Added working note
This commit is contained in:
Alex Gebben Work
parent
7d0b23ea79
commit
b5e715400e
@ -1,3 +1,5 @@
|
||||
######################################DATA WORKING OFF OF DATA SCRIPT!!!!!!!!!!!!!!!!!!! Start there
|
||||
|
||||
#Future things to consider
|
||||
###Naughton 1 & 2 natural gas conversion
|
||||
###Add some variance in employment at TerraPower (odds of more or less)
|
||||
@ -26,7 +28,7 @@ plot(ARMA_POP,main="Lincoln County Population Forecast",xlab="Year",ylab="Popula
|
||||
DIAMOND <- c(1000,1070,1114,1101,1082,1078,1063,991,916,876,864,863,847,835,835,827,808,774,748,732,705,695,690,689,695,700,710,723,738,745,731,704,677,667,652,629,613,586,559,540,523,526,527,521,517)
|
||||
AREA_POP <- KEM+DIAMOND
|
||||
LN <- c(12177,13254,14031,14110,14111,14319,14384,13658,12875,12552,12625,12975,13124,13329,13759,14073,14206,14099,14114,14338,14621,14697,14858,15117,15539,15917,16429,17013,17629,18082,18083,17946,17822,18148,18346,18473,18766,18899,19042,19379,19658,20174,20690,20909,21000)
|
||||
NO_CITY <- c(10095,10392,10747,10944,11043)
|
||||
# NO_CITY <- c(10095,10392,10747,10944,11043)
|
||||
YEAR <- 1980:2024
|
||||
####Old data addtion:Period Ends in 1970
|
||||
#See in part http://eadiv.state.wy.us/demog_data/cntycity_hist.htm
|
||||
@ -40,7 +42,7 @@ plot(ARMA_POP,main="Lincoln County Population Forecast",xlab="Year",ylab="Popula
|
||||
A <- cbind(YEAR2,LN2) %>% as_tibble %>% rename(Population=LN2) %>% mutate(Region='Lincoln County')
|
||||
B <- cbind(YEAR2,AREA2) %>% as_tibble %>% rename(Population=AREA2) %>% mutate(Region='Kemmerer & Diamondvile')
|
||||
DATA <- rbind(A,B) %>% rename(Year=YEAR2)
|
||||
ggplot(aes(x=Year,y=Population,group=Region,color=Region),data=DATA2) +geom_line(linewidth=1.5)
|
||||
ggplot(aes(x=Year,y=Population,group=Region,color=Region),data=DATA) +geom_line(linewidth=1.5)+scale_x_continuous()+geom_vline(xintercept= 2022, linetype = "dashed", color = "red",size = 1)
|
||||
###Kemmerer ARMA
|
||||
KEM_TS <- DATA %>% filter(Year>=1980,Region=='Kemmerer & Diamondvile') %>% pull(Population) %>% ts(start=c(1980),end=c(2024),frequency=1)
|
||||
BC <- BoxCox.lambda(KEM_TS)
|
||||
|
||||
130
Scripts/Data_Load.r
Normal file
130
Scripts/Data_Load.r
Normal file
@ -0,0 +1,130 @@
|
||||
library(rvest)
|
||||
library(tidyverse)
|
||||
|
||||
|
||||
########County, Death, Birth and Migration Data
|
||||
#Data found on the page http://eadiv.state.wy.us/pop/
|
||||
PAGE <- read_html("http://eadiv.state.wy.us/pop/BirthDeathMig.htm")
|
||||
NODE <- html_element(PAGE ,"table")
|
||||
TBL <- html_table(NODE)
|
||||
|
||||
ST <- which(toupper(TBL$X1)=="ALBANY")
|
||||
END <- which(toupper(TBL$X1)=="TOTAL")
|
||||
TYPES <- TBL[ST-2,1]
|
||||
|
||||
ST_YEAR <- 1971
|
||||
ALL_DATA <- list()
|
||||
TBL <- TBL[,c(1,which(!is.na(as.numeric(TBL[ST[1],]))))]
|
||||
TBL <- TBL[,-ncol(TBL)]
|
||||
colnames(TBL) <- c("County",(ST_YEAR:(ST_YEAR+ncol(TBL)-1)))
|
||||
TBL$Type <- NA
|
||||
for(i in 1:length(ST)){
|
||||
TBL[ST[i]:END[i],"Type"]<- as.character(TYPES[i,1])
|
||||
}
|
||||
TBL[ST[2]:END[2],"Type"] <- as.character(TYPES[2,1])
|
||||
TBL$Type
