Indices of Multiple Deprivation (IMD)
To get the IMD scores (raw scores and ranked deciles) for a dataset run the following code to generate some random example postcodes:
tibble_postcodes <- tibble::tibble(postcode = c("HD1 2UT", "HD1 2UU", "HD1 2UV"))
tibble_postcodes
#> # A tibble: 3 × 1
#> postcode
#> <chr>
#> 1 HD1 2UT
#> 2 HD1 2UU
#> 3 HD1 2UVThen, using the get_data() function for a vector:
# Execution halted
NHSRpopulation::get_data(postcodes) |>
dplyr::select(
new_postcode,
result_type,
lsoa_code
)
#> ℹ The following postcodes are terminated:
#> HD1 2UT
#> and have been replaced with these current postcodes:
#> HD1 2RD
#> ℹ The following postcodes are invalid:
#> HD1 2UV
#> and have been replaced with these nearby postcodes:
#> HD1 2UD
#> Error in `dplyr::select()`:
#> ! Can't select columns that don't exist.
#> ✖ Column `postcode` doesn't exist.Or with a data frame:
NHSRpopulation::get_data(tibble_postcodes) |>
dplyr::select(
postcode,
new_postcode,
result_type,
lsoa_code
)
#> ℹ The following postcodes are terminated:
#> HD1 2UT
#> and have been replaced with these current postcodes:
#> HD1 2RD
#> ℹ The following postcodes are invalid:
#> HD1 2UV
#> and have been replaced with these nearby postcodes:
#> HD1 2UD
#> Joining with `by = join_by(postcode)`
#> # A tibble: 3 × 4
#> postcode new_postcode result_type lsoa_code
#> <chr> <chr> <chr> <chr>
#> 1 HD1 2UT HD1 2RD terminated E01011107
#> 2 HD1 2UU HD1 2UU valid E01011229
#> 3 HD1 2UV HD1 2UD autocompleted E01011229Note that this function uses the {NHSRpostcodetools} package to offer
the opportunity to fix postcodes which are terminated or are incorrect.
This is default and appears in the column new_postcode and
does not overwrite the original postcode column. Switching
off this automatic fix can be done with the code and will accept both
vectors and data frames:
NHSRpopulation::get_data(tibble_postcodes, fix_invalid = FALSE) |>
dplyr::select(
postcode,
new_postcode,
result_type,
lsoa_code
)
#> ℹ The following postcodes are invalid:
#> HD1 2UT
#> but have not been successfully replaced with valid codes.
#> The following postcodes are invalid:
#> HD1 2UV
#> but have not been successfully replaced with valid codes.
#> Joining with `by = join_by(postcode)`
#> # A tibble: 3 × 4
#> postcode new_postcode result_type lsoa_code
#> <chr> <chr> <chr> <chr>
#> 1 HD1 2UT <NA> <NA> <NA>
#> 2 HD1 2UU HD1 2UU valid E01011229
#> 3 HD1 2UV <NA> <NA> <NA>Index of Multiple Deprivation
# Note that the third LSOA in this list is incorrect on purpose
imd <- c("E01011107", "E01011229", "E01002")
tibble_imd <- imd |>
tibble::as_tibble() |>
dplyr::rename(lsoa11 = value)
tibble_imd
#> # A tibble: 3 × 1
#> lsoa11
#> <chr>
#> 1 E01011107
#> 2 E01011229
#> 3 E01002Using the same function but with a parameter/argument to return IMD data:
NHSRpopulation::get_data(tibble_imd, url_type = "imd") |>
dplyr::select(
lsoa11,
imd_rank,
imd_decile,
imd_score
)
#> # A tibble: 3 × 4
#> lsoa11 imd_rank imd_decile imd_score
#> <chr> <int> <int> <dbl>
#> 1 E01011107 2928 1 45.6
#> 2 E01011229 9558 3 27.0
#> 3 E01002 NA NA NAData can be either vectors or data frames.
No corrections are made to incorrect LSOA codes.
