mj

.Rproj.user/8CADE01B/sources/prop/171EFBF7

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "117,76",
+    "scrollLine": "0"
+}

.Rproj.user/8CADE01B/sources/prop/282E8E50

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "21,0",
+    "scrollLine": "0"
+}

.Rproj.user/8CADE01B/sources/prop/65227095

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "11,42",
+    "scrollLine": "6"
+}

.Rproj.user/8CADE01B/sources/prop/D9D85F80

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "17,147",
+    "scrollLine": "8"
+}

.Rproj.user/8CADE01B/sources/prop/DA89EDF8

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "56,7",
+    "scrollLine": "16"
+}

.Rproj.user/8CADE01B/sources/prop/EA7C7384

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "9,0",
+    "scrollLine": "0"
+}

.Rproj.user/8CADE01B/sources/prop/F92CFE2A

@@ -0,0 +1,6 @@
+{
+    "source_window_id": "",
+    "Source": "Source",
+    "cursorPosition": "21,10",
+    "scrollLine": "14"
+}

.Rproj.user/8CADE01B/sources/session-7f1d55ad/73C8D9BE

@@ -0,0 +1,28 @@
+{
+    "id": "73C8D9BE",
+    "path": null,
+    "project_path": null,
+    "type": "object_explorer",
+    "hash": "0",
+    "contents": "",
+    "dirty": false,
+    "created": 1688683077840.0,
+    "source_on_save": false,
+    "relative_order": 4,
+    "properties": {
+        "id": "d0a197b9ed8749e684d1852ccafbbc24",
+        "name": "uswithdata1",
+        "title": "uswithdata1",
+        "language": "R",
+        "source_window_id": "",
+        "Source": "Source"
+    },
+    "folds": "",
+    "lastKnownWriteTime": 0,
+    "encoding": "",
+    "collab_server": "",
+    "source_window": "",
+    "last_content_update": 1688683077840,
+    "read_only": false,
+    "read_only_alternatives": []
+}

.Rproj.user/8CADE01B/sources/session-7f1d55ad/C8782AF5

@@ -0,0 +1,26 @@
+{
+    "id": "C8782AF5",
+    "path": "~/Desktop/R/scripts/countyoutscleaner.Rmd",
+    "project_path": "scripts/countyoutscleaner.Rmd",
+    "type": "r_markdown",
+    "hash": "0",
+    "contents": "",
+    "dirty": false,
+    "created": 1688680198801.0,
+    "source_on_save": false,
+    "relative_order": 9,
+    "properties": {
+        "source_window_id": "",
+        "Source": "Source",
+        "cursorPosition": "56,7",
+        "scrollLine": "15"
+    },
+    "folds": "",
+    "lastKnownWriteTime": 1688686479,
+    "encoding": "UTF-8",
+    "collab_server": "",
+    "source_window": "",
+    "last_content_update": 1688687094337,
+    "read_only": false,
+    "read_only_alternatives": []
+}

