From 2174d4e506a92850cdae9ce80bab3c0519af00b1 Mon Sep 17 00:00:00 2001 From: Priec Date: Thu, 12 Mar 2026 15:20:07 +0100 Subject: [PATCH] working pca_first --- hod_1/Cargo.lock | 729 +++++++++++++++++++++++++++++++++++++++++++++- hod_1/Cargo.toml | 2 + hod_1/src/lib.rs | 96 +++--- hod_1/src/main.rs | 86 +++++- 4 files changed, 844 insertions(+), 69 deletions(-) diff --git a/hod_1/Cargo.lock b/hod_1/Cargo.lock index 50845fd..4036701 100644 --- a/hod_1/Cargo.lock +++ b/hod_1/Cargo.lock @@ -17,6 +17,17 @@ version = "2.0.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa" +[[package]] +name = "aes" +version = "0.8.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0" +dependencies = [ + "cfg-if", + "cipher", + "cpufeatures", +] + [[package]] name = "ahash" version = "0.8.12" @@ -103,6 +114,12 @@ dependencies = [ "windows-sys", ] +[[package]] +name = "anyhow" +version = "1.0.102" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c" + [[package]] name = "arrayvec" version = "0.7.6" @@ -157,6 +174,12 @@ dependencies = [ "windows-link", ] +[[package]] +name = "base64ct" +version = "1.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2af50177e190e07a26ab74f8b1efbfe2ef87da2116221318cb1c2e82baf7de06" + [[package]] name = "bincode" version = "2.0.1" @@ -197,6 +220,15 @@ version = "0.1.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0d8c1fef690941d3e7788d328517591fecc684c084084702d6ff1641e993699a" +[[package]] +name = "block-buffer" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71" +dependencies = [ + "generic-array", +] + [[package]] name = "bumpalo" version = "3.20.2" @@ -395,6 +427,12 @@ dependencies = [ "syn", ] +[[package]] +name = "byteorder" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" + [[package]] name = "bytes" version = "1.11.1" @@ -404,6 +442,47 @@ dependencies = [ "portable-atomic", ] +[[package]] +name = "bzip2" +version = "0.4.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bdb116a6ef3f6c3698828873ad02c3014b3c85cadb88496095628e3ef1e347f8" +dependencies = [ + "bzip2-sys", + "libc", +] + +[[package]] +name = "bzip2" +version = "0.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f3a53fac24f34a81bc9954b5d6cfce0c21e18ec6959f44f56e8e90e4bb7c346c" +dependencies = [ + "libbz2-rs-sys", +] + +[[package]] +name = "bzip2-sys" +version = "0.1.13+1.0.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "225bff33b2141874fe80d71e07d6eec4f85c5c216453dd96388240f96e1acc14" +dependencies = [ + "cc", + "pkg-config", +] + +[[package]] +name = "cc" +version = "1.2.56" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "aebf35691d1bfb0ac386a69bac2fde4dd276fb618cf8bf4f5318fe285e821bb2" +dependencies = [ + "find-msvc-tools", + "jobserver", + "libc", + "shlex", +] + [[package]] name = "cfg-if" version = "1.0.4" @@ -416,6 +495,16 @@ version = "0.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724" +[[package]] +name = "cipher" +version = "0.4.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad" +dependencies = [ + "crypto-common", + "inout", +] + [[package]] name = "clap" version = "4.5.60" @@ -502,6 +591,18 @@ dependencies = [ "tiny-keccak", ] +[[package]] +name = "constant_time_eq" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "245097e9a4535ee1e3e3931fcfcd55a796a44c643e8596ff6566d68f09b87bbc" + +[[package]] +name = "constant_time_eq" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b" + [[package]] name = "convert_case" version = "0.10.0" @@ -538,6 +639,24 @@ dependencies = [ "libc", ] +[[package]] +name = "cpufeatures" +version = "0.2.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280" +dependencies = [ + "libc", +] + +[[package]] +name = "crc32fast" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511" +dependencies = [ + "cfg-if", +] + [[package]] name = "critical-section" version = "1.2.0" @@ -584,6 +703,16 @@ version = "0.2.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5" +[[package]] +name = "crypto-common" +version = "0.1.