPURS LYRICA ~ BRX PFIZER~ 900 ## 2 PHARMACY 1~ SPURS ADVAIR ~ BRX GLAXOS~ 1260 ## 3 PHARMACY 1~ SPURS SUBOXON~ BRX INDIVI~ 1040 ## 4 PHARMACY 1~ SPURS HUMALOG~ BRX ELI LI~ 170 ## 5 PHARMACY 1~ SPURS HYDROCO~ GRX MALLIN~ 2326 ## 6 PHARMACY 1~ SPURS HYDROCO~ GRX ACTAVI~ 204 ## # ... with 1 more variable: COGS_PRC_MTRC <dbl>
Task 10: Determining Leakage in Dollar Amount
There is a leakage of $446,359,418 in 13 weeks.
d9 <- d8 %>% mutate(
Dollar_Amount_Leakage = Leakage_Variable_for_13Wk * COGS_PRC_MTRC
)
head(d9)
## # A tibble: 6 x 8 ## PHRMCY_NAME BUY_GRP_NAM NDC_DESC BRX_GRX_CD MFG_NAM Leakage_Variabl~ ## <chr> <chr> <chr> <chr> <chr> <dbl> ## 1 PHARMACY 1~ SPURS LYRICA ~ BRX PFIZER~ 900 ## 2 PHARMACY 1~ SPURS ADVAIR ~ BRX GLAXOS~ 1260 ## 3 PHARMACY 1~ SPURS SUBOXON~ BRX INDIVI~ 1040 ## 4 PHARMACY 1~ SPURS HUMALOG~ BRX ELI LI~ 170 ## 5 PHARMACY 1~ SPURS HYDROCO~ GRX MALLIN~ 2326 ## 6 PHARMACY 1~ SPURS HYDROCO~ GRX ACTAVI~ 204 ## # ... with 2 more variables: COGS_PRC_MTRC <dbl>, Dollar_Amount_Leakage <dbl>
Total Leakage
Annualy leakage is four times the quaterly value, which $1,785,437,672.
Almost $1.8 Bn annual loss in expected revenue.
Total_Leakage<-sum(d9$Dollar_Amount_Leakage) print(Total_Leakage)
## [1] 446359418
Leakage by pharmacies
d10 <- d9 %>% select(PHRMCY_NAME, Dollar_Amount_Leakage) %>%
group_by(PHRMCY_NAME) %>%
summarise(
Leakage = sum(Dollar_Amount_Leakage)
)
## `summarise()` ungrouping output (override with `.groups` argument)
head(d10)
## # A tibble: 6 x 2 ## PHRMCY_NAME Leakage ## <chr> <dbl> ## 1 PHARMACY 1 884. ## 2 PHARMACY 10 -11695. ## 3 PHARMACY 100 -8273. ## 4 PHARMACY 1000 4995. ## 5 PHARMACY 1001 -68021. ## 6 PHARMACY 1002 2019171.
Percentage of total leakage per pharmacy
d11 <- d10 %>% mutate( Leakage_percent = as.integer((Leakage/446359418)*100) ) %>% filter(Leakage_percent >= 1) print(d11)
## # A tibble: 5 x 3 ## PHRMCY_NAME Leakage Leakage_percent ## <chr> <dbl> <int> ## 1 PHARMACY 1338 6945934. 1 ## 2 PHARMACY 1793 104679245. 23 ## 3 PHARMACY 2631 6647050. 1 ## 4 PHARMACY 2644 13987693. 3 ## 5 PHARMACY 536 216808755. 48
Leakage plot by pharmacy name
d12 <- d11 %>% select(-Leakage) ggplot(d12, aes(x=PHRMCY_NAME, y=Leakage_percent, fill = PHRMCY_NAME)) + geom_bar(stat = "identity", width = 0.5) + geom_text(aes(label=Leakage_percent), vjust=1.6, color="black", size=3.5)+ theme_minimal()
##
Leakage plot by buying group
## `summarise()` ungrouping output (override with `.groups` argument)
##
Leakage plot by Drug
## `summarise()` ungrouping output (override with `.groups` argument)
## Thank You