This release combines the unreleased 0.2.2 and 0.2.3 fixes and both fresh audits. Results change from CRAN 0.2.1 for missing-value placement, winsorized assignment, dropped missing responses, tie-aware frequency groups and factor counts.
rbin_create() accept
bare column names, strings and variables holding names, including long
non-syntactic names, consistently with rbin_factor()
(rx2h-L2 / rx2d-L1).rbin_equal_length() and
rbin_winsorize() compute cut points only from values with
absolute value up to 1e300 (for rbin_winsorize(), the
values after winsorizing) and otherwise stop with a message, because
near the double-precision limit exact-cut membership would depend on the
platform. rbin_create() still scores any finite value into
the first or last bin.
Predictor classes: I() (AsIs) columns are binned as
their numbers; integer64 and difftime
predictors are refused by the numeric methods and
rbin_create() with a message on how to convert them
(difftime units can differ between fitting and scoring data); factor,
Date and POSIXct predictors point to rbin_factor() /
rbin_factor_create(). rbin_factor() accepts
classed predictors except integer64.
rbin_create() rejects incompatible bins
objects with a class diagnostic, while valid all-missing fits still
produce no indicators (fx6 astra M7).
Winsorized binning validates winsor_rate as a single
number in [0, 0.5], including when clamp endpoints are supplied.
remove_na = FALSE gives a clear error for retained missing
predictors (fx6 opus M2 / astra M8).
Fitters and rbin_create() reject
integer64 and other unsupported numeric classes before
arithmetic, with conversion guidance for integer64 values within +/-2^53
(fx6 H2).
Equal-width and winsorized cuts multiply the span before division, keeping observations on exact mathematical boundaries in the left-closed bin. Large integer spans no longer emit integer overflow warnings (fx6 H1, M6).
Quantile binning rejects computed NA/NaN cut points, including interpolation between negative and positive infinity, while valid infinite cuts remain supported. Numeric assignment rejects unmatched non-missing values rather than putting them into a missing bin (rx2h-H1).
Equal-frequency dummy names format all boundaries together,
preserving the precision of the final >= threshold
(rx2h-L1).
Manual display bounds stay ordered when cuts lie outside the observed predictor range (rx2h-L3).
rbin_equal_length() handles empty intervals and
computes finite internal edges even when the finite range overflows;
equal-width and winsorized methods reject infinite predictors (H01,
A2-H05).
rbin_quantiles() constructs probabilities directly
as integer fractions, preserving exact cut-point membership and derived
statistics (A2-H06).
rbin_winsorize() treats supplied endpoints as clamp
values, estimates only unspecified endpoints, rejects reversed limits,
and handles missing predictors with include_na = FALSE
(H04).
rbin_equal_freq() now keeps tied values together
using empirical quantiles, returning fewer non-empty bins with a message
when cuts coincide. Counts can differ from 0.2.1, and
rbin_create() dummies match the non-missing training
summary. Untied sizes differ by at most one; more bins than observations
still error and missing predictors retain a separate final group (H02,
A2-H01).
rbin_create() preserves bin order, keeps columns for
absent bins, makes colliding boundary labels distinct, and assigns
values outside the training range to the outer intervals (H03,
H10).
rbin_create() uses equal-frequency dummy names
describing the actual scoring thresholds, including gaps
(A2-L01).
rbin_create() applies stored winsor clamp endpoints
before scoring, including collapsed fitted ranges and limits outside the
training range. Older saved winsorized objects without clamp metadata
must be fitted again (A2-H02).
Numeric WoE plots include the missing-predictor group (H15).
(missing) when
an explicit NA factor level is present, in both printed summaries and
plot ticks (rx3-L1).(missing) when a literal "NA" category is
also present, preserving the usual display and stored typed labels
otherwise (rx2d-L2).rbin_factor() groups on integer IDs, preserving
distinct numeric and temporal categories whose display text collides,
and preserving explicit NA factor levels separately from missing codes.
NaN and NA numeric predictors share one missing bin; all retained
observations contribute to counts and statistics (A2-H03, A2-H04,
Hydrogen H1, Hydrogen H2, Hydrogen H3).rbin_factor() preserves ordered classes and explicit NA
level metadata; include_na = FALSE removes missing codes
while retaining explicit NA levels (Hydrogen M4, Hydrogen M5).rbin_factor() accepts bare, character and indirect
column names, including long non-syntactic names, and labels missing
plot ticks as NA (Hydrogen M2, Hydrogen M6).rbin_factor_combine() matches exact names without regex
or substring effects and preserves ordered factors, explicit NA levels
and unselected missing codes. Selecting NA consistently combines both
kinds of NA with the new level (H05, A2-M01, Hydrogen H4, Hydrogen H5,
Hydrogen M5).rbin_factor_create() preserves original columns,
accepts character predictors, creates indicators from factor codes
(including explicit NA levels), and makes generated names unique.
Zero-level inputs return unchanged (H07, H08, H09, A2-M02, Hydrogen
M1)."NA"
and explicit NA levels; selecting the NA level combines the intended
rows (fx6 H3).This is a patch release for minor bug fixes.
This is a minor release for bug fixes and internal changes.
NEWS.md file to track changes to the
package.