|
| 1 | +# C50 0.4.0 |
| 2 | + |
| 3 | +* Build configuration changes for Windows |
| 4 | + |
| 5 | +# C50 0.3.0 |
| 6 | + |
| 7 | +* Build configuration changes for Windows |
| 8 | + |
| 9 | + |
| 10 | +# C50 0.2.4 |
| 11 | + |
| 12 | +* Maintenance release to fix CRAN issues by adding rmarkdown to Suggests. |
| 13 | + |
| 14 | +* Re-wrote parts of the vignettes and added another for model tuning. |
| 15 | + |
| 16 | + |
| 17 | +# C50 0.2.3 |
| 18 | + |
| 19 | +* Maintenance release to fix CRAN issues for GCC 10 -fno-common flag. |
| 20 | + |
| 21 | +* `tidy_rules()` was removed since the code is now in the tidyrules package. |
| 22 | + |
| 23 | +* Changes to better work with tibble inputs. |
| 24 | + |
| 25 | + |
| 26 | +# C50 0.2.2 |
| 27 | + |
| 28 | +* Maintenance release to fix CRAN issues for C string buffers |
| 29 | + |
| 30 | + |
| 31 | +# C50 0.2.1 |
| 32 | + |
| 33 | +* Fixed a bug in the code that escapes improper characters. |
| 34 | + |
| 35 | + |
| 36 | +# C50 0.2.0 |
| 37 | + |
| 38 | +* Converted documentation to `roxygen2`. |
| 39 | + |
| 40 | +* Revised some compiler options to reduce `R CMD check` warnings. |
| 41 | + |
| 42 | + |
| 43 | + |
| 44 | + |
| 45 | +# C50 0.0.19 |
| 46 | + |
| 47 | +* A bug was fixed, found by Duncan Murdoch. |
| 48 | +* A bug in predictions when sampling was used was fixed by Laurae (a random data witch/magician) \issue{1} |
| 49 | + |
| 50 | + |
| 51 | + |
| 52 | +# C50 0.0.17 |
| 53 | + |
| 54 | + |
| 55 | +* Memory allocation bugs in the R version of the C code, which lead to segmentation faults, were fixed. |
| 56 | + |
| 57 | + |
| 58 | + |
| 59 | +# C50 0.0.15 |
| 60 | + |
| 61 | + |
| 62 | +* A bug was fixed where the model failed if no predictors were included in the model (thanks to Gabe Gershenfeld for the find). |
| 63 | + |
| 64 | + |
| 65 | + |
| 66 | +# C50 0.0.14 |
| 67 | + |
| 68 | + |
| 69 | +* The Windows build configuration was updated. |
| 70 | + |
| 71 | +* Some files were synced with the C50 package. |
| 72 | + |
| 73 | + |
| 74 | + |
| 75 | +# C50 0.0.13 |
| 76 | + |
| 77 | + |
| 78 | +* More efficient code was borrowed from the C50 package to write the data file to a string. |
| 79 | + |
| 80 | +* A bug related to column names found by David Clifford was fixed. |
| 81 | + |
| 82 | + |
| 83 | +# C50 0.0.12 |
| 84 | + |
| 85 | + |
| 86 | +* A bug was fixed that occurred when splits were determined in models with a categorical variable involving more than two categories (eg. "if X4 in {a, b}") |
| 87 | + |
| 88 | +* Also, a bug was found in the variable importances calculations when a variable was used only in the conditions and not the model. |
| 89 | + |
| 90 | +* The 'doc' directory was moved into the "vignettes" directory |
| 91 | + |
| 92 | + |
| 93 | +# C50 0.0.11 |
| 94 | + |
| 95 | + |
| 96 | +* cubist uses a string buffer to capture the output files that would normally get saved to external files. The package was failing R CMD check only on windows because the output files were getting garbled. `s*printf` functions work differently on Windows. On Linux, they return the size that is needed to correctly print the string. On Windows, if there isn't enough space, they return -1. |
| 97 | + |
| 98 | +* Also, work-arounds were added to the C sources because of R CMD check issues. `printf()`, `assert()` and `exist()` statements were removed or redefined. |
| 99 | + |
| 100 | + |
| 101 | +# C50 0.0.8 |
| 102 | + |
| 103 | +* A bug was fixed for the `coef` method. |
| 104 | + |
| 105 | + |
| 106 | + |
| 107 | +# C50 0.0.6 |
| 108 | + |
| 109 | +* The GPL version was revised to be version 3 (thanks to Ross Quinlan for the note). |
| 110 | + |
| 111 | +* The variable usage statistics were saved to a data frame in called `object$usage`. The package vignette and help files were updated accordingly. |
| 112 | + |
| 113 | +* When using `cubist`, if `x` was a vector or a single variable, an error occurred. This was fixed. |
| 114 | + |
| 115 | +* The vignette was also expanded to show how caret can be used to tune the model and a technical error was corrected about the boosting algorithm (thanks again to Ross Quinlan). |
| 116 | + |
| 117 | + |
| 118 | + |
0 commit comments