Migration Diagrams 5/21

Migration Table

This table shows the 100 origin-destination pairs for moves with origin and desintation risk

## Rows: 33999 Columns: 22
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): fips_code, lead_county, NAME_old, NAME_new, avg_eal_tercile_old, a...
## dbl (12): archive_version_year, row_count, CBSAFP_old, CBSAFP_new, avg_eal_o...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## `summarise()` has grouped output by 'avg_eal_tercile_old', 'avg_eal_tercile_new'. You can override using the `.groups` argument.

Top 100 Moves by CBSA

avg_eal_tercile_old	avg_eal_tercile_new	cbsa_move	row_count
High	High	Los Angeles-Long Beach-Anaheim, CA to Riverside-San Bernardino-Ontario, CA	1966
High	High	Riverside-San Bernardino-Ontario, CA to Los Angeles-Long Beach-Anaheim, CA	1133
High	High	San Jose-Sunnyvale-Santa Clara, CA to San Francisco-Oakland-Berkeley, CA	894
High	High	Los Angeles-Long Beach-Anaheim, CA to Oxnard-Thousand Oaks-Ventura, CA	887
Low	Moderate	Washington-Arlington-Alexandria, DC-VA-MD-WV to Baltimore-Columbia-Towson, MD	695
High	High	San Francisco-Oakland-Berkeley, CA to San Jose-Sunnyvale-Santa Clara, CA	682
High	High	Oxnard-Thousand Oaks-Ventura, CA to Los Angeles-Long Beach-Anaheim, CA	628
Moderate	Low	Baltimore-Columbia-Towson, MD to Washington-Arlington-Alexandria, DC-VA-MD-WV	500
Outside	Low	Boulder, CO to Denver-Aurora-Lakewood, CO	465
Moderate	Moderate	Boston-Cambridge-Newton, MA-NH to Worcester, MA-CT	419
Low	Moderate	Durham-Chapel Hill, NC to Raleigh-Cary, NC	414
Outside	High	Trenton-Princeton, NJ to New York-Newark-Jersey City, NY-NJ-PA	403
Moderate	Moderate	Boston-Cambridge-Newton, MA-NH to Providence-Warwick, RI-MA	398
High	Moderate	New Haven-Milford, CT to Hartford-East Hartford-Middletown, CT	387
Outside	High	Naples-Marco Island, FL to Cape Coral-Fort Myers, FL	387
Outside	Moderate	Ann Arbor, MI to Detroit-Warren-Dearborn, MI	387
Moderate	Low	Raleigh-Cary, NC to Durham-Chapel Hill, NC	368
Moderate	Moderate	Worcester, MA-CT to Boston-Cambridge-Newton, MA-NH	362
Moderate	High	Hartford-East Hartford-Middletown, CT to New Haven-Milford, CT	344
High	High	Bridgeport-Stamford-Norwalk, CT to New Haven-Milford, CT	337
High	High	New York-Newark-Jersey City, NY-NJ-PA to Philadelphia-Camden-Wilmington, PA-NJ-DE-MD	326
Moderate	Moderate	Providence-Warwick, RI-MA to Boston-Cambridge-Newton, MA-NH	325
High	High	San Diego-Chula Vista-Carlsbad, CA to Los Angeles-Long Beach-Anaheim, CA	317
Moderate	Low	Akron, OH to Cleveland-Elyria, OH	306
High	High	San Francisco-Oakland-Berkeley, CA to Los Angeles-Long Beach-Anaheim, CA	305
High	High	Los Angeles-Long Beach-Anaheim, CA to San Diego-Chula Vista-Carlsbad, CA	297
Low	Moderate	Cleveland-Elyria, OH to Akron, OH	289
High	Moderate	Salt Lake City, UT to Provo-Orem, UT	281
Outside	Low	Gainesville, GA to Atlanta-Sandy Springs-Alpharetta, GA	279
High	Moderate	Houston-The Woodlands-Sugar Land, TX to Dallas-Fort Worth-Arlington, TX	273
High	High	Orlando-Kissimmee-Sanford, FL to Deltona-Daytona Beach-Ormond Beach, FL	265
High	Moderate	New York-Newark-Jersey City, NY-NJ-PA to Poughkeepsie-Newburgh-Middletown, NY	264
High	High	New Haven-Milford, CT to Bridgeport-Stamford-Norwalk, CT	254
High	High	Philadelphia-Camden-Wilmington, PA-NJ-DE-MD to New York-Newark-Jersey City, NY-NJ-PA	252
High	Moderate	Salt Lake City, UT to Ogden-Clearfield, UT	241
Moderate	High	Dallas-Fort Worth-Arlington, TX to Houston-The Woodlands-Sugar Land, TX	238
Outside	Moderate	Manchester-Nashua, NH to Boston-Cambridge-Newton, MA-NH	238
Moderate	High	Ogden-Clearfield, UT to Salt Lake City, UT	235
Moderate	High	Provo-Orem, UT to Salt Lake City, UT	235
Outside	High	Santa Cruz-Watsonville, CA to San Jose-Sunnyvale-Santa Clara, CA	232
Moderate	Low	Colorado Springs, CO to Denver-Aurora-Lakewood, CO	231
Moderate	Low	Dayton-Kettering, OH to Cincinnati, OH-KY-IN	214
Low	Moderate	Denver-Aurora-Lakewood, CO to Colorado Springs, CO	211
High	High	Tucson, AZ to Phoenix-Mesa-Chandler, AZ	206
High	High	San Diego-Chula Vista-Carlsbad, CA to Riverside-San Bernardino-Ontario, CA	203
High	High	Los Angeles-Long Beach-Anaheim, CA to San Francisco-Oakland-Berkeley, CA	199
Moderate	Low	Greensboro-High Point, NC to Winston-Salem, NC	189
High	High	Deltona-Daytona Beach-Ormond Beach, FL to Orlando-Kissimmee-Sanford, FL	184
Outside	High	Port St. Lucie, FL to Miami-Fort Lauderdale-Pompano Beach, FL	183
Low	Moderate	Winston-Salem, NC to Greensboro-High Point, NC	182
Moderate	High	Poughkeepsie-Newburgh-Middletown, NY to New York-Newark-Jersey City, NY-NJ-PA	181
High	High	San Francisco-Oakland-Berkeley, CA to Sacramento-Roseville-Folsom, CA	177
High	High	New York-Newark-Jersey City, NY-NJ-PA to Miami-Fort Lauderdale-Pompano Beach, FL	173
High	Moderate	New York-Newark-Jersey City, NY-NJ-PA to Allentown-Bethlehem-Easton, PA-NJ	170
Outside	Moderate	Spartanburg, SC to Greenville-Anderson, SC	159
Low	Moderate	Cincinnati, OH-KY-IN to Dayton-Kettering, OH	157
Moderate	Moderate	Austin-Round Rock-Georgetown, TX to San Antonio-New Braunfels, TX	156
High	High	Riverside-San Bernardino-Ontario, CA to San Diego-Chula Vista-Carlsbad, CA	152
Outside	High	Reading, PA to Philadelphia-Camden-Wilmington, PA-NJ-DE-MD	150
Outside	Moderate	Flint, MI to Detroit-Warren-Dearborn, MI	150
High	High	Bridgeport-Stamford-Norwalk, CT to New York-Newark-Jersey City, NY-NJ-PA	148
Outside	High	Salem, OR to Portland-Vancouver-Hillsboro, OR-WA	146
Outside	High	Santa Rosa-Petaluma, CA to San Francisco-Oakland-Berkeley, CA	145
Outside	Low	Glens Falls, NY to Albany-Schenectady-Troy, NY	141
