diff --git a/Cargo.lock b/Cargo.lock index 53ed951..b4e55b5 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2,12 +2,99 @@ # It is not intended for manual editing. version = 3 +[[package]] +name = "aho-corasick" +version = "1.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916" +dependencies = [ + "memchr", +] + +[[package]] +name = "anstream" +version = "0.6.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "64e15c1ab1f89faffbf04a634d5e1962e9074f2741eef6d97f3c4e322426d526" +dependencies = [ + "anstyle", + "anstyle-parse", + "anstyle-query", + "anstyle-wincon", + "colorchoice", + "is_terminal_polyfill", + "utf8parse", +] + +[[package]] +name = "anstyle" +version = "1.0.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bec1de6f59aedf83baf9ff929c98f2ad654b97c9510f4e70cf6f661d49fd5b1" + +[[package]] +name = "anstyle-parse" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eb47de1e80c2b463c735db5b217a0ddc39d612e7ac9e2e96a5aed1f57616c1cb" +dependencies = [ + "utf8parse", +] + +[[package]] +name = "anstyle-query" +version = "1.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6d36fc52c7f6c869915e99412912f22093507da8d9e942ceaf66fe4b7c14422a" +dependencies = [ + "windows-sys", +] + +[[package]] +name = "anstyle-wincon" +version = "3.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5bf74e1b6e971609db8ca7a9ce79fd5768ab6ae46441c572e46cf596f59e57f8" +dependencies = [ + "anstyle", + "windows-sys", +] + [[package]] name = "cfg-if" version = "1.0.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" +[[package]] +name = "colorchoice" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3fd119d74b830634cea2a0f58bbd0d54540518a14397557951e79340abc28c0" + +[[package]] +name = "env_filter" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4f2c92ceda6ceec50f43169f9ee8424fe2db276791afde7b2cd8bc084cb376ab" +dependencies = [ + "log", + "regex", +] + +[[package]] +name = "env_logger" +version = "0.11.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e13fa619b91fb2381732789fc5de83b45675e882f66623b7d8cb4f643017018d" +dependencies = [ + "anstream", + "anstyle", + "env_filter", + "humantime", + "log", +] + [[package]] name = "getrandom" version = "0.2.11" @@ -19,16 +106,42 @@ dependencies = [ "wasi", ] +[[package]] +name = "humantime" +version = "2.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4" + +[[package]] +name = "is_terminal_polyfill" +version = "1.70.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf" + [[package]] name = "libc" version = "0.2.151" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "302d7ab3130588088d277783b1e2d2e10c9e9e4a16dd9050e6ec93fb3e7048f4" +[[package]] +name = "log" +version = "0.4.22" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24" + +[[package]] +name = "memchr" +version = "2.7.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" + [[package]] name = "multimarkov" -version = "0.5.0" +version = "1.0.0" dependencies = [ + "env_logger", + "log", "rand", ] @@ -68,8 +181,116 @@ dependencies = [ "getrandom", ] +[[package]] +name = "regex" +version = "1.10.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4219d74c6b67a3654a9fbebc4b419e22126d13d2f3c4a07ee0cb61ff79a79619" +dependencies = [ + "aho-corasick", + "memchr", + "regex-automata", + "regex-syntax", +] + +[[package]] +name = "regex-automata" +version = "0.4.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df" +dependencies = [ + "aho-corasick", + "memchr", + "regex-syntax", +] + +[[package]] +name = "regex-syntax" +version = "0.8.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b" + +[[package]] +name = "utf8parse" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" + [[package]] name = "wasi" version = "0.11.0+wasi-snapshot-preview1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" + +[[package]] +name = "windows-sys" +version = "0.52.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d" +dependencies = [ + "windows-targets", +] + +[[package]] +name = "windows-targets" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" +dependencies = [ + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", + "windows_i686_gnullvm", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" + +[[package]] +name = "windows_i686_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" + +[[package]] +name = "windows_i686_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" diff --git a/Cargo.toml b/Cargo.toml index 88e1a05..c557192 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -12,7 +12,7 @@ [package] edition = "2021" name = "multimarkov" -version = "0.5.0" +version = "1.0.0" authors = ["joeclark-phd "] description = """ This is a generic tool for training and using multi-order Markov chains for procedural generation applications @@ -22,6 +22,12 @@ readme = "README.md" license = "MIT" repository = "https://github.com/joeclark-phd/multimarkov" +[dependencies] +log = "0.4.22" + [dependencies.rand] version = "0.8.5" features = [ "small_rng" ] + +[dev-dependencies] +env_logger = "0.11.5" diff --git a/README.md b/README.md index 28f5110..194846f 100644 --- a/README.md +++ b/README.md @@ -56,6 +56,8 @@ is much more likely to draw `'f'` because it has trained a model for what comes ## Release notes: +**1.0.0**: Replaced `println`s with logging using the `log` crate. Added logging of the number of known states and trained sequences within the `add_priors` function on `MultiMarkovBuilder`. It turns out that that step can really explode if you have a large dataset, so this logging may be helpful downstream. Also: moved the binary target (`main.rs`) into the "examples" directory. Run it with `cargo run --example main`. + 0.5.0: MultiMarkov now implements `Debug` 0.4.0: The addition of a method `with_rng()` on the builder allows you to add a custom RNG, for example, if you want to use a random number seed. Thanks RicardRC. diff --git a/src/main.rs b/examples/main.rs similarity index 91% rename from src/main.rs rename to examples/main.rs index fefb7aa..ac11bae 100644 --- a/src/main.rs +++ b/examples/main.rs @@ -1,11 +1,14 @@ -mod builder; - use multimarkov::MultiMarkov; use rand::{rngs::SmallRng, SeedableRng}; use std::fs::File; use std::io::{BufRead, BufReader}; fn main() { + + // initialize logging + env_logger::builder().filter_level(log::LevelFilter::Debug).init(); + + let file = File::open("resources/romans.txt").unwrap(); let reader = BufReader::new(file); let lines = reader diff --git a/src/builder.rs b/src/builder.rs index 3ddec07..e510747 100644 --- a/src/builder.rs +++ b/src/builder.rs @@ -1,4 +1,5 @@ use crate::MultiMarkov; +use log::{debug, info}; use rand::{thread_rng, RngCore}; use std::cmp::max; use std::collections::{BTreeMap, HashMap, HashSet}; @@ -80,8 +81,8 @@ where Err(_) => error_count += 1, }; } - println!( - "{} sequences successfully trained; {} errors", + debug!( + "{} sequences successfully trained; {} errors.", success_count, error_count ); self @@ -90,7 +91,7 @@ where /// Learn all the transitions possible from one training sequence, adding observations to the Markov model. fn train_sequence(&mut self, sequence: Vec) -> Result<(), &str> { if sequence.len() < 2 { - return Err("sequence was too short, must contain at least two states"); + return Err("Sequence was too short, must contain at least two states."); } // loop backwards through the characters in the sequence @@ -141,13 +142,15 @@ where /// Should be called after training is complete, because only then do we know the full set of /// known states, and which transitions are unobserved. fn add_priors(&mut self) { + let mut num_priors_added: usize = 0; match self.prior { Some(p) => { for v in self.markov_chain.values_mut() { for a in self.known_states.iter() { - v.entry(a.clone()).or_insert(p); + v.entry(a.clone()).or_insert_with(|| {num_priors_added+=1; p}); } } + info!("Model has {} known states and {} trained sequences. {} priors added.",self.markov_chain.len(),self.known_states.len(),num_priors_added); } None => (), }