|
||||
TBL <- TBL %>% filter(!is.na(Type)) %>% select(County,Type,everything())
|
||||
GROUP <- colnames(TBL)[-1:-2]
|
||||
Data <- pivot_longer(TBL,all_of(GROUP),names_to="Year",values_to="Pop_Change")
|
||||
Data$County <- ifelse(toupper(Data$County)=="TOTAL","Wyoming",Data$County)
|
||||
WY_COUNTY_DATA_SET <- pivot_wider(Data,names_from=Type,values_from=Pop_Change) %>% rename("Migration"=`Net Migration`) %>% mutate(Year=as.integer(Year),Births=parse_number(Births),Deaths=parse_number(Deaths),Migration=parse_number(Migration))
|
||||
|
||||
########################City and County Population Data 2020 to 2024
|
||||
PAGE <- read_html('http://eadiv.state.wy.us/pop/Place-24EST.htm')
|
||||
NODE <- html_element(PAGE ,"table")
|
||||
TBL <- html_table(NODE)
|
||||
|
||||
ST <- which(toupper(TBL$X1)==toupper("Albany County"))
|
||||
END <- which(toupper(TBL$X1)==toupper("Balance of Weston County"))
|
||||
|
||||
#More years than are pulled are listed to make more generic
|
||||
COLUMNS <- c(1,which(TBL[ST-2,] %in% 1970:2025))
|
||||
NAMES <- TBL[4,COLUMNS][-1]
|
||||
TBL <- TBL[ST:END,COLUMNS ]
|
||||
colnames(TBL) <- c("County",NAMES)
|
||||
|
||||
TBL <- pivot_longer(TBL,all_of(colnames(TBL)[-1]),names_to="Year",values_to="Population") %>% mutate(Year=as.integer(Year),Population=parse_number(Population))
|
||||
TBL$County <- gsub(" "," ",gsub("\n","",gsub("\r","",TBL %>% pull(County))))
|
||||
|
||||
COUNTY_POP<- TBL[grep("COUNTY",TBL %>% pull(County),ignore.case=TRUE),]
|
||||
COUNTY_POP<- COUNTY_POP[grep("Balance",COUNTY_POP%>% pull(County),invert=TRUE,ignore.case=TRUE),]
|
||||
COUNTY_POP$County <- gsub(" ","_",gsub(" County","",COUNTY_POP$County))
|
||||
CITY_POP <- TBL[sort(c(grep("County",TBL %>% pull(County),invert=TRUE,ignore.case=TRUE),grep("Balance",TBL %>% pull(County),ignore.case=TRUE))),]
|
||||
CITY_POP$County <- gsub(" ","_",gsub("Balance of","Unincorporated",gsub(" County","",gsub(" city","",gsub(" town","",CITY_POP$County,ignore.case=TRUE),ignore.case=TRUE),ignore.case=TRUE),ignore.case=TRUE))
|
||||
CITY_POP <- CITY_POP %>% rename("City"=County)
|
||||
########################City Population Data 2010 to 2020
|
||||
PAGE <- read_html('http://eadiv.state.wy.us/pop/sub-est11-19.htm')
|
||||
NODE <- html_element(PAGE ,"table")
|
||||
TBL <- html_table(NODE)
|
||||
ST <- which(toupper(TBL$X1)==toupper("Afton town, Wyoming"))
|
||||
END <- which(toupper(TBL$X1)==toupper("Yoder town, Wyoming"))
|
||||
#More years than are pulled are listed to make more generic
|
||||
COLUMNS <- c(1,which(TBL[ST-1,] %in% 1970:2025))
|
||||
NAMES <- TBL[3,COLUMNS][-1]
|
||||
TBL <- TBL[ST:END,COLUMNS ]
|
||||
colnames(TBL) <- c("City",NAMES)
|
||||
TBL <- pivot_longer(TBL,all_of(colnames(TBL)[-1]),names_to="Year",values_to="Population") %>% mutate(Year=as.integer(Year),Population=parse_number(Population))
|
||||
TBL$City <- gsub(" ","_",gsub(" $","",gsub("\r|\n| Wyoming|,| town| city","",TBL$City,ignore.case=TRUE)))
|
||||
CITY_POP <- rbind(TBL,CITY_POP)
|
||||
########################County Population Data 2010 to 2020
|
||||
PAGE <- read_html('http://eadiv.state.wy.us/pop/ctyest11-19.htm')