High	High	Los Angeles-Long Beach-Anaheim, CA to New York-Newark-Jersey City, NY-NJ-PA	140
High	High	Miami-Fort Lauderdale-Pompano Beach, FL to Orlando-Kissimmee-Sanford, FL	139
Low	Moderate	Nashville-Davidson–Murfreesboro–Franklin, TN to Charlotte-Concord-Gastonia, NC-SC	139
Outside	High	Vallejo, CA to San Francisco-Oakland-Berkeley, CA	138
Outside	High	Modesto, CA to Stockton, CA	136
High	High	Miami-Fort Lauderdale-Pompano Beach, FL to Tampa-St. Petersburg-Clearwater, FL	128
Moderate	High	Allentown-Bethlehem-Easton, PA-NJ to New York-Newark-Jersey City, NY-NJ-PA	127
High	High	Orlando-Kissimmee-Sanford, FL to Miami-Fort Lauderdale-Pompano Beach, FL	125
High	High	Sacramento-Roseville-Folsom, CA to San Francisco-Oakland-Berkeley, CA	125
Moderate	Moderate	Austin-Round Rock-Georgetown, TX to Dallas-Fort Worth-Arlington, TX	125
Outside	High	Bremerton-Silverdale-Port Orchard, WA to Seattle-Tacoma-Bellevue, WA	125
Outside	High	Torrington, CT to New Haven-Milford, CT	125
High	High	New York-Newark-Jersey City, NY-NJ-PA to Bridgeport-Stamford-Norwalk, CT	124
High	High	Orlando-Kissimmee-Sanford, FL to Lakeland-Winter Haven, FL	124
Moderate	High	Allentown-Bethlehem-Easton, PA-NJ to Philadelphia-Camden-Wilmington, PA-NJ-DE-MD	122
Outside	Low	Greeley, CO to Denver-Aurora-Lakewood, CO	122
Outside	Moderate	Holland, MI to Grand Rapids-Kentwood, MI	122
High	High	Lakeland-Winter Haven, FL to Orlando-Kissimmee-Sanford, FL	121
Outside	Low	Indiana, PA to Pittsburgh, PA	121
Outside	Moderate	Sherman-Denison, TX to Dallas-Fort Worth-Arlington, TX	121
Outside	High	Trenton-Princeton, NJ to Philadelphia-Camden-Wilmington, PA-NJ-DE-MD	119
Moderate	Low	Greenville-Anderson, SC to Atlanta-Sandy Springs-Alpharetta, GA	118
Outside	High	Punta Gorda, FL to North Port-Sarasota-Bradenton, FL	118
Outside	Moderate	Canton-Massillon, OH to Akron, OH	116
High	High	North Port-Sarasota-Bradenton, FL to Tampa-St. Petersburg-Clearwater, FL	110
High	High	Phoenix-Mesa-Chandler, AZ to Tucson, AZ	110
High	High	Tampa-St. Petersburg-Clearwater, FL to North Port-Sarasota-Bradenton, FL	108
High	Moderate	New Orleans-Metairie, LA to Baton Rouge, LA	108
Moderate	Moderate	San Antonio-New Braunfels, TX to Austin-Round Rock-Georgetown, TX	108
Outside	Moderate	Barnstable Town, MA to Boston-Cambridge-Newton, MA-NH	104
High	High	San Jose-Sunnyvale-Santa Clara, CA to Los Angeles-Long Beach-Anaheim, CA	103
Outside	Moderate	Kingston, NY to Poughkeepsie-Newburgh-Middletown, NY	103
High	Moderate	Houston-The Woodlands-Sugar Land, TX to Austin-Round Rock-Georgetown, TX	102
Outside	High	The Villages, FL to Orlando-Kissimmee-Sanford, FL	102
High	High	New York-Newark-Jersey City, NY-NJ-PA to Los Angeles-Long Beach-Anaheim, CA	100
High	Moderate	Los Angeles-Long Beach-Anaheim, CA to Dallas-Fort Worth-Arlington, TX	100