.Rproj.user/8CADE01B/sources/session-7f1d55ad/C8782AF5-contents

@@ -0,0 +1,73 @@
+
+a cleaner version of countyouts.rmd, for the sake of double checking my work
+
+##loading packages
+```{r}
+library(tidyverse)
+library(sf)
+```
+
+##read data
+```{r}
+countyoutflow <- read.csv("~/Desktop/R/data/countyoutflow2021.csv")
+
+us <- st_read("/Users/elin/Downloads/cb_2018_us_county_500k")
+```
+##filter it down
+```{r}
+california <- countyoutflow %>% group_by(y2_countyname) %>% filter(y1_statefips == "6" & y2_statefips !=96 & y2_statefips !=97 & y2_statefips !=98)
+```
+
+##adding the full fips code
+str_pad makes the fips codes into 3 digits (county) and 2 digits (state) so that they can be concated together into a real ~~boy~~ fips code
+```{r}
+california$y2_countyfips <- str_pad(california$y2_countyfips, 3, pad = 0)
+
+california$y2_statefips <- str_pad(california$y2_statefips, 2, pad = 0)
+
+california <- california %>% mutate(state2fullfips = str_c(y2_statefips, y2_countyfips))
+```
+
+### adding the full fips code to the us shapefile
+```{r}
+us <- us %>% mutate(fullfips = str_c(STATEFP, COUNTYFP))
+```
+
+##grouping
+going to group by y2 county names so that i can 
+```{r}
+california %>% group_by(y2_countyname, state2fullfips) %>% summarise(individuals = sum(n2))
+```
+
+### integrity check: hennepin county
+```{r}
+california %>% group_by(y2_countyname) %>% filter(y2_countyname == "Hennepin County") %>% summarise(individuals = sum(n2))
+```
+it looks right to me but will definitely need a second set of eyes
+
+```{r}
+simplified <- california %>% group_by(y2_countyname, state2fullfips) %>% summarise(individuals = sum(n2))
+```
+
+##merging
+```{r}
+uswithdata <- merge(simplified, us, by.x = "state2fullfips", by.y = "fullfips")
+```
+
+##print
+```{r}
+st_write(uswithdata, "uswithdata.shp")
+```
+
+okay so that printed well, everything worked the way I wanted to in order to animate in blender. however, the problem is that it contains exclusively the counties to which people migrated from california. (which is correct for its code). HOWEVER (again), it means that there are large swaths of the country that are just blank. so i need 0 values for every county in the country. 
+
+the goal: uswithdata1 has 3222 observations of 13 variables. there's a 0 for the counties that received no california migrants
+
+###trying a different merge
+```{r}
+uswithdata1 <- merge(us, simplified, by.x = "fullfips", by.y = "state2fullfips", all.x = TRUE)
+
+st_write(uswithdata1, "uswithdata.shp")
+```
+
+did not create a full country outlook? 

.Rproj.user/8CADE01B/sources/session-7f1d55ad/DEACC27B

@@ -0,0 +1,34 @@
+{
+    "id": "DEACC27B",
+    "path": null,
+    "project_path": null,
+    "type": "r_dataframe",
+    "hash": "0",
+    "contents": "",
+    "dirty": false,
+    "created": 1688681840603.0,
+    "source_on_save": false,
+    "relative_order": 3,
+    "properties": {
+        "expression": "uswithdata",
+        "caption": "uswithdata",
+        "totalObservations": 633,
+        "displayedObservations": 633,
+        "variables": 13,
+        "cacheKey": "6868E546",
+        "object": "uswithdata",
+        "environment": "",
+        "contentUrl": "grid_resource/gridviewer.html?env=&obj=uswithdata&cache_key=6868E546&max_cols=50",
+        "preview": 0,
+        "source_window_id": "",
+        "Source": "Source"
+    },
+    "folds": "",
+    "lastKnownWriteTime": 0,
+    "encoding": "",
+    "collab_server": "",
+    "source_window": "",
+    "last_content_update": 1688681840603,
+    "read_only": false,
+    "read_only_alternatives": []
+}

.Rproj.user/8CADE01B/sources/session-7f1d55ad/F6062D21

@@ -0,0 +1,26 @@
+{
+    "id": "F6062D21",
+    "path": "~/Desktop/R/scripts/countyouts.Rmd",
+    "project_path": "scripts/countyouts.Rmd",
+    "type": "r_markdown",
+    "hash": "0",
+    "contents": "",
+    "dirty": false,
+    "created": 1688153055369.0,
+    "source_on_save": false,
+    "relative_order": 1,
+    "properties": {
+        "source_window_id": "",
+        "Source": "Source",
+        "cursorPosition": "117,76",
+        "scrollLine": "0"
+    },
+    "folds": "",
+    "lastKnownWriteTime": 1688680191,
+    "encoding": "UTF-8",
+    "collab_server": "",
+    "source_window": "",
+    "last_content_update": 1688680191047,
+    "read_only": false,
+    "read_only_alternatives": []
+}

.Rproj.user/8CADE01B/sources/session-7f1d55ad/F6062D21-contents

@@ -0,0 +1,121 @@
+
+```{r}
+library(tidyverse)
+library(readxl)
+library(tigris)
+```
+## load the data
+outs.xlsx is census data
+```{r}
+outs <- read_excel("~/Desktop/elliesacbeeR/data/outs.xlsx", sheet=1)
+
+irsouts <- read.csv("~/Desktop/elliesacbeeR/data/countyoutflow2021.csv")
+
+irsins <- read.csv("~/Desktop/elliesacbeeR/data/countyinflow2021.csv")
+
+state2state <- read_excel("~/Desktop/elliesacbeeR/data/2021ca (1).xlsx")
+
+latlongs <- read_csv("https://gist.github.com/russellsamora/12be4f9f574e92413ea3f92ce1bc58e6/raw/3f18230058afd7431a5d394dab7eeb0aafd29d81/us_county_latlng.csv")
+```
+
+California state fips code = 06
+
+##filter down
+```{r}
+nosummaryrows <-irsouts %>% group_by(y2_countyname) %>% filter(y1_statefips == "6" & y2_statefips !=96 & y2_statefips !=97 & y2_statefips !=98)
+```
+
+Just four-county area
+```{r}
+nosummaryrows %>% filter(y1_countyfips == 34 | y1_countyfips == 31 | y1_countyfips == 9 | y1_countyfips == 57)
+```
+## getting prepped to geocode
+using str_pad to make both the county fips code columns and the state fips code columns have leading zeroes so they're like actual fips codes. then, im gonna concatenate the columns. 
+```{r}
+irsins$y1_countyfips <- str_pad(irsins$y1_countyfips, 3, pad = 0)
+
+irsins$y1_statefips <- str_pad(irsins$y1_statefips, 2, pad = 0)
+
+irsins$y2_countyfips <- str_pad(irsins$y2_countyfips, 3, pad = 0)
+
+irsins$y2_statefips <- str_pad(irsins$y2_statefips, 2, pad = 0)
+
+irsins <- irsins %>% mutate(state1fullfips = str_c(y1_statefips, y1_countyfips))
+
+irsins <- irsins %>% mutate(state2fullfips = str_c(y2_statefips, y2_countyfips))
+```
+
+formatting both.
+```{r}
+irsouts$y1_countyfips <- str_pad(irsouts$y1_countyfips, 3, pad = 0)
+
+irsouts$y1_statefips <- str_pad(irsouts$y1_statefips, 2, pad = 0)
+
+irsouts$y2_countyfips <- str_pad(irsouts$y2_countyfips, 3, pad = 0)
+
+irsouts$y2_statefips <- str_pad(irsouts$y2_statefips, 2, pad = 0)
+
+irsouts <- irsouts %>% mutate(state1fullfips = str_c(y1_statefips, y1_countyfips))
+
+irsouts <- irsouts %>% mutate(state2fullfips = str_c(y2_statefips, y2_countyfips))
+```
+
+## making a table for outmigration from just california
+```{r}
+justca <- irsouts %>% group_by(y2_countyname) %>% filter(y1_statefips == "06")
+
+justca <- justca %>% filter(y2_statefips !=96 & y2_statefips !=97 & y2_statefips !=98)
+
+supersimplified <- justca %>% group_by(y2_countyname, state2fullfips) %>% summarise(sum(n2))
+```
+
+
+## to merge with lat long data
+```{r}
+justcawithlatlong <- merge(justca, latlongs, by.x = "state2fullfips", by.y = "fips_code")
+```
+
+##print
+```{r}
+write.csv(justcawithlatlong, "californiaoutmigration.csv")
+
+justca <- justca[complete.cases(justca), ]
+
+write.csv(justca, "californiaoutmigrationnolatlong.csv")
+```
+
+```{r}
+mergeddata <- read_csv("~/Desktop/elliesacbeeR/data/merge__california__georef-uni.csv")
+```
+
+
+```{r}
+mergeddata <- mergeddata[complete.cases(mergeddata), ]
+```
+
+
+```{r}
+write.csv(supersimplified, "supersimplified.csv")
+```
+
+Ellie EOD note 6/30: 
+
+I need to find the totals for each county's migrants from California. Then, I need to somehow merge that data into a JSON format so that mapbox can read it OR I can open it in After Effects. 
+
+
+## binding data to shp 
+```{r}
+library(sf)
+```
+
+```{r}
+us <- st_read("/Users/elin/Downloads/cb_2018_us_county_500k")
+
+us <- us %>% mutate(fullfips = str_c(STATEFP, COUNTYFP))
+
+irsouts <- irsouts %>% group_by(y2_countyname) %>% filter(y1_statefips == "6" & y2_statefips !=96 & y2_statefips !=97 & y2_statefips !=98)
+
+uswithdata <- merge(irsouts, us, by.x = "state2fullfips", by.y = "fullfips")
+
+st_write(uswithdata, "uswithdata.shp")
+```