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a" +dependencies = [ + "generic-array", + "typenum", +] + [[package]] name = "cubecl" version = "0.9.0" @@ -907,6 +1036,21 @@ version = "2.10.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d7a1e2f27636f116493b8b860f5546edb47c8d8f8ea73e1d2a20be88e28d1fea" +[[package]] +name = "deflate64" +version = "0.1.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "807800ff3288b621186fe0a8f3392c4652068257302709c24efd918c3dffcdc2" + +[[package]] +name = "deranged" +version = "0.5.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7cd812cc2bc1d69d4764bd80df88b4317eaef9e773c75226407d9bc0876b211c" +dependencies = [ + "powerfmt", +] + [[package]] name = "derive-new" version = "0.7.0" @@ -941,6 +1085,17 @@ dependencies = [ "unicode-xid", ] +[[package]] +name = "digest" +version = "0.10.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292" +dependencies = [ + "block-buffer", + "crypto-common", + "subtle", +] + [[package]] name = "dirs" version = "6.0.0" @@ -1088,12 +1243,29 @@ version = "2.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be" +[[package]] +name = "find-msvc-tools" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582" + [[package]] name = "fixedbitset" version = "0.4.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80" +[[package]] +name = "flate2" +version = "1.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c" +dependencies = [ + "crc32fast", + "miniz_oxide", + "zlib-rs", +] + [[package]] name = "float-ord" version = "0.3.2" @@ -1203,6 +1375,16 @@ dependencies = [ "slab", ] +[[package]] +name = "generic-array" +version = "0.14.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a" +dependencies = [ + "typenum", + "version_check", +] + [[package]] name = "getrandom" version = "0.2.17" @@ -1222,10 +1404,25 @@ checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd" dependencies = [ "cfg-if", "libc", - "r-efi", + "r-efi 5.3.0", "wasip2", ] +[[package]] +name = "getrandom" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0de51e6874e94e7bf76d726fc5d13ba782deca734ff60d5bb2fb2607c7406555" +dependencies = [ + "cfg-if", + "js-sys", + "libc", + "r-efi 6.0.0", + "wasip2", + "wasip3", + "wasm-bindgen", +] + [[package]] name = "gimli" version = "0.32.3" @@ -1372,6 +1569,15 @@ version = "0.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "dfa686283ad6dd069f105e5ab091b04c62850d3e4cf5d67debad1933f55023df" +[[package]] +name = "hmac" +version = "0.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e" +dependencies = [ + "digest", +] + [[package]] name = "hod_1" version = "0.1.0" @@ -1380,8 +1586,16 @@ dependencies = [ "burn-ndarray", "clap", "ndarray", + "npyz", + "zip 8.2.0", ] +[[package]] +name = "id-arena" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954" + [[package]] name = "ident_case" version = "1.0.1" @@ -1396,6 +1610,17 @@ checksum = "7714e70437a7dc3ac8eb7e6f8df75fd8eb422675fc7678aff7364301092b1017" dependencies = [ "equivalent", "hashbrown 0.16.1", + "serde", + "serde_core", +] + +[[package]] +name = "inout" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "879f10e63c20629ecabbb64a8010319738c66a5cd0c29b02d63d272b03751d01" +dependencies = [ + "generic-array", ] [[package]] @@ -1425,6 +1650,16 @@ version = "0.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8eaf4bc02d17cbdd7ff4c7438cafcdf7fb9a4613313ad11b4f8fefe7d3fa0130" +[[package]] +name = "jobserver" +version = "0.1.34" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33" +dependencies = [ + "getrandom 0.3.4", + "libc", +] + [[package]] name = "js-sys" version = "0.3.91" @@ -1452,6 +1687,18 @@ version = "3.1.