|
||||
NODE <- html_element(PAGE ,"table")
|
||||
TBL <- html_table(NODE)
|
||||
ST <- grep("Albany",TBL$X1)
|
||||
END <- grep("Weston",TBL$X1)
|
||||
#More years than are pulled are listed to make more generic
|
||||
COLUMNS <- c(1,which(TBL[ST-2,] %in% 1970:2025))
|
||||
NAMES <- TBL[3,COLUMNS][-1]
|
||||
TBL <- TBL[ST:END,COLUMNS ]
|
||||
colnames(TBL) <- c("County",NAMES)
|
||||
TBL <- pivot_longer(TBL,all_of(colnames(TBL)[-1]),names_to="Year",values_to="Population") %>% mutate(Year=as.integer(Year),Population=parse_number(Population))
|
||||
TBL$County <- gsub(" ","_",gsub(" "," ",gsub(" $","",gsub("\r|\n| Wyoming|,| town| city| County|\\.","",TBL$County,ignore.case=TRUE))))
|
||||
|
||||
COUNTY_POP <- rbind(TBL,COUNTY_POP)
|
||||
|
||||
########################County and City Population Data 2000 to 2010
|
||||
PAGE <- read_html('http://eadiv.state.wy.us/pop/sub-est01-09.htm')
|
||||
NODE <- html_element(PAGE ,"table")
|
||||
TBL <- html_table(NODE)
|
||||
|
||||
ST <- which(toupper(TBL$X1)==toupper("Albany County"))
|
||||
END <- which(toupper(TBL$X1)==toupper("Balance of Weston County"))
|
||||
|
||||
#More years than are pulled are listed to make more generic
|
||||
COLUMNS <- c(1,which(TBL[ST-4,] %in% 1970:2025))
|
||||
NAMES <- TBL[4,COLUMNS][-1]
|
||||
TBL <- TBL[ST:END,COLUMNS ]
|
||||
colnames(TBL) <- c("County",NAMES)
|
||||
TBL <- pivot_longer(TBL,all_of(colnames(TBL)[-1]),names_to="Year",values_to="Population") %>% mutate(Year=as.integer(Year),Population=parse_number(Population))
|
||||
TBL$County <- gsub(" "," ",gsub("\n","",gsub("\r","",TBL %>% pull(County))))
|
||||
|
||||
COUNTY_TBL <- TBL[grep("COUNTY",TBL %>% pull(County),ignore.case=TRUE),]
|
||||
COUNTY_TBL <-COUNTY_TBL[grep("Balance",COUNTY_TBL%>% pull(County),invert=TRUE,ignore.case=TRUE),]
|
||||
COUNTY_TBL$County <-gsub("_(pt.)","", gsub(" ","_",gsub(" County","",COUNTY_TBL$County)))
|
||||
|
||||
CITY_TBL <- TBL[sort(c(grep("County",TBL %>% pull(County),invert=TRUE,ignore.case=TRUE),grep("Balance",TBL %>% pull(County),ignore.case=TRUE))),]
|
||||
CITY_TBL$County <- gsub(" ","_",gsub("Balance of","Unincorporated",gsub(" County","",gsub(" city","",gsub(" town","",CITY_TBL$County,ignore.case=TRUE),ignore.case=TRUE),ignore.case=TRUE),ignore.case=TRUE))
|
||||
CITY_TBL <- CITY_TBL %>% rename("City"=County)
|
||||
CITY_POP <- rbind(CITY_TBL,CITY_POP)
|
||||
#Cleanup names
|
||||
CITY_POP$City <- gsub("LaGrange","La_Grange",CITY_POP$City)
|
||||
COUNTY_POP <- rbind(COUNTY_TBL,COUNTY_POP)
|
||||
####################County and City Population DAta for 1990-2000
|
||||
PAGE <- read_html('http://eadiv.state.wy.us/pop/c&sc90_00.htm')
|
||||
NODE <- html_element(PAGE ,"body")
|
||||
TEST <- read_table(html_text2(NODE),skip=21,skip_empty_rows=TRUE)
|
||||
TO_ADJ <- sum((!is.na(TEST[2,])))-11
|
||||
|
||||
?read_table
|
||||
?html_text2
|
||||
?html_text
|
||||
TBL <- html_table(NODE)
|
||||
TBL
|
||||
|
||||
ST <- which(toupper(TBL$X1)==toupper("Albany Cnty"))
|
||||
END <- which(toupper(TBL$X1)==toupper("Balance of Weston County"))
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user