load("/Users/abbiemckay/DataVis/project1/providerspokane.RDA")
names(providerspokane)
## [1] "National.Provider.Identifier"
## [2] "Last.Name.Organization.Name.of.the.Provider"
## [3] "First.Name.of.the.Provider"
## [4] "Middle.Initial.of.the.Provider"
## [5] "Credentials.of.the.Provider"
## [6] "Gender.of.the.Provider"
## [7] "Entity.Type.of.the.Provider"
## [8] "Street.Address.1.of.the.Provider"
## [9] "Street.Address.2.of.the.Provider"
## [10] "City.of.the.Provider"
## [11] "Zip.Code.of.the.Provider"
## [12] "State.Code.of.the.Provider"
## [13] "Country.Code.of.the.Provider"
## [14] "Provider.Type"
## [15] "Medicare.Participation.Indicator"
## [16] "Place.of.Service"
## [17] "HCPCS.Code"
## [18] "HCPCS.Description"
## [19] "HCPCS.Drug.Indicator"
## [20] "Number.of.Services"
## [21] "Number.of.Medicare.Beneficiaries"
## [22] "Number.of.Distinct.Medicare.Beneficiary.Per.Day.Services"
## [23] "Average.Medicare.Allowed.Amount"
## [24] "Average.Submitted.Charge.Amount"
## [25] "Average.Medicare.Payment.Amount"
## [26] "Average.Medicare.Standardized.Amount"
library(tidyverse)
## ── Attaching packages ─────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.2.1 ✓ purrr 0.3.3
## ✓ tibble 2.1.3 ✓ dplyr 0.8.3
## ✓ tidyr 1.0.0 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.4.0
## ── Conflicts ────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(ggplot2)
summary(providerspokane)
## National.Provider.Identifier
## Min. :1.003e+09
## 1st Qu.:1.276e+09
## Median :1.509e+09
## Mean :1.516e+09
## 3rd Qu.:1.771e+09
## Max. :1.993e+09
##
## Last.Name.Organization.Name.of.the.Provider
## PATHOLOGY ASSOCIATES MEDICAL LABORATORIES LLC: 491
## MUELLER : 109
## KING : 105
## JOHNSON : 103
## JONES : 99
## LEE : 99
## (Other) :17972
## First.Name.of.the.Provider Middle.Initial.of.the.Provider
## : 964 :3583
## MICHAEL: 630 M :1571
## JOHN : 469 J :1569
## DAVID : 434 A :1506
## ROBERT : 410 L :1299
## WILLIAM: 324 D :1273
## (Other):15747 (Other):8177
## Credentials.of.the.Provider Gender.of.the.Provider Entity.Type.of.the.Provider
## MD :7497 : 964 I:18014
## M.D. :4871 F: 5558 O: 964
## :1322 M:12456
## PA-C : 904
## ARNP : 873
## D.O. : 313
## (Other):3198
## Street.Address.1.of.the.Provider Street.Address.2.of.the.Provider
## 801 S STEVENS ST: 1663 :10058
## 122 W 7TH AVE : 1194 SUITE 200: 538
## 400 E 5TH AVE : 1176 SUITE 310: 421
## 910 W 5TH AVE : 1038 SUITE 100: 345
## 101 W 8TH AVE : 820 SUITE 700: 311
## 105 W 8TH AVE : 802 SUITE 400: 306
## (Other) :12285 (Other) : 6999
## City.of.the.Provider Zip.Code.of.the.Provider State.Code.of.the.Provider
## SPOKANE:18978 992042654: 1663 WA:18975
## 992021334: 1176 WI: 2
## 992042349: 1125 WY: 1
## 992042966: 1062
## 992042307: 702
## 992042302: 607
## (Other) :12643
## Country.Code.of.the.Provider Provider.Type
## US:18978 Diagnostic Radiology: 2414
## Internal Medicine : 1809
## Family Practice : 1541
## Physician Assistant : 1240
## Nurse Practitioner : 1214
## Hematology/Oncology : 745
## (Other) :10015
## Medicare.Participation.Indicator Place.of.Service HCPCS.Code
## N: 2 F: 6157 99213 : 820
## Y:18976 O:12821 99214 : 742