Column names
Where data frames are used the expectation of the functions is that
postcodes will be in a column called postcode and IMD will
be from lsoa11, however, this can be overwritten:
The argument/parameter column = can be used to set the
column name:
# Create datasets
pcs_tb <- dplyr::tibble(
pcs = postcodes
)
pcs_tb
#> # A tibble: 3 × 1
#> pcs
#> <chr>
#> 1 HD1 2UT
#> 2 HD1 2UU
#> 3 HD1 2UV
NHSRpopulation::get_data(pcs_tb,
column = "pcs"
)
#> ℹ The following postcodes are terminated:
#> HD1 2UT
#> and have been replaced with these current postcodes:
#> HD1 2RD
#> ℹ The following postcodes are invalid:
#> HD1 2UV
#> and have been replaced with these nearby postcodes:
#> HD1 2UD
#> Joining with `by = join_by(pcs)`
#> # A tibble: 3 × 40
#> pcs new_postcode result_type quality eastings northings country nhs_ha longitude latitude european_electoral_r…¹ primary_care_trust region lsoa msoa incode
#> <chr> <chr> <chr> <int> <int> <int> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 HD1 2UT HD1 2RD terminated 1 414639 416430 England Yorkshir… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2RD
#> 2 HD1 2UU HD1 2UU valid 1 414433 416422 England Yorkshir… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2UU
#> 3 HD1 2UV HD1 2UD autocompleted 1 414371 416317 England Yorkshir… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2UD
#> # ℹ abbreviated name: ¹european_electoral_region
#> # ℹ 24 more variables: outcode <chr>, parliamentary_constituency <chr>, parliamentary_constituency_2024 <chr>, admin_district <chr>, parish <chr>,
#> # date_of_introduction <chr>, admin_ward <chr>, ccg <chr>, nuts <chr>, pfa <chr>, admin_district_code <chr>, admin_county_code <chr>, admin_ward_code <chr>,
#> # parish_code <chr>, parliamentary_constituency_code <chr>, parliamentary_constituency_2024_code <chr>, ccg_code <chr>, ccg_id_code <chr>, ced_code <chr>,
#> # nuts_code <chr>, lsoa_code <chr>, msoa_code <chr>, lau2_code <chr>, pfa_code <chr>
lsoa_tb <- dplyr::tibble(
lower_soa = imd
)
lsoa_tb
#> # A tibble: 3 × 1
#> lower_soa
#> <chr>
#> 1 E01011107
#> 2 E01011229
#> 3 E01002
NHSRpopulation::get_data(lsoa_tb,
column = "lower_soa"
)
#> # A tibble: 3 × 66
#> lower_soa fid lsoa11nm lsoa11nmw st_areasha st_lengths imd_rank imd_decile lsoa01nm la_dcd la_dnm imd_score imd_rank0 imd_dec0 inc_score inc_rank inc_dec emp_score
#> <chr> <int> <chr> <chr> <dbl> <dbl> <int> <int> <chr> <chr> <chr> <dbl> <int> <int> <dbl> <int> <int> <dbl>
#> 1 E01011107 11200 Kirklees… Kirklees… 1921709. 7525. 2928 1 Kirklee… E0800… Kirkl… 45.6 2928 1 0.256 3753 2 0.176
#> 2 E01011229 11707 Kirklees… Kirklees… 833130. 7023. 9558 3 Kirklee… E0800… Kirkl… 27.0 9558 3 0.092 17587 6 0.068
#> 3 E01002 NA <NA> <NA> NA NA NA NA <NA> <NA> <NA> NA NA NA NA NA NA NA
#> # ℹ 48 more variables: emp_rank <int>, emp_dec <int>, edu_score <dbl>, edu_rank <int>, edu_dec <int>, hdd_score <dbl>, hdd_rank <int>, hdd_dec <int>, cri_score <dbl>,
#> # cri_rank <int>, cri_dec <int>, bhs_score <dbl>, bhs_rank <int>, bhs_dec <int>, env_score <dbl>, env_rank <int>, env_dec <int>, idc_score <dbl>, idc_rank <int>,
#> # idc_dec <int>, ido_score <dbl>, ido_rank <int>, ido_dec <int>, cyp_score <dbl>, cyp_rank <int>, cyp_dec <int>, as_score <dbl>, as_rank <int>, as_dec <int>,
#> # gb_score <dbl>, gb_rank <int>, gb_dec <int>, wb_score <dbl>, wb_rank <int>, wb_dec <int>, ind_score <dbl>, ind_rank <int>, ind_dec <int>, out_score <dbl>,
#> # out_rank <int>, out_dec <int>, tot_pop <int>, dep_chi <int>, pop16_59 <int>, pop60 <int>, work_pop <dbl>, shape_area <dbl>, shape_length <dbl>Getting IMD data from postcodes
If the data has postcodes (which automatically connects to the
postcode API) and IMD information is wanted, the argument/parameter
url_type == "imd" will override the returned data to
IMD.
