From a75da9d7478c80c3a327c11dd78aaa4471af798a Mon Sep 17 00:00:00 2001 From: Francois Berenger Date: Thu, 5 Jan 2023 13:05:57 +0900 Subject: [PATCH 1/6] new file: packages/orf/orf.1.0.1/opam compiles w/ ocaml-5 and many other versions probably --- packages/orf/orf.1.0.1/opam | 63 +++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) create mode 100644 packages/orf/orf.1.0.1/opam diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam new file mode 100644 index 00000000000..6ee0e0247b1 --- /dev/null +++ b/packages/orf/orf.1.0.1/opam @@ -0,0 +1,63 @@ +opam-version: "2.0" +authors: "Francois Berenger" +maintainer: "unixjunkie@sdf.org" +homepage: "https://github.com/UnixJunkie/orf" +bug-reports: "https://github.com/UnixJunkie/orf/issues" +dev-repo: "git+https://github.com/UnixJunkie/orf.git" +license: "LGPL-2.1-or-later WITH OCaml-LGPL-linking-exception" +build: ["dune" "build" "-p" name "-j" jobs] +depends: [ + "batteries" {>= "3.2.0"} + "cpm" {>= "6.0.0"} + "dolog" {>= "4.0.0"} + "dune" {>= "2.8"} + "minicli" + "ocaml" + "parany" {>= "11.0.0"} + "line_oriented" +] +depopts: [ + "conf-gnuplot" +] +synopsis: "OCaml Random Forests" +description:""" +Random Forests (RFs) can do classification or regression modeling. + +Random Forests are one of the workhorse of modern machine +learning. Especially, they cannot over-fit to the training set, are +fast to train, predict fast, parallelize well and give you a reasonable +model even without optimizing the model's default hyper-parameters. In +other words, it is hard to shoot yourself in the foot while training +or exploiting a Random Forests model. In comparison, with deep neural +networks it is very easy to shoot yourself in the foot. + +Using out of bag (OOB) samples, you can even get an idea of a RFs +performance, without the need for a held out (test) data-set. + +Their only drawback is that RFs, being an ensemble model, cannot predict +values which are outside of the training set range of values (this is +a serious limitation in case you are trying to optimize or minimize +something in order to discover outliers, compared to your training +set samples). + +For the moment, this implementation only consider a sparse vector +of integers as features. i.e. categorical variables will need to be +one-hot-encoded. +For classification, the dependent variable must be an integer +(encoding a class label). +For regression, the dependent variable must be a float. + +Bibliography +============ + +Breiman, Leo. (1996). Bagging Predictors. Machine learning, 24(2), +123-140. + +Breiman, Leo. (2001). Random Forests. Machine learning, 45(1), 5-32. + +Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely Randomized +Trees. Machine learning, 63(1), 3-42.""" +url { + src: "https://github.com/UnixJunkie/orf/archive/refs/tags/v1.0.1.tar.gz" + checksum: "md5=d41d8cd98f00b204e9800998ecf8427e" +} From ac3bdf3f8e97de8a30e6c6ae32685613302fa3a6 Mon Sep 17 00:00:00 2001 From: Kate Date: Tue, 14 Feb 2023 12:48:57 +0000 Subject: [PATCH 2/6] Update packages/orf/orf.1.0.1/opam --- packages/orf/orf.1.0.1/opam | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam index 6ee0e0247b1..766528d82fe 100644 --- a/packages/orf/orf.1.0.1/opam +++ b/packages/orf/orf.1.0.1/opam @@ -59,5 +59,5 @@ Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely Randomized Trees. Machine learning, 63(1), 3-42.""" url { src: "https://github.com/UnixJunkie/orf/archive/refs/tags/v1.0.1.tar.gz" - checksum: "md5=d41d8cd98f00b204e9800998ecf8427e" + checksum: "md5=8e58bcd5ccfd2cb11ab5c09a23000379" } From baf42edb1f3f1847a551f1254f21013e36cc6e8e Mon Sep 17 00:00:00 2001 From: Kate Date: Tue, 14 Feb 2023 21:25:56 +0000 Subject: [PATCH 3/6] Update opam --- packages/orf/orf.1.0.1/opam | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam index 766528d82fe..7dcf37520b9 100644 --- a/packages/orf/orf.1.0.1/opam +++ b/packages/orf/orf.1.0.1/opam @@ -12,6 +12,7 @@ depends: [ "dolog" {>= "4.0.0"} "dune" {>= "2.8"} "minicli" + "molenc" "ocaml" "parany" {>= "11.0.0"} "line_oriented" From 34641fd3865fbdaba020a5ba8cf8ee628b472548 Mon Sep 17 00:00:00 2001 From: Marcello Seri Date: Wed, 18 Oct 2023 15:38:08 +0200 Subject: [PATCH 4/6] Apply suggestions from code review --- packages/orf/orf.1.0.1/opam | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam index 7dcf37520b9..a102aabf112 100644 --- a/packages/orf/orf.1.0.1/opam +++ b/packages/orf/orf.1.0.1/opam @@ -8,12 +8,12 @@ license: "LGPL-2.1-or-later WITH OCaml-LGPL-linking-exception" build: ["dune" "build" "-p" name "-j" jobs] depends: [ "batteries" {>= "3.2.0"} - "cpm" {>= "6.0.0"} + "cpm" {>= "11.0.0"} "dolog" {>= "4.0.0"} "dune" {>= "2.8"} "minicli" "molenc" - "ocaml" + "ocaml" {>= "4.12"} "parany" {>= "11.0.0"} "line_oriented" ] From a0567dab6a6860a843633804e9fed0a4f231942a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fran=C3=A7ois=20B=C3=A9renger?= Date: Thu, 20 Jun 2024 09:14:51 +0900 Subject: [PATCH 5/6] Update packages/orf/orf.1.0.1/opam Co-authored-by: Shon Feder --- packages/orf/orf.1.0.1/opam | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam index a102aabf112..9a8bea2f258 100644 --- a/packages/orf/orf.1.0.1/opam +++ b/packages/orf/orf.1.0.1/opam @@ -12,7 +12,7 @@ depends: [ "dolog" {>= "4.0.0"} "dune" {>= "2.8"} "minicli" - "molenc" + "molenc" {>= "16.15.0"} "ocaml" {>= "4.12"} "parany" {>= "11.0.0"} "line_oriented" From 383b08ed82f99c89eeeb996d860a939eb790e8fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fran=C3=A7ois=20B=C3=A9renger?= Date: Thu, 20 Jun 2024 12:08:35 +0900 Subject: [PATCH 6/6] Update opam use a sha256 sum instead of md5 --- packages/orf/orf.1.0.1/opam | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/orf/orf.1.0.1/opam b/packages/orf/orf.1.0.1/opam index 9a8bea2f258..46154fe974e 100644 --- a/packages/orf/orf.1.0.1/opam +++ b/packages/orf/orf.1.0.1/opam @@ -60,5 +60,5 @@ Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely Randomized Trees. Machine learning, 63(1), 3-42.""" url { src: "https://github.com/UnixJunkie/orf/archive/refs/tags/v1.0.1.tar.gz" - checksum: "md5=8e58bcd5ccfd2cb11ab5c09a23000379" + checksum: "sha256=7e3977bf99284fca63144dad27bdb5f024e59425188b58246b89bf4770f43791" }