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

Moves by Tercile, rows (old), columns (new)

avg_eal_tercile_old	High	Low	Moderate
High	17264	1766	4423
Low	1821	1964	3936
Moderate	3697	3639	4162
NA	8472	7714	8221

Bar Charts

This chunk produces bar graphs for all 100 CBSAs and corresponding entries/exits and births/deaths for all years of data

library(ggpattern)
data <- read_csv("cbsa_births_deaths_exits_entrys.csv")

## Rows: 1000 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): NAME, avg_eal_tercile
## dbl (8): archive_version_year, CBSAFP, entry, exit, births, deaths, avg_eal,...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

summary(data)

##  archive_version_year     CBSAFP          entry             exit       
##  Min.   :2013         Min.   :10420   Min.   :  1.00   Min.   :  1.00  
##  1st Qu.:2015         1st Qu.:19348   1st Qu.: 26.00   1st Qu.: 25.00  
##  Median :2018         Median :32060   Median : 45.00   Median : 44.00  
##  Mean   :2018         Mean   :30209   Mean   : 67.08   Mean   : 67.08  
##  3rd Qu.:2020         3rd Qu.:40080   3rd Qu.: 84.00   3rd Qu.: 79.00  
##  Max.   :2022         Max.   :49340   Max.   :561.00   Max.   :670.00  
##                                                        NA's   :100     
##      births           deaths           NAME              avg_eal     
##  Min.   :  1328   Min.   :  1128   Length:1000        Min.   :38.21  
##  1st Qu.:  3617   1st Qu.:  3416   Class :character   1st Qu.:65.60  
##  Median :  6166   Median :  5294   Mode  :character   Median :75.28  
##  Mean   : 12411   Mean   : 10836                      Mean   :77.28  
##  3rd Qu.: 13648   3rd Qu.: 11576                      3rd Qu.:94.11  
##  Max.   :171670   Max.   :139494                      Max.   :99.91  
##                   NA's   :100                                        
##     tercile     avg_eal_tercile   
##  Min.   :1.00   Length:1000       
##  1st Qu.:1.00   Class :character  
##  Median :2.00   Mode  :character  
##  Mean   :1.99                     
##  3rd Qu.:3.00                     
##  Max.   :3.00                     
## 

data <- data %>% gather(type,row_count, c(entry,exit,births,deaths)) %>%
  group_by(NAME,avg_eal_tercile,tercile,type) %>%
  summarise(row_count=sum(row_count,na.rm = TRUE)) %>%
  mutate(label= paste0(type,"-",avg_eal_tercile))

## `summarise()` has grouped output by 'NAME', 'avg_eal_tercile', 'tercile'. You
## can override using the `.groups` argument.

color_ramp <- c("births-Low" = "#00b100", "births-Moderate" = "#007e00", "births-High" = "#004b00",
          "deaths-Low" = "#c600c6", "deaths-Moderate" = "#9f009f", "deaths-High" = "#780078")
data %>%
  filter(type %in% c("births", "deaths")) %>%
  group_by(NAME) %>%
  mutate(sort = sum(row_count,na.rm = T)) %>%
  ungroup() %>%
  ggplot(aes(x = fct_reorder(NAME, sort), y = row_count, fill = label)) + 
  geom_bar(position = "dodge", stat = "identity")+
  coord_flip()+
  theme_minimal()+
  scale_fill_manual(values=color_ramp)+
  ggtitle("Births and Deaths - 2013-2022")+
  theme(legend.position = "bottom")

color_ramp <- c("entry-Low" = "#00b100", "entry-Moderate" = "#007e00", "entry-High" = "#004b00",
          "exit-Low" = "#c600c6", "exit-Moderate" = "#9f009f", "exit-High" = "#780078")
data %>% filter(type %in% c("entry","exit")) %>%
  group_by(NAME) %>%
  mutate(sort = sum(row_count,na.rm = T)) %>%
  ungroup() %>%
  ggplot(aes(fill = label, y = row_count, x = forcats::fct_reorder(NAME, sort))) + 
  geom_bar(position = "dodge", stat = "identity")+
  coord_flip()+
  theme_minimal()+
  scale_fill_manual(values=color_ramp)+
  ggtitle("Entries and Exits - 2013-2022")+
  theme(legend.position = "bottom")

## Chord This chunk produces chord diagrams for flows between the top 100 CBSAs.

regions <- read_csv("top100_regions.csv") %>%
  mutate(GEOID =as.character(GEOID)) %>%
  select(GEOID, Region)

## Rows: 100 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): pop_tercile, NAME, Region
## dbl (1): GEOID
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

top100_cbsa <- get_acs(geography = "cbsa", variables = c(pop="B01001_001"),output = "wide") %>%
  top_n(100,popE) %>%
  mutate(pop_tercile = ntile(popE, 3)) %>%
  mutate(pop_tercile=as_factor(pop_tercile)) %>%
  mutate(pop_tercile = factor(pop_tercile, levels = 1:3, labels = c("Pop: Low", "Pop: Moderate", "Pop: High"))) %>% 
  select(pop_tercile,popE,GEOID) %>%
  left_join(regions)

## Getting data from the 2018-2022 5-year ACS
## Joining with `by = join_by(GEOID)`

top100_cbsa_new <- top100_cbsa %>%
  rename_with(~paste0(., "_new"), everything())
top100_cbsa_old <- top100_cbsa %>%
  rename_with(~paste0(., "_old"), everything())

moves <- read_csv("migration_map.csv") %>%
  select(CBSAFP_old,CBSAFP_new,NAME_old,NAME_new,row_count,avg_eal_tercile_old,avg_eal_tercile_new) %>%
  mutate(CBSAFP_old=as.character(CBSAFP_old)) %>%
  mutate(CBSAFP_new=as.character(CBSAFP_new)) %>%
  mutate(NAME_old=ifelse(is.na(avg_eal_tercile_old),"Outside",NAME_old)) %>%
  mutate(NAME_new=ifelse(is.na(avg_eal_tercile_new),"Outside",NAME_new)) %>%
  group_by(CBSAFP_old,CBSAFP_new,NAME_old,NAME_new,avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count)) %>%
  left_join(top100_cbsa_old, by=c("CBSAFP_old"="GEOID_old")) %>%
  left_join(top100_cbsa_new, by=c("CBSAFP_new"="GEOID_new")) %>%
  mutate(avg_eal_tercile_old=ifelse(is.na(avg_eal_tercile_old),"Outside",avg_eal_tercile_old)) %>%
  mutate(avg_eal_tercile_new=ifelse(is.na(avg_eal_tercile_new),"Outside",avg_eal_tercile_new)) %>%
  mutate(Region_old=ifelse(is.na(Region_old),"Outside",Region_old)) %>%
  mutate(Region_new=ifelse(is.na(Region_new),"Outside",Region_new))

## Rows: 63970 Columns: 22
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): fips_code, lead_county, NAME_old, NAME_new, avg_eal_tercile_old, a...
## dbl (12): archive_version_year, row_count, CBSAFP_old, CBSAFP_new, avg_eal_o...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## `summarise()` has grouped output by 'CBSAFP_old', 'CBSAFP_new', 'NAME_old', 'NAME_new', 'avg_eal_tercile_old'. You can override using the `.groups` argument.

data <- moves %>%
  group_by(NAME_old,NAME_new) %>%
  summarise(row_count=sum(row_count))

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

#standardize color  
    
chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow")

data <- moves %>%
  group_by(NAME_old,NAME_new) %>%
  summarise(row_count=sum(row_count)) %>%
  filter(row_count>150)

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow")
title("> 150 flows", cex.main = 1)

data <- moves %>%
  group_by(NAME_old,NAME_new) %>%
  summarise(row_count=sum(row_count)) %>%
  filter(row_count>250)

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow")
title("> 250 flows", cex.main = 1)

data <- moves %>%
  group_by(NAME_old,NAME_new) %>%
  summarise(row_count=sum(row_count)) %>%
  filter(row_count>500)

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow")
title("> 500 flows", cex.main = 1)

#region
data <- moves %>%
  group_by(Region_old,Region_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow")
title("Region", cex.main = 1)

#region
data <- moves %>%
  group_by(Region_old,Region_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow")
title("Region", cex.main = 1)

#rsame region egion
data <- moves %>%
  filter(Region_old==Region_new) %>%
  filter(Region_old!="Outside") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
    grid.col = c(High="red",Moderate="yellow", Low="green"))
title("Moves within Region", cex.main = 1)

data <- moves %>%
  filter(Region_old!=Region_new) %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
    grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Moves outside Region", cex.main = 1)

This chunk produces the chord diagrams by risk level and segmented by origin/destination population

data <- moves %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Risk level to Risk level", cex.main = 1)

#start pop low
data <- moves %>%
  filter(pop_tercile_new=="Pop: Low") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:Low - Risk level to Risk level", cex.main = 1)

#start pop medium
data <- moves %>%
  filter(pop_tercile_new=="Pop: Moderate") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:Moderate - Risk level to Risk level", cex.main = 1)

#start pop high
data <- moves %>%
  filter(pop_tercile_new=="Pop: High") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:High - Risk level to Risk level", cex.main = 1)

#start pop low
data <- moves %>%
  filter(pop_tercile_old=="Pop: Low") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:Low - Risk level to Risk level", cex.main = 1)

#start pop medium
data <- moves %>%
  filter(pop_tercile_old=="Pop: Moderate") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:Moderate - Risk level to Risk level", cex.main = 1)

#start pop high
data <- moves %>%
  filter(pop_tercile_old=="Pop: High") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:High - Risk level to Risk level", cex.main = 1)

### Chord - Risk and Population This chunk produces the chord diagrams for in-region moves by risk level and segmented by origin/destination population

data <- moves %>%
  filter(Region_old==Region_new) %>%
  filter(Region_old!="Outside") %>%
  filter(Region_new!="Outside") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Risk level to Risk level", cex.main = 1)

#start pop low
data <- moves %>%
  filter(pop_tercile_new=="Pop: Low") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:Low - Risk level to Risk level", cex.main = 1)

#start pop medium
data <- moves %>%
  filter(pop_tercile_new=="Pop: Moderate") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:Moderate - Risk level to Risk level", cex.main = 1)

#start pop high
data <- moves %>%
  filter(pop_tercile_new=="Pop: High") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Destination Pop:High - Risk level to Risk level", cex.main = 1)

#start pop low
data <- moves %>%
  filter(pop_tercile_old=="Pop: Low") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:Low - Risk level to Risk level", cex.main = 1)

#start pop medium
data <- moves %>%
  filter(pop_tercile_old=="Pop: Moderate") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:Moderate - Risk level to Risk level", cex.main = 1)

#start pop high
data <- moves %>%
  filter(pop_tercile_old=="Pop: High") %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(row_count=sum(row_count))

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

chordDiagram(
  x=data, directional = 1, direction.type = c("diffHeight", "arrows"),link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Origin Pop:High - Risk level to Risk level", cex.main = 1)

Chord - Critical

This chunk produces the chord diagrams for critical services and non-critical services

data <- read_csv("moves_crit.csv") %>%
  mutate(avg_eal_tercile_old=ifelse(is.na(avg_eal_tercile_old),"Outside",avg_eal_tercile_old)) %>%
  mutate(avg_eal_tercile_new=ifelse(is.na(avg_eal_tercile_new),"Outside",avg_eal_tercile_new))

## Rows: 16 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): avg_eal_tercile_old, avg_eal_tercile_new
## dbl (1): row_count
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Critical: Risk level to Risk level", cex.main = 1)

data <- read_csv("moves_non_crit.csv") %>%
  mutate(avg_eal_tercile_old=ifelse(is.na(avg_eal_tercile_old),"Outside",avg_eal_tercile_old)) %>%
  mutate(avg_eal_tercile_new=ifelse(is.na(avg_eal_tercile_new),"Outside",avg_eal_tercile_new))

## Rows: 16 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): avg_eal_tercile_old, avg_eal_tercile_new
## dbl (1): row_count
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Non-Critical: Risk level to Risk level", cex.main = 1)

This chunk produces the chord diagrams for standalone and chains

data <- read_csv("moves_chain.csv") %>%
  mutate(avg_eal_tercile_old=ifelse(is.na(avg_eal_tercile_old),"Outside",avg_eal_tercile_old)) %>%
  mutate(avg_eal_tercile_new=ifelse(is.na(avg_eal_tercile_new),"Outside",avg_eal_tercile_new))

## Rows: 16 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): avg_eal_tercile_old, avg_eal_tercile_new
## dbl (1): row_count
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Chain: Risk level to Risk level", cex.main = 1)

data <- read_csv("moves_standalone.csv") %>%
  mutate(avg_eal_tercile_old=ifelse(is.na(avg_eal_tercile_old),"Outside",avg_eal_tercile_old)) %>%
  mutate(avg_eal_tercile_new=ifelse(is.na(avg_eal_tercile_new),"Outside",avg_eal_tercile_new))

## Rows: 16 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): avg_eal_tercile_old, avg_eal_tercile_new
## dbl (1): row_count
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

chordDiagram(
  x=data,
  directional = 1,
  direction.type = c("diffHeight", "arrows"),
  link.arr.type = "big.arrow",
  grid.col = c(High="red",Moderate="yellow", Low="green",Outside="gray"))
title("Standalone: Risk level to Risk level", cex.main = 1)

Sankey

This chunk produces a interactive Sankey for moves

library(networkD3)
library(dplyr)
library(htmlwidgets)

## 
## Attaching package: 'htmlwidgets'

## The following object is masked from 'package:networkD3':
## 
##     JS

# A connection data frame is a list of flows with intensity for each flow

data <- moves %>%
  mutate(pop_tercile_old=if_else(is.na(pop_tercile_old),"Pop: Outside",pop_tercile_old),
         pop_tercile_new=if_else(is.na(pop_tercile_new),"Pop: Outside",pop_tercile_new))

data$pop_tercile_old <- factor(data$pop_tercile_old, levels = c("Pop: High", "Pop: Moderate", "Pop: Low", "Pop: Outside"), ordered = TRUE)
data$pop_tercile_new <- factor(data$pop_tercile_new, levels = c("Pop: High", "Pop: Moderate", "Pop: Low", "Pop: Outside"), ordered = TRUE)
data$avg_eal_tercile_old <- factor(data$avg_eal_tercile_old, levels = c("High", "Moderate", "Low", "Outside"), ordered = TRUE)
data$avg_eal_tercile_new <- factor(data$avg_eal_tercile_new, levels = c("High", "Moderate", "Low", "Outside"), ordered = TRUE)

pop_to_origin <- data %>%
  group_by(pop_tercile_old,avg_eal_tercile_old) %>%
  summarise(value=sum(row_count,na.rm = TRUE)) %>%
  ungroup() %>%
  mutate(source=str_replace(pop_tercile_old,"Pop:","Origin Pop:"),
         target=paste("Origin: ",avg_eal_tercile_old)) %>%
  select(source,target,value)

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

origin_to_destination <- data %>%
  group_by(avg_eal_tercile_old,avg_eal_tercile_new) %>%
  summarise(value=sum(row_count,na.rm = TRUE)) %>%
  ungroup() %>%
  mutate(source=paste("Origin: ",avg_eal_tercile_old),
         target=paste("Destination: ",avg_eal_tercile_new)) %>%
  select(source,target,value)

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

destination_to_pop <- data %>%
  group_by(avg_eal_tercile_new,pop_tercile_new) %>%
  summarise(value=sum(row_count,na.rm = TRUE)) %>%
  ungroup() %>%
  mutate(source=paste("Destination: ",avg_eal_tercile_new),
         target=str_replace(pop_tercile_new,"Pop:","Destination Pop:")) %>%
  select(source,target,value)

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

links <- bind_rows(pop_to_origin,origin_to_destination,destination_to_pop)
write_csv(links,"links.csv")
# From these flows we need to create a node data frame: it lists every entities involved in the flow
nodes <- data.frame(
  name=c(as.character(links$source), 
  as.character(links$target)) %>% unique()
)
# With networkD3, connection must be provided using id, not using real name like in the links dataframe.. So we need to reformat it.
links$IDsource <- match(links$source, nodes$name)-1 
links$IDtarget <- match(links$target, nodes$name)-1

# Make the Network
p <- sankeyNetwork(Links = links, Nodes = nodes,
                   iterations = 0,
              Source = "IDsource", Target = "IDtarget",
              Value = "value", NodeID = "name", 
              sinksRight=FALSE)

## Links is a tbl_df. Converting to a plain data frame.

p