The Tangram Rust crate makes it easy to make predictions with your Tangram machine learning model from Rust.
toml
[dependencies]
tangram = { version = "*" }
```rust let model: tangram::Model = tangram::Model::from_path("examples/heart-disease.tangram", None).unwrap();
let input = tangram::predict_input! { "age": 63.0, "gender": "male", // ... };
let output = model.predict_one(input, None); ```
For more information, read the docs.
Tangram for Rust is currently supported on Linux, macOS, and Windows with AMD64 CPUs. Are you interested in another platform? Open an issue or send us an email at help@tangram.xyz.
The source for this crate contains two examples, examples/basic.rs and examples/advanced.rs.
The basic example demonstrates loading a model from a .tangram file and making a prediction.
To run the example:
$ cargo run --example basic
The advanced example demonstrates logging predictions and true values to the Tangram app. Before running the example, run tangram app to start the app running locally, open http://localhost:8080 in your browser, and upload the file examples/heart_disease.tangram to it.
To run the example:
$ TANGRAM_URL=http://localhost:8080 cargo run --example advanced
Now if you refresh the production stats or production metrics tabs for the model you uploaded, you should see predictions and true values.
For more information, read the docs.