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e2db585e1d738fc771bf08a151420d3ed193d9d895a36df7f6f8a9456b911ddc" +[[package]] +name = "leb128fmt" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2" + +[[package]] +name = "libbz2-rs-sys" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2c4a545a15244c7d945065b5d392b2d2d7f21526fba56ce51467b06ed445e8f7" + [[package]] name = "libc" version = "0.2.182" @@ -1504,6 +1751,15 @@ version = "0.4.29" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897" +[[package]] +name = "lzma-rust2" +version = "0.16.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "47bb1e988e6fb779cf720ad431242d3f03167c1b3f2b1aae7f1a94b2495b36ae" +dependencies = [ + "sha2", +] + [[package]] name = "macerator" version = "0.2.10" @@ -1588,6 +1844,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316" dependencies = [ "adler2", + "simd-adler32", ] [[package]] @@ -1662,6 +1919,18 @@ dependencies = [ "jni-sys", ] +[[package]] +name = "npyz" +version = "0.8.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9f0e759e014e630f90af745101b614f761306ddc541681e546649068e25ec1b9" +dependencies = [ + "byteorder", + "num-bigint", + "py_literal", + "zip 0.6.6", +] + [[package]] name = "num" version = "0.4.3" @@ -1695,6 +1964,12 @@ dependencies = [ "num-traits", ] +[[package]] +name = "num-conv" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf97ec579c3c42f953ef76dbf8d55ac91fb219dde70e49aa4a6b7d74e9919050" + [[package]] name = "num-integer" version = "0.1.46" @@ -1820,12 +2095,88 @@ dependencies = [ "windows-link", ] +[[package]] +name = "password-hash" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7676374caaee8a325c9e7a2ae557f216c5563a171d6997b0ef8a65af35147700" +dependencies = [ + "base64ct", + "rand_core 0.6.4", + "subtle", +] + [[package]] name = "paste" version = "1.0.15" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" +[[package]] +name = "pbkdf2" +version = "0.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "83a0692ec44e4cf1ef28ca317f14f8f07da2d95ec3fa01f86e4467b725e60917" +dependencies = [ + "digest", + "hmac", + "password-hash", + "sha2", +] + +[[package]] +name = "pbkdf2" +version = "0.12.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f8ed6a7761f76e3b9f92dfb0a60a6a6477c61024b775147ff0973a02653abaf2" +dependencies = [ + "digest", + "hmac", +] + +[[package]] +name = "pest" +version = "2.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e0848c601009d37dfa3430c4666e147e49cdcf1b92ecd3e63657d8a5f19da662" +dependencies = [ + "memchr", + "ucd-trie", +] + +[[package]] +name = "pest_derive" +version = "2.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "11f486f1ea21e6c10ed15d5a7c77165d0ee443402f0780849d1768e7d9d6fe77" +dependencies = [ + "pest", + "pest_generator", +] + +[[package]] +name = "pest_generator" +version = "2.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8040c4647b13b210a963c1ed407c1ff4fdfa01c31d6d2a098218702e6664f94f" +dependencies = [ + "pest", + "pest_meta", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "pest_meta" +version = "2.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "89815c69d36021a140146f26659a81d6c2afa33d216d736dd4be5381a7362220" +dependencies = [ + "pest", + "sha2", +] + [[package]] name = "petgraph" version = "0.6.5" @@ -1866,6 +2217,18 @@ dependencies = [ "portable-atomic", ] +[[package]] +name = "powerfmt" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391" + +[[package]] +name = "ppmd-rust" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "efca4c95a19a79d1c98f791f10aebd5c1363b473244630bb7dbde1dc98455a24" + [[package]] name = "ppv-lite86" version = "0.2.21" @@ -1906,6 +2269,19 @@ version = "1.0.17" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3eb8486b569e12e2c32ad3e204dbaba5e4b5b216e9367044f25f1dba42341773" +[[package]] +name = "py_literal" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "102df7a3d46db9d3891f178dcc826dc270a6746277a9ae6436f8d29fd490a8e1" +dependencies = [ + "num-bigint", + "num-complex", + "num-traits", + "pest", + "pest_derive", +] + [[package]] name = "quote" version = "1.0.45" @@ -1921,6 +2297,12 @@ version = "5.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f" +[[package]] +name = "r-efi" +version = "6.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf" + [[package]] name = "rand" version = "0.9.2" @@ -1928,7 +2310,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1" dependencies = [ "rand_chacha", - "rand_core", + "rand_core 0.9.5", ] [[package]] @@ -1938,9 +2320,15 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb" dependencies = [ "ppv-lite86", - "rand_core", + "rand_core 0.9.5", ] +[[package]] +name = "rand_core" +version = "0.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c" + [[package]] name = "rand_core" version = "0.9.5" @@ -2175,6 +2563,40 @@ dependencies = [ "serde_core", ] +[[package]] +name = "sha1" +version = "0.10.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3bf829a2d51ab4a5ddf1352d8470c140cadc8301b2ae1789db023f01cedd6ba" +dependencies = [ + "cfg-if", + "cpufeatures", + "digest", +] + +[[package]] +name = "sha2" +version = "0.10.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283" +dependencies = [ + "cfg-if", + "cpufeatures", + "digest", +] + +[[package]] +name = "shlex" +version = "1.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64" + +[[package]] +name = "simd-adler32" +version = "0.3.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e320a6c5ad31d271ad523dcf3ad13e2767ad8b1cb8f047f75a8aeaf8da139da2" + [[package]] name = "slab" version = "0.4.12" @@ -2233,6 +2655,12 @@ version = "0.11.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" +[[package]] +name = "subtle" +version = "2.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292" + [[package]] name = "syn" version = "2.0.117" @@ -2302,6 +2730,26 @@ dependencies = [ "crossbeam-channel", ] +[[package]] +name = "time" +version = "0.3.47" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "743bd48c283afc0388f9b8827b976905fb217ad9e647fae3a379a9283c4def2c" +dependencies = [ + "deranged", + "js-sys", + "num-conv", + "powerfmt", + "serde_core", + "time-core", +] + +[[package]] +name = "time-core" +version = "0.1.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7694e1cfe791f8d31026952abf09c69ca6f6fa4e1a1229e18988f06a04a12dca" + [[package]] name = "tiny-keccak" version = "2.0.2" @@ -2359,6 +2807,24 @@ dependencies = [ "rustc-hash 2.1.1", ] +[[package]] +name = "typed-path" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e28f89b80c87b8fb0cf04ab448d5dd0dd0ade2f8891bae878de66a75a28600e" + +[[package]] +name = "typenum" +version = "1.19.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb" + +[[package]] +name = "ucd-trie" +version = "0.1.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971" + [[package]] name = "unicode-ident" version = "1.0.24" @@ -2439,6 +2905,15 @@ dependencies = [ "wit-bindgen", ] +[[package]] +name = "wasip3" +version = "0.4.0+wasi-0.3.0-rc-2026-01-06" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5428f8bf88ea5ddc08faddef2ac4a67e390b88186c703ce6dbd955e1c145aca5" +dependencies = [ + "wit-bindgen", +] + [[package]] name = "wasm-bindgen" version = "0.2.114" @@ -2498,6 +2973,40 @@ dependencies = [ "unicode-ident", ] +[[package]] +name = "wasm-encoder" +version = "0.244.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "990065f2fe63003fe337b932cfb5e3b80e0b4d0f5ff650e6985b1048f62c8319" +dependencies = [ + "leb128fmt", + "wasmparser", +] + +[[package]] +name = "wasm-metadata" +version = "0.244.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bb0e353e6a2fbdc176932bbaab493762eb1255a7900fe0fea1a2f96c296cc909" +dependencies = [ + "anyhow", + "indexmap", + "wasm-encoder", + "wasmparser", +] + +[[package]] +name = "wasmparser" +version = "0.244.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "47b807c72e1bac69382b3a6fb3dbe8ea4c0ed87ff5629b8685ae6b9a611028fe" +dependencies = [ + "bitflags", + "hashbrown 0.15.5", + "indexmap", + "semver", +] + [[package]] name = "web-sys" version = "0.3.91" @@ -2830,6 +3339,88 @@ name = "wit-bindgen" version = "0.51.