cleaning

Author: thuy2020

.gitignore

@@ -2,5 +2,4 @@
 .Rhistory
 .RData
 .Ruserdata
-data
 querydata_from_postgresQL.Rmd

acfrs_nces_school_discts.csv

@@ -1,18 +1,26 @@
 ---
-title: "Comparing ACFRS data with Census Data"
-output: 
+title: "Data Summary Statistics"
+date: June 11, 2022
+output:
   html_document:
     toc: true
     toc_float: true
-    toc_depth: 2
+    toc_depth: 3
 ---
 
 ```{r setup, include=FALSE}
 knitr::opts_chunk$set(echo = FALSE, warning = FALSE, message = FALSE)
 library(tidyverse)
+library(dplyr)
+library(purrr)
+library(kableExtra)
+options(scipen=999)
 ```
 
-## Read in ACFRS data
+
+##ACFRS Data
+Data was downloaded from website on Jan 11. Filtered out "Non-profit" category
+
 ```{r}
 options(scipen=999)
 jan11_site <- rio::import(here::here("data", "CAFRdata_20220111_221828.xlsx"))
@@ -21,19 +29,17 @@ jan11_site %>%
   select(State, Entity, Category,
     `Net Pension Liability`, `Net OPEB Assets`, `Net OPEB Liability`, `Bonds Outstanding`, `Notes Outstanding`, 
      Leases, `Loans Outstanding`, `Compensated Absences`, `Total Liabilities`, Revenues) -> d
+head(d)
 
-d %>% head()
 ```
 
-
-## Read in census data
-
+## Compare with Census Data
 The Census Bureau has national and state debt totals here:
 https://www2.census.gov/programs-surveys/gov-finances/tables/2019/19slsstab1a.xlsx
 and here:
 https://www2.census.gov/programs-surveys/gov-finances/tables/2019/19slsstab1b.xlsx.
 
-The excel files have 5 components for each state. The column used below is "state & local government amount"
+The excel files has 5 components for each state. The column used below is "state & local government amount"
 
 ```{r}
 # first half
@@ -60,15 +66,18 @@ filter(`...1` == "125") %>%
 # joining 
 state_local_amount_census <- rbind(state_local_amount1, state_local_amount2) 
 
+state_local_amount_census
 
 ```
-Census Debt Outstanding
 
+Getting state.abb column 
 ```{r}
-#Getting state.abb column to join with acfrs data later
+
+left_join(state_local_amount_census, state_abb)
 state_name_abb <- data.frame(state.abb, state.name) %>% 
   rename("Name" = state.name)
-dc <- c("DC", "District of Columbia") # state.abb in R does not have DC
+
+dc <- c("DC", "District of Columbia")
 
 rbind(dc, state_name_abb) %>% 
   arrange(Name) -> foo1
@@ -80,11 +89,9 @@ state_local_amount_census %>%
 
 debt_outstanding_census <- cbind(foo1, foo2) %>% select(-State) %>% 
   rename("State" = state.abb)
-
-debt_outstanding_census
 ```
 
-## Compute sum of `Bonds Outstanding`, `Notes Outstanding`, Leases by state
+Compute sum of `Bonds Outstanding`, `Notes Outstanding`, `Leases` by state
 
 ```{r}
 d %>% 
@@ -97,18 +104,14 @@ d %>%
   acfrs_debt
 ```
 
-Joining & Comparing census and ACFRS data
-
 ```{r}
 acfrs_debt %>% 
-  left_join(debt_outstanding_census) -> comparing_census_acfrs
-comparing_census_acfrs
-#write_csv(comparing_census_acfrs, "comparing_census_acfrs.csv")
-```
-
-
-
-
-
+  left_join(debt_outstanding_census) %>% 
+  mutate(ratio = state_sum_bonds_notes_leases - debt_outstanding_census)
 
+debt_outstanding_census %>% 
+  as_tibble()  %>% 
+  as.double(debt_outstanding_census)
+map_dbl(sum)
+```