initial commit

.envrc

@@ -0,0 +1 @@
+use flake

.gitignore

@@ -0,0 +1,6 @@
+model-out
+.direnv
+
+# Added by cargo
+
+/target

Cargo.lock

@@ -0,0 +1,43 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "cc"
+version = "1.2.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a012a0df96dd6d06ba9a1b29d6402d1a5d77c6befd2566afdc26e10603dc93d7"
+dependencies = [
+ "shlex",
+]
+
+[[package]]
+name = "cfasttext-sys"
+version = "0.7.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "982185af4edba23861639c25e46b36e077d2d60e553c20d1341c9fbf17fdb369"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "fasttext"
+version = "0.7.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd26f3978ff7b22e594af9026912da644237fd7d360889d0c5a6ac8ec4f940c8"
+dependencies = [
+ "cfasttext-sys",
+]
+
+[[package]]
+name = "fasttext-classifier"
+version = "0.1.0"
+dependencies = [
+ "fasttext",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"

Cargo.toml

@@ -0,0 +1,7 @@
+[package]
+name = "fasttext-classifier"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]
+fasttext = "0.7.8"

data/readme.txt

@@ -0,0 +1,17 @@
+The data in this archive is derived from the user-contributed content on the
+Cooking Stack Exchange website (https://cooking.stackexchange.com/), used under
+CC-BY-SA 3.0 (http://creativecommons.org/licenses/by-sa/3.0/).
+
+The original data dump can be downloaded from:
+https://archive.org/download/stackexchange/cooking.stackexchange.com.7z
+and details about the dump obtained from:
+https://archive.org/details/stackexchange
+
+We distribute two files, under CC-BY-SA 3.0:
+
+ - cooking.stackexchange.txt, which contains all question titles and
+   their associated tags (one question per line, tags are prefixed by
+   the string "__label__") ;
+
+ - cooking.stackexchange.id, which contains the corresponding row IDs,
+   from the original data dump.

flake.lock

@@ -0,0 +1,43 @@
+{
+  "nodes": {
+    "crane": {
+      "locked": {
+        "lastModified": 1736101677,
+        "narHash": "sha256-iKOPq86AOWCohuzxwFy/MtC8PcSVGnrxBOvxpjpzrAY=",
+        "owner": "ipetkov",
+        "repo": "crane",
+        "rev": "61ba163d85e5adeddc7b3a69bb174034965965b2",
+        "type": "github"
+      },
+      "original": {
+        "owner": "ipetkov",
+        "repo": "crane",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1736012469,
+        "narHash": "sha256-/qlNWm/IEVVH7GfgAIyP6EsVZI6zjAx1cV5zNyrs+rI=",
+        "owner": "nixos",
+        "repo": "nixpkgs",
+        "rev": "8f3e1f807051e32d8c95cd12b9b421623850a34d",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nixos",
+        "ref": "nixos-unstable",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "crane": "crane",
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,59 @@
+{
+  description = "Fasttext experiments";
+
+  inputs = {
+    nixpkgs.url = "github:nixos/nixpkgs/nixos-unstable";
+    crane.url = "github:ipetkov/crane";
+  };
+
+  outputs =
+    {
+      self,
+      nixpkgs,
+      crane,
+    }:
+    let
+      systems = [
+        "x86_64-linux"
+        "aarch64-linux"
+        "aarch64-darwin"
+        "x86_64-darwin"
+      ];
+      forAllSystems = nixpkgs.lib.genAttrs systems;
+    in
+    {
+      packages = forAllSystems (
+        system:
+        let
+          pkgs = import nixpkgs { inherit system; };
+          craneLib = crane.mkLib pkgs;
+        in
+        {
+          default = craneLib.buildPackage {
+            src = craneLib.cleanCargoSource ./.;
+
+            buildInputs = with pkgs; [
+              fasttext
+            ];
+          };
+        }
+      );
+      devShells = forAllSystems (
+        system:
+        let
+          pkgs = import nixpkgs { inherit system; };
+          craneLib = crane.mkLib pkgs;
+        in
+        {
+          default = craneLib.devShell {
+            inputsFrom = [ self.packages.${system}.default ];
+
+            packages = with pkgs; [
+              clippy
+              rust-analyzer
+            ];
+          };
+        }
+      );
+    };
+}

src/main.rs

@@ -0,0 +1,30 @@
+use std::path::Path;
+
+use fasttext::{Args, FastText, LossName, ModelName};
+
+fn train_cooking_model() -> Result<(), String> {
+    let mut args = Args::new();
+    args.set_input("../data/cooking.train").unwrap();
+    args.set_model(ModelName::SUP);
+    args.set_lr(1.0);
+    args.set_epoch(25);
+    //args.set_loss(LossName::SOFTMAX);
+    let mut ft_model = FastText::new();
+    ft_model.train(&args).unwrap();
+
+    ft_model.save_model("../model-out/out.bin")
+}
+
+fn test_cooking_model(filename: &Path) -> Vec<fasttext::Prediction> {
+    let mut text = FastText::new();
+
+    let _ = text.load_model(filename.to_str().unwrap());
+    text.predict("Safe temperatures to bake cookies at?", 3, 0.2)
+        .unwrap()
+}
+
+fn main() {
+    //train_cooking_model().unwrap();
+    let result = test_cooking_model(Path::new("../model-out/out.bin"));
+    println!("{:?}", result);
+}