## 99204 : 316
## 99203 : 312
## 99232 : 286
## 99212 : 261
## (Other):16241
## HCPCS.Description
## Established patient office or other outpatient visit, typically 15 minutes: 820
## Established patient office or other outpatient, visit typically 25 minutes: 742
## New patient office or other outpatient visit, typically 45 minutes : 316
## New patient office or other outpatient visit, typically 30 minutes : 312
## Subsequent hospital inpatient care, typically 25 minutes per day : 286
## Established patient office or other outpatient visit, typically 10 minutes: 261
## (Other) :16241
## HCPCS.Drug.Indicator Number.of.Services Number.of.Medicare.Beneficiaries
## N:17844 Min. : 11.0 Min. : 11.0
## Y: 1134 1st Qu.: 20.0 1st Qu.: 17.0
## Median : 42.0 Median : 31.0
## Mean : 291.2 Mean : 101.8
## 3rd Qu.: 115.0 3rd Qu.: 71.0
## Max. :155972.0 Max. :70013.0
##
## Number.of.Distinct.Medicare.Beneficiary.Per.Day.Services
## Min. : 11.0
## 1st Qu.: 19.0
## Median : 39.0
## Mean : 154.1
## 3rd Qu.: 101.0
## Max. :155971.0
##
## Average.Medicare.Allowed.Amount Average.Submitted.Charge.Amount
## Min. : 0.019 Min. : 0.23
## 1st Qu.: 19.003 1st Qu.: 48.00
## Median : 56.170 Median : 132.00
## Mean : 104.731 Mean : 295.21
## 3rd Qu.: 107.572 3rd Qu.: 276.00
## Max. :29872.890 Max. :45998.00
##
## Average.Medicare.Payment.Amount Average.Medicare.Standardized.Amount
## Min. : 0.011 Min. : 0.011
## 1st Qu.: 15.498 1st Qu.: 15.990
## Median : 40.720 Median : 43.613
## Mean : 80.178 Mean : 83.320
## 3rd Qu.: 81.984 3rd Qu.: 85.360
## Max. :23420.340 Max. :21855.610
##
str(providerspokane$Place.of.Service)
## Factor w/ 2 levels "F","O": 1 1 2 2 2 2 2 2 1 2 ...
levels(providerspokane$Place.of.Service)=c("Facility","Non-Facility")
#average medicare payment at facilities and non-facilities
Place_AMPA = providerspokane%>%
group_by(Place.of.Service)%>%
summarise(mean_medicare_paid = mean(Average.Medicare.Payment.Amount))
ggplot(Place_AMPA, mapping = aes(Place.of.Service, mean_medicare_paid, fill = Place.of.Service)) +geom_bar(stat = "identity")
#average submitted charge amount for facilities and non-facilities
Place_ASCA = providerspokane%>%
group_by(Place.of.Service)%>%
summarise(mean_submitted_charge_amount = mean(Average.Submitted.Charge.Amount))
ggplot(Place_ASCA, mapping = aes(Place.of.Service, mean_submitted_charge_amount, fill = Place.of.Service)) +geom_bar(stat = "identity")
#average number of services at facilities and non facilities
Place_ANOS = providerspokane%>%
group_by(Place.of.Service)%>%
summarise(average_number_of_services = mean(Number.of.Services))
ggplot(Place_ANOS, mapping = aes(Place.of.Service,average_number_of_services, fill = Place.of.Service )) +geom_bar(stat = "identity")
#average number of beneficiary services per day at facilities and non-facilities
Place_ANBS = providerspokane%>%
group_by(Place.of.Service)%>%
summarise(average_number_of_beneficiary_services = mean(Number.of.Distinct.Medicare.Beneficiary.Per.Day.Services))
ggplot(Place_ANBS, mapping = aes(Place.of.Service,average_number_of_beneficiary_services, fill = Place.of.Service )) +geom_bar(stat = "identity")