East Py Datascience

East Data Science

Data science and machine learning platform functions for the East language. Provides optimization, ML models, preprocessing, and explainability.

Quick Start

import { East, FloatType, variant } from "@elaraai/east";
import { MADS } from "@elaraai/east-py-datascience";

// Define objective function
const objective = East.function([MADS.Types.VectorType], FloatType, ($, x) => {
    const x0 = $.let(x.get(0n));
    const x1 = $.let(x.get(1n));
    return $.return(x0.multiply(x0).add(x1.multiply(x1)));
});

// Optimize
const optimize = East.function([], MADS.Types.ResultType, $ => {
    const x0 = $.let([0.5, 0.5]);
    const bounds = $.let({ lower: [-1.0, -1.0], upper: [1.0, 1.0] });
    const config = $.let({
        max_bb_eval: variant('some', 100n),
        display_degree: variant('some', 0n),
        direction_type: variant('none', null),
        initial_mesh_size: variant('none', null),
        min_mesh_size: variant('none', null),
        seed: variant('some', 42n),
    });
    return $.return(MADS.optimize(objective, x0, bounds, variant('none', null), config));
});

Decision Tree: Which Module to Use

Task → What do you need?
    │
    ├─ MADS (derivative-free continuous optimization)
    │   └─ .optimize()
    │
    ├─ Optuna (Bayesian hyperparameter tuning)
    │   └─ .optimize()
    │
    ├─ SimAnneal (discrete/combinatorial optimization)
    │   └─ .optimize(), .optimizePermutation(), .optimizeSubset()
    │
    ├─ ALNS (adaptive large neