added scripts

data/Schools/Enrollement_2022-2023/DataDisclaimer.txt

@@ -0,0 +1,3 @@
+Data Dissemination Disclaimer
+The Department of Public Instruction (DPI) has made a reasonable effort to ensure that the accompanying information is up-to-date, accurate, complete, and comprehensive at the time of disclosure. These records reflect data as reported to this agency by the educational community we serve for the reporting period indicated. These records are a true and accurate representation of the data on file at the DPI. Authenticated information is accurate only as of the time of validation and verification. The DPI is not responsible for data that is misinterpreted or altered in any way. Derived conclusions and analyses generated from this data are not to be considered attributable to the DPI.
+

data/Schools/Enrollement_2022-2023/enrollement_widen.R

@@ -0,0 +1,24 @@
+library(tidyverse)
+
+enrollment_data <- read_csv(file = "/home/ben/Documents/Data analysis/map/data/Enrollement_2022-2023/enrollment_by_gradelevel_certified_2022-23.csv")
+enrollment_data_wide <- 
+  enrollment_data %>% 
+  mutate(district_school = paste0(DISTRICT_CODE, SCHOOL_CODE),
+         variable_name = paste0(GROUP_BY, "__", GROUP_BY_VALUE)) %>%
+  mutate(variable_name = str_replace_all(variable_name, "[ ]", "_")) %>%
+  pivot_wider(id_cols = c(district_school, GRADE_LEVEL, SCHOOL_NAME, DISTRICT_NAME), names_from = variable_name, values_from = PERCENT_OF_GROUP)
+
+write_csv(enrollment_data_wide, file = "/home/ben/Documents/Data analysis/map/data/Enrollement_2022-2023/enrollment_by_gradelevel_certified_2022-23_wide.csv")
+
+
+# school comparison
+schools <- data.frame(Name = c("East High", "West High", "Memorial High", "LaFollette High"),
+                      district_school = c(32690150,32690840,32690360,32690420))
+
+enrollment_data_wide %>% 
+  filter(district_school %in% schools$district_school) %>%
+  group_by(district_school)
+  summarise(mean_econ_disadv = mean(as.double('Economic_Status__Econ_Disadv'), na.rm = TRUE))
+  ggplot() + 
+  geom_col(aes(x = SCHOOL_NAME,
+               y = mean_econ_disadv))

data/Schools/Enrollement_2022-2023/enrollment_by_gradelevel_certified_2022-23_layout.csv

@@ -0,0 +1,17 @@
+"Field No","Field Name","Field Datatype","Length","Field Description"
+"1","SCHOOL_YEAR","Text","7","School year of enrollment"
+"2","AGENCY_TYPE","Text","50","School/district type"
+"3","CESA","Text","10","Cooperative Educational Service Agency"
+"4","COUNTY","Text","50","County of main district office"
+"5","DISTRICT_CODE","Text","10","District code - Unique 4 digit code assigned by DPI"
+"6","SCHOOL_CODE","Text","10","School code - 4 digit code unique within district and assigned by DPI"
+"7","GRADE_GROUP","Text","50","School grade group. Grade ranges of schools in the same GRADE_GROUP may vary. See also LOW_GRADE and HIGH_GRADE"
+"8","CHARTER_IND","Text","4","Whether school/district is a charter"
+"9","DISTRICT_NAME","Text","100","District name"
+"10","SCHOOL_NAME","Text","100","School name"
+"11","GRADE_LEVEL","Text","50","Student grade when enrolled"
+"12","GROUP_BY","Text","50","Data group - student attribute name"
+"13","GROUP_BY_VALUE","Text","200","Data group - student attribute value"
+"14","GROUP_COUNT","Text","20","Count of students in the data group enrolled on the 3rd Friday of September"
+"15","STUDENT_COUNT","Text","20","Count of students in the data group or subgroup enrolled on the 3rd Friday of September"
+"16","PERCENT_OF_GROUP","Text","20","Percent this group is of all students enrolled on TFS"