Skip to content
This repository has been archived by the owner on Sep 17, 2024. It is now read-only.

feat(A16): add pipeline #47

Merged
merged 6 commits into from
Aug 7, 2023
Merged
Changes from 5 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
74 changes: 74 additions & 0 deletions pipelines/A16/A16.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,74 @@
# create ds object --------------------------------------------------------

ds <- create_dataset(id = "A16")


# download the data -------------------------------------------------------

ds <- download_data(ds)

# data cleaning -----------------------------------------------------------

### Filter specific dimensions

# To reduce the dataset size, we will not include sex and citizenship category
ds$data %>%
janitor::clean_names() %>%
dplyr::filter(
sex == "Sex - total"
) %>%
dplyr::select(-sex, -citizenship_category) -> ds$postgres_export

# Pivot indicators into 1 indicator per column and cleanup names
ds$postgres_export %>%
tidyr::pivot_wider(
names_from = demographic_component,
values_from = demographic_balance_by_canton
) %>%
janitor::clean_names() %>%
dplyr::rename(
"total_population" = population_on_1_january,
"births" = live_birth,
"deaths" = death,
"net_migration" = net_migration_incl_change_of_population_type,
"immigration" = immigration_incl_change_of_population_type
) -> ds$postgres_export

# Remove redundant or constant columns
# + acquisition of swiss citizenship is always 0
# + The 'change of population type' component is
# always included in the demographic components of
# 'immigration' and 'net migration'.
ds$postgres_export %>%
dplyr::select(
-change_of_population_type,
-population_on_31_december,
-natural_change,
) -> ds$postgres_export

# Remove rows with no canton and 0 values
# Excluding years 1971 - 1980 where there is only
# information about net migration
ds$postgres_export %>%
dplyr::filter(year >= 1981) %>%
dplyr::filter(canton != "No indication") -> ds$postgres_export

# join the cleaned data to the postgres spatial units table ---------------

spatial_map <- ds$postgres_export %>%
dplyr::select(canton) %>%
dplyr::distinct(canton) %>%
map_ds_spatial_units()

ds$postgres_export %<>%
dplyr::left_join(spatial_map, by = "canton") %>%
dplyr::select(-canton)

## check that each spatial unit could be matched -> this has to be TRUE

assertthat::noNA(ds$data$spatialunit_uid)


# ingest into postgres ----------------------------------------------------

### important: name the table as demographic_balance_by_canton