Returns a tidy tibble showing how each comparison contributed to the
total match weight for a specific record pair. Designed for use with
ggplot2::geom_col() and ggplot2::coord_flip().
Arguments
- pairs
An
il_comparedtibble frompredict.il_model().- which
An integer index identifying which row (pair) to decompose. Defaults to
1L.
Value
A tibble::tibble() with columns step, order, contribution,
direction, start, and end. The rows include the prior odds,
one row per comparison contribution, and a final total.
Examples
df <- data.frame(
unique_id = 1:20,
first_name = c(
'John', 'Jon', 'Jane', 'Jane', 'Bob',
'Bobby', 'Alice', 'Alicia', 'Tom', 'Thomas',
'John', 'Jon', 'Jane', 'Janet', 'Bob',
'Robert', 'Alice', 'Alison', 'Tom', 'Tomas'
),
surname = c(
'Smith', 'Smith', 'Doe', 'Doe', 'Jones',
'Jones', 'Brown', 'Brown', 'White', 'White',
'Smith', 'Smyth', 'Doe', 'Doe', 'Jones',
'Jones', 'Brown', 'Browne', 'White', 'White'
),
dob = c(
'1990-01-01', '1990-01-01', '1985-06-15', '1985-06-15',
'2000-12-01', '2000-12-01', '1975-03-22', '1975-03-22',
'1988-07-04', '1988-07-04', '1990-01-01', '1990-01-02',
'1985-06-15', '1985-06-16', '2000-12-01', '2000-12-02',
'1975-03-22', '1975-03-23', '1988-07-04', '1988-07-05'
),
city = c(
'London', 'London', 'Paris', 'Paris', 'Berlin',
'Berlin', 'Rome', 'Rome', 'Madrid', 'Madrid',
'London', 'London', 'Paris', 'Paris', 'Berlin',
'Berlin', 'Rome', 'Rome', 'Madrid', 'Madrid'
),
email = c(
'john@example.com', 'jon@example.com', 'jane@example.com',
'jane@example.com', 'bob@example.com', 'bobby@example.com',
'alice@example.com', 'alicia@example.com', 'tom@example.com',
'thomas@example.com', 'john@example.com', 'jon@example.com',
'jane@example.com', 'janet@example.com', 'bob@example.com',
'robert@example.com', 'alice@example.com', 'alison@example.com',
'tom@example.com', 'tomas@example.com'
)
)
con <- DBI::dbConnect(duckdb::duckdb())
spec <- il_spec() |>
il_compare(first_name, cl_jaro_winkler(0.9, 0.7)) |>
il_compare(surname, cl_jaro_winkler(0.9, 0.7)) |>
il_compare(dob, cl_exact()) |>
il_block_on(surname) |>
il_block_on(first_name)
model <- il_model(df, spec = spec, con = con)
model <- il_estimate_u(model)
model <- il_estimate_em(model, block_on(surname))
#> EM trained: first_name and dob | skipped (blocked on): surname
pairs <- predict(model, threshold = 0.5)
il_waterfall(pairs, which = 1)
#> # A tibble: 5 × 6
#> step order contribution direction start end
#> <chr> <int> <dbl> <chr> <dbl> <dbl>
#> 1 Prior 1 -0.0510 prior 0 -0.0510
#> 2 first_name 2 2.91 positive -0.0510 2.86
#> 3 surname 3 2.66 positive 2.86 5.52
#> 4 dob 4 -1.72 negative 5.52 3.81
#> 5 Final 5 3.81 final 0 3.81
DBI::dbDisconnect(con, shutdown = TRUE)