source('2_process/src/data_utils.R')
p2_targets <- list(
# Confirming raw data matches `p1_unc_stats` from SB
tar_target(p2_unc_agg_summary,
p1_unc_agg |>
group_by(dimension, determinant) |>
summarize(across(c(contains('related'),
contains('unknown'),
contains('significant')),
list(total = ~sum(.x, na.rm=TRUE)))) |>
mutate(evidence_val = positively_related_total + negatively_related_total +
unrelated_total + unknown_direction_total)
),
# Based on metadata:
# Amt of evidence: Small = total_studies < 5; Medium = total_studies 5-9; Large,total_studies = > 9
# Amt of agreement: Low = < 50% of models; Medium = >50% & <74% of models; High = >74% of models; NA if the level of agreement could not be calculated as indicator was measured only once.
tar_target(p2_top_trend_stats,
p2_unc_agg_summary |>
dplyr::select(dimension, determinant, #indicator,
positively_related_total, negatively_related_total, unrelated_total,
unknown_direction_total) |>
pivot_longer(!c(dimension,determinant)) |>
group_by(dimension, determinant) |>
# for each indicator find the maximum % of studies in agreement
# across the significance categories.
slice_max(value) |>
rename(sig_name = name, sig_value = value)
),
# Join `p2_unc_agg_summary` to top trends to get percentages of agreement and evidence
tar_target(p2_unc_agg_summary_csv,
p2_unc_agg_summary |>
left_join(p2_top_trend_stats) |>
# level of agreement is the max percent of studies in agreement
dplyr::mutate(level_agreement = 100*(sig_value/evidence_val)) |>
readr::write_csv('2_process/out/indicator_uncertainty.csv')
),
tar_target(p2_indicators,
p1_unc_stats |>
distinct(dimension, determinant, indicator)
),
# Process census data for variables of interest
# B01003_001 = Total Population
# B19013_001 = Median Household Income in the Past 12 Months (in 2022 Inflation-Adjusted Dollars)
# B02001_003 = Estimate!!Total:!!Black or African American alone
# B03001_003 = Estimate!!Total:!!Hispanic or Latino:
# B01001_002 = Estimate!!Total:!!Male:
# B01001_026 = Estimate!!Total:!!Female:
tar_target(p2_census_acs5_layers,
list("B01003_001", "B19013_001", "B02001_003",
"B03001_003", "B01001_002", "B01001_026")
),
tar_target(p2_census_acs5_data,
get_census_data(geography = 'county', variable = p2_census_acs5_layers,
states = p1_census_states, year = 2022, proj = p1_proj,
survey_var = "acs5", percent_rename = FALSE),
pattern = map(p2_census_acs5_layers),
iteration = "list"
),
tar_target(p2_tot_pop,
p2_census_acs5_data[[1]] |>
st_drop_geometry() |>
rename(tot_pop = estimate)),
# Add % of total population col to each census layer
tar_target(p2_perc_census_acs5_layers_sf,
process_perc(tot_var = p2_census_acs5_data,
tot_pop = p2_tot_pop),
pattern = map(p2_census_acs5_data),
iteration = "list"),
# Disaggregated census data
# The subject tables include the following geographies: nation, all states (including DC and Puerto Rico), all metropolitan areas, all congressional districts, all counties, all places and all tracts. Subject tables provide an overview of the estimates available in a particular topic. The data are presented as both counts and percentages. There are over 66,000 variables in this dataset.
# More info here: https://api.census.gov/data/2019/acs/acs5.html
# load_variables(2022, "acs5/subject", cache = TRUE)
# Age related variables
# S0101_C02_022 = Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!Under 18 years
# S0101_C02_023 = Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!18 to 24 years
# S0101_C02_024 = Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!15 to 44 years
# S0101_C02_028 = Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!60 years and over
tar_target(p2_census_acs5sub_age_layers,
c("S0101_C02_022", "S0101_C02_023", "S0101_C02_024", "S0101_C02_028")),
tar_target(p2_census_acs5sub_age_data,
get_census_data(geography = 'county', variable = p2_census_acs5sub_age_layers,
states = p1_census_states, year = 2022, proj = p1_proj,
survey_var = "acs5", percent_rename = TRUE),
pattern = map(p2_census_acs5sub_age_layers),
iteration = "list"),
# income related variables
# S1901_C01_014 = Estimate!!Households!!PERCENT ALLOCATED!!Household income in the past 12 months
tar_target(p2_census_acs5sub_income_layers,
c("S1901_C01_014")),
tar_target(p2_census_acs5sub_income_data,
get_census_data(geography = 'county', variable = p2_census_acs5sub_income_layers,
states = p1_census_states, year = 2022, proj = p1_proj,
survey_var = "acs5", percent_rename = TRUE),
pattern = map(p2_census_acs5sub_income_layers),
iteration = "list"),
# education related variables
# S1501_C01_003 = Estimate!!Total!!AGE BY EDUCATIONAL ATTAINMENT!!Population 18 to 24 years!!High school graduate (includes equivalency)
# S1501_C01_009 = Estimate!!Total!!AGE BY EDUCATIONAL ATTAINMENT!!Population 25 years and over!!High school graduate (includes equivalency)
tar_target(p2_census_acs5sub_education_layers,
c("S1501_C01_003", "S1501_C01_009")),
tar_target(p2_census_acs5sub_education_data,
get_census_data(geography = 'county', variable = p2_census_acs5sub_education_layers,
states = p1_census_states, year = 2022, proj = p1_proj,
survey_var = "acs5", percent_rename = FALSE),
pattern = map(p2_census_acs5sub_education_layers),
iteration = "list"),
# household related variables
# S1101_C01_001 = Estimate!!Total!!HOUSEHOLDS!!Total households
# S1101_C04_001 = Estimate!!Female householder, no spouse present, family household!!HOUSEHOLDS!!Total households
# B25064_001 = Estimate!!Median gross rent
tar_target(p2_census_acs5_household_layers,
c("S1101_C01_001", "S1101_C04_001", "B25064_001")),
tar_target(p2_census_acs5sub_household_data,
get_census_data(geography = 'county', variable = p2_census_acs5_household_layers,
states = p1_census_states, year = 2022, proj = p1_proj,
survey_var = "acs5", percent_rename = FALSE),
pattern = map(p2_census_acs5_household_layers),
iteration = "list")
)