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d7249219f66ced02969388cf2bb044a09756a083d0fab1e566056b04d9fbcaa5" +dependencies = [ + "wit-bindgen-rust-macro", +] + +[[package]] +name = "wit-bindgen-core" +version = "0.51.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ea61de684c3ea68cb082b7a88508a8b27fcc8b797d738bfc99a82facf1d752dc" +dependencies = [ + "anyhow", + "heck", + "wit-parser", +] + +[[package]] +name = "wit-bindgen-rust" +version = "0.51.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b7c566e0f4b284dd6561c786d9cb0142da491f46a9fbed79ea69cdad5db17f21" +dependencies = [ + "anyhow", + "heck", + "indexmap", + "prettyplease", + "syn", + "wasm-metadata", + "wit-bindgen-core", + "wit-component", +] + +[[package]] +name = "wit-bindgen-rust-macro" +version = "0.51.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0c0f9bfd77e6a48eccf51359e3ae77140a7f50b1e2ebfe62422d8afdaffab17a" +dependencies = [ + "anyhow", + "prettyplease", + "proc-macro2", + "quote", + "syn", + "wit-bindgen-core", + "wit-bindgen-rust", +] + +[[package]] +name = "wit-component" +version = "0.244.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9d66ea20e9553b30172b5e831994e35fbde2d165325bec84fc43dbf6f4eb9cb2" +dependencies = [ + "anyhow", + "bitflags", + "indexmap", + "log", + "serde", + "serde_derive", + "serde_json", + "wasm-encoder", + "wasm-metadata", + "wasmparser", + "wit-parser", +] + +[[package]] +name = "wit-parser" +version = "0.244.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ecc8ac4bc1dc3381b7f59c34f00b67e18f910c2c0f50015669dde7def656a736" +dependencies = [ + "anyhow", + "id-arena", + "indexmap", + "log", + "semver", + "serde", + "serde_derive", + "serde_json", + "unicode-xid", + "wasmparser", +] [[package]] name = "xml-rs" @@ -2857,8 +3448,140 @@ dependencies = [ "syn", ] +[[package]] +name = "zeroize" +version = "1.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0" +dependencies = [ + "zeroize_derive", +] + +[[package]] +name = "zeroize_derive" +version = "1.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85a5b4158499876c763cb03bc4e49185d3cccbabb15b33c627f7884f43db852e" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "zip" +version = "0.6.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "760394e246e4c28189f19d488c058bf16f564016aefac5d32bb1f3b51d5e9261" +dependencies = [ + "aes", + "byteorder", + "bzip2 0.4.4", + "constant_time_eq 0.1.5", + "crc32fast", + "crossbeam-utils", + "flate2", + "hmac", + "pbkdf2 0.11.0", + "sha1", + "time", + "zstd 0.11.2+zstd.1.5.2", +] + +[[package]] +name = "zip" +version = "8.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b680f2a0cd479b4cff6e1233c483fdead418106eae419dc60200ae9850f6d004" +dependencies = [ + "aes", + "bzip2 0.6.1", + "constant_time_eq 0.4.2", + "crc32fast", + "deflate64", + "flate2", + "getrandom 0.4.2", + "hmac", + "indexmap", + "lzma-rust2", + "memchr", + "pbkdf2 0.12.2", + "ppmd-rust", + "sha1", + "time", + "typed-path", + "zeroize", + "zopfli", + "zstd 0.13.3", +] + +[[package]] +name = "zlib-rs" +version = "0.6.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3be3d40e40a133f9c916ee3f9f4fa2d9d63435b5fbe1bfc6d9dae0aa0ada1513" + [[package]] name = "zmij" version = "1.0.21" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa" + +[[package]] +name = "zopfli" +version = "0.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f05cd8797d63865425ff89b5c4a48804f35ba0ce8d125800027ad6017d2b5249" +dependencies = [ + "bumpalo", + "crc32fast", + "log", + "simd-adler32", +] + +[[package]] +name = "zstd" +version = "0.11.2+zstd.1.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "20cc960326ece64f010d2d2107537f26dc589a6573a316bd5b1dba685fa5fde4" +dependencies = [ + "zstd-safe 5.0.2+zstd.1.5.2", +] + +[[package]] +name = "zstd" +version = "0.13.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a" +dependencies = [ + "zstd-safe 7.2.4", +] + +[[package]] +name = "zstd-safe" +version = "5.0.2+zstd.1.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1d2a5585e04f9eea4b2a3d1eca508c4dee9592a89ef6f450c11719da0726f4db" +dependencies = [ + "libc", + "zstd-sys", +] + +[[package]] +name = "zstd-safe" +version = "7.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d" +dependencies = [ + "zstd-sys", +] + +[[package]] +name = "zstd-sys" +version = "2.0.16+zstd.1.5.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "91e19ebc2adc8f83e43039e79776e3fda8ca919132d68a1fed6a5faca2683748" +dependencies = [ + "cc", + "pkg-config", +] diff --git a/hod_1/Cargo.toml b/hod_1/Cargo.toml index 1bb129e..3422d2d 100644 --- a/hod_1/Cargo.toml +++ b/hod_1/Cargo.toml @@ -8,3 +8,5 @@ burn = { version = "0.20.1", default-features = false, features = ["ndarray"] } burn-ndarray = "0.20.1" clap = { version = "4.5.60", features = ["derive"] } ndarray = "0.17.2" +npyz = { version = "0.8.4", features = ["npz"] } +zip = { version = "8.2.0", features = ["deflate"] } diff --git a/hod_1/src/lib.rs b/hod_1/src/lib.rs index 1af3c55..0825363 100644 --- a/hod_1/src/lib.rs +++ b/hod_1/src/lib.rs @@ -1,63 +1,57 @@ use burn::tensor::Tensor; -use std::collections::HashMap; -use std::fs::File; -use std::io::{BufRead, BufReader}; +use burn::tensor::linalg::diag; +use burn::tensor::Shape; pub type B = burn_ndarray::NdArray; -// Funkcia na načítanie a zarovnanie dát -pub fn load_and_align(data_path: &str, model_path: &str) -> (Vec, Vec) { - let mut counts = HashMap::new(); - let mut total_count = 0.0; - - let file_p = File::open(data_path).expect("Nepodarilo sa otvoriť dáta"); - for line in BufReader::new(file_p).lines() { - let point = line.unwrap().trim().to_string(); - if point.is_empty() { continue; } - *counts.entry(point).or_insert(0.0) += 1.0; - total_count += 1.0; - } - - let mut model_map = HashMap::new(); - let file_q = File::open(model_path).expect("Nepodarilo sa otvoriť model"); - for line in BufReader::new(file_q).lines() { - let l = line.unwrap(); - let parts: Vec<&str> = l.split('\t').collect(); - if parts.len() >= 2 { - model_map.insert(parts[0].to_string(), parts[1].parse::().unwrap()); - } - } - - let mut p_vals = Vec::new(); - let mut q_vals = Vec::new(); - for (point, count) in counts.iter() { - p_vals.push(count / total_count); - q_vals.push(*model_map.get(point).unwrap_or(&0.0)); - } - (p_vals, q_vals) +fn l2_norm(v: Tensor) -> f64 { + v.clone() + .mul(v) // element-wise: v_i * v_i + .sum() // suma všetkých v_i^2 + .sqrt() // odmocnina + .into_scalar() // na f32 } -pub fn entropy(p: Tensor) -> f64 { - let zero_mask = p.clone().equal_elem(0.0); - let p_safe = p.clone().mask_fill(zero_mask, 1.0); - let terms = p * p_safe.log(); - -terms.sum().into_scalar() +/// Input: [N, 784], Output: [N, 784] +pub fn center(x: Tensor) -> Tensor { + let mean = x.clone().mean_dim(0); + x.sub(mean) } -pub fn cross_entropy(p: Tensor, q: Tensor) -> f64 { - let zero_mask_q = q.clone().equal_elem(0.0); - let p_exists = p.clone().greater_elem(0.0); - if p_exists.bool_and(zero_mask_q.clone()).any().into_scalar() { - return f64::INFINITY; +/// Input: [N, 784], Output: [784, 784] +pub fn covariance(x: Tensor) -> Tensor { + let cen = center(x); + let transpose = cen.clone().transpose(); + let n = cen.dims()[0] as f64; + let mul = transpose.matmul(cen); + mul.div_scalar(n - 1.0) + +} + +pub fn total_variance(x: Tensor) -> f64 { + let cov: Tensor = covariance(x); + let diag: Tensor = diag(cov); + let sum = diag.sum().into_scalar(); + sum +} + +/// Input: [784, 784], scalar, Output: [784] +pub fn power_iteration(cov: Tensor, iterations: usize) -> (Tensor, f64) { + let n = cov.dims()[0]; + let device = cov.device(); + let mut v: Tensor = Tensor::ones(Shape::new([n]), &device); + let mut s: f64 = 0.0; + + for _ in 0..iterations { + let v_new_2d = cov.clone().matmul(v.reshape([n, 1])); + let v_new = v_new_2d.squeeze::<1>(); + s = l2_norm(v_new.clone()); + v = v_new.div_scalar(s); } - let q_safe = q.mask_fill(zero_mask_q, 1.0); - let terms = p * q_safe.log(); - -terms.sum().into_scalar() + return (v, s); } -pub fn kl_div2(p: Tensor, q: Tensor) -> f64 { - let ce = cross_entropy(p.clone(), q); - let e = entropy(p); - let result = ce - e; - if result < 0.0 { 0.0 } else { result } +/// Input: [784, 784], [784], Output: f32 +pub fn explained_variance(total_var: f64, s: f64) -> f64 { + s / total_var } diff --git a/hod_1/src/main.rs b/hod_1/src/main.rs index 4ca358c..2924483 100644 --- a/hod_1/src/main.rs +++ b/hod_1/src/main.rs @@ -1,30 +1,86 @@ -use burn::tensor::{backend::Backend, Tensor}; +use burn::tensor::backend::Backend; +use burn::tensor::Tensor; use clap::Parser; -// Nahraď 'hod_1' názvom tvojho projektu v Cargo.toml -use hod_1::{load_and_align, entropy, cross_entropy, kl_div2, B}; +use hod_1::{covariance, explained_variance, power_iteration, total_variance, B}; +use std::fs::File; +use std::io::Read; #[derive(Parser, Debug)] #[command(author, version, about, long_about = None)] struct Args { - #[arg(long = "data_path")] - data_path: String, + #[arg(long = "examples", default_value = "1024")] + examples: usize, + #[arg(long = "iterations", default_value = "64")] + iterations: usize, +} - #[arg(long = "model_path")] - model_path: String, +fn load_mnist(examples: usize, device: &::Device) -> Tensor { + let file = File::open("mnist.npz").expect("Cannot open mnist.npz"); + let mut archive = zip::ZipArchive::new(file).expect("Cannot read zip"); + + // Print all available array names so you can see what's inside + eprintln!("Arrays in mnist.npz:"); + for i in 0..archive.len() { + eprintln!(" {}", archive.by_index(i).unwrap().name()); + } + + // Try the most common key names used for MNIST train images + let candidates = [ + "train_images.npy", + "train.images.npy", + "x_train.npy", + "images.npy", + ]; + + let mut bytes = Vec::new(); + let mut found_name = ""; + for name in &candidates { + if archive.by_name(name).is_ok() { + archive + .by_name(name) + .unwrap() + .read_to_end(&mut bytes) + .expect("Failed to read entry"); + found_name = name; + break; + } + } + assert!(!bytes.is_empty(), "Could not find train images — check the printed names above and update candidates[]"); + eprintln!("Loaded from: {found_name}"); + + // Parse the .npy header to get the shape + let npy = npyz::NpyFile::new(&bytes[..]).expect("Cannot parse npy"); + let shape = npy.shape().to_vec(); + eprintln!("Raw array shape: {shape:?}"); + + // MNIST is stored as uint8 (0–255); we normalise to [0.0, 1.0] + let raw: Vec = npy.into_vec().expect("Failed to read as u8 — dtype mismatch?"); + + let n = examples.min(shape[0] as usize); + let pixels = raw.len() / shape[0] as usize; // 784 = 1*28*28, regardless of how axes are ordered + + let data: Vec = raw[..n * pixels] + .iter() + .map(|&p| p as f64 / 255.0) + .collect(); + + eprintln!("Loaded {n} examples, {pixels} pixels each"); + + let tensor_data = burn::tensor::TensorData::new(data, [n, pixels]); + Tensor::::from_data(tensor_data, device) } fn main() { let args = Args::parse(); let device = ::Device::default(); - // Použijeme funkciu z lib.rs - let (p_vec, q_vec) = load_and_align(&args.data_path, &args.model_path); + let x = load_mnist(args.examples, &device); - let p = Tensor::::from_data(p_vec.as_slice(), &device); - let q = Tensor::::from_data(q_vec.as_slice(), &device); + let cov = covariance(x.clone()); + let total_var = total_variance(x.clone()); + let (_pc, s) = power_iteration(cov, args.iterations); + let ev = explained_variance(total_var, s); - // Výpočty - println!("{}", entropy(p.clone())); - println!("{}", cross_entropy(p.clone(), q.clone())); - println!("{}", kl_div2(p, q)); + println!("Total variance: {:.2}", total_var); + println!("Explained variance: {:.2}%", 100.0 * ev); }