NHSRpopulation::get_data(tibble_postcodes,
url_type = "imd")
#> ℹ The following postcodes are terminated:
#> HD1 2UT
#> and have been replaced with these current postcodes:
#> HD1 2RD
#> ℹ The following postcodes are invalid:
#> HD1 2UV
#> and have been replaced with these nearby postcodes:
#> HD1 2UD
#> Joining with `by = join_by(postcode)`
#> # A tibble: 3 × 105
#> postcode new_postcode result_type quality eastings northings country nhs_ha longitude latitude european_electoral_r…¹ primary_care_trust region lsoa msoa incode
#> <chr> <chr> <chr> <int> <int> <int> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 HD1 2UT HD1 2RD terminated 1 414639 416430 England Yorkshi… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2RD
#> 2 HD1 2UU HD1 2UU valid 1 414433 416422 England Yorkshi… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2UU
#> 3 HD1 2UV HD1 2UD autocompleted 1 414371 416317 England Yorkshi… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2UD
#> # ℹ abbreviated name: ¹european_electoral_region
#> # ℹ 89 more variables: outcode <chr>, parliamentary_constituency <chr>, parliamentary_constituency_2024 <chr>, admin_district <chr>, parish <chr>,
#> # date_of_introduction <chr>, admin_ward <chr>, ccg <chr>, nuts <chr>, pfa <chr>, admin_district_code <chr>, admin_county_code <chr>, admin_ward_code <chr>,
#> # parish_code <chr>, parliamentary_constituency_code <chr>, parliamentary_constituency_2024_code <chr>, ccg_code <chr>, ccg_id_code <chr>, ced_code <chr>,
#> # nuts_code <chr>, lsoa_code <chr>, msoa_code <chr>, lau2_code <chr>, pfa_code <chr>, fid <int>, lsoa11nm <chr>, lsoa11nmw <chr>, st_areasha <dbl>, st_lengths <dbl>,
#> # imd_rank <int>, imd_decile <int>, lsoa01nm <chr>, la_dcd <chr>, la_dnm <chr>, imd_score <dbl>, imd_rank0 <int>, imd_dec0 <int>, inc_score <dbl>, inc_rank <int>,
#> # inc_dec <int>, emp_score <dbl>, emp_rank <int>, emp_dec <int>, edu_score <dbl>, edu_rank <int>, edu_dec <int>, hdd_score <dbl>, hdd_rank <int>, hdd_dec <int>, …Note that the postcode data is still validated.
NHSRpopulation::get_data(tibble_postcodes,
url_type = "imd",
fix_invalid = FALSE)
#> ℹ The following postcodes are invalid:
#> HD1 2UT
#> but have not been successfully replaced with valid codes.
#> The following postcodes are invalid:
#> HD1 2UV
#> but have not been successfully replaced with valid codes.
#> Joining with `by = join_by(postcode)`
#> # A tibble: 3 × 105
#> postcode new_postcode result_type quality eastings northings country nhs_ha longitude latitude european_electoral_r…¹ primary_care_trust region lsoa msoa incode
#> <chr> <chr> <chr> <int> <int> <int> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 HD1 2UT <NA> <NA> NA NA NA <NA> <NA> NA NA <NA> <NA> <NA> <NA> <NA> <NA>
#> 2 HD1 2UU HD1 2UU valid 1 414433 416422 England Yorkshire… -1.78 53.6 Yorkshire and The Hum… Kirklees Yorks… Kirk… Kirk… 2UU
#> 3 HD1 2UV <NA> <NA> NA NA NA <NA> <NA> NA NA <NA> <NA> <NA> <NA> <NA> <NA>
#> # ℹ abbreviated name: ¹european_electoral_region
#> # ℹ 89 more variables: outcode <chr>, parliamentary_constituency <chr>, parliamentary_constituency_2024 <chr>, admin_district <chr>, parish <chr>,
#> # date_of_introduction <chr>, admin_ward <chr>, ccg <chr>, nuts <chr>, pfa <chr>, admin_district_code <chr>, admin_county_code <chr>, admin_ward_code <chr>,
#> # parish_code <chr>, parliamentary_constituency_code <chr>, parliamentary_constituency_2024_code <chr>, ccg_code <chr>, ccg_id_code <chr>, ced_code <chr>,
#> # nuts_code <chr>, lsoa_code <chr>, msoa_code <chr>, lau2_code <chr>, pfa_code <chr>, fid <int>, lsoa11nm <chr>, lsoa11nmw <chr>, st_areasha <dbl>, st_lengths <dbl>,
#> # imd_rank <int>, imd_decile <int>, lsoa01nm <chr>, la_dcd <chr>, la_dnm <chr>, imd_score <dbl>, imd_rank0 <int>, imd_dec0 <int>, inc_score <dbl>, inc_rank <int>,
#> # inc_dec <int>, emp_score <dbl>, emp_rank <int>, emp_dec <int>, edu_score <dbl>, edu_rank <int>, edu_dec <int>, hdd_score <dbl>, hdd_rank <int>, hdd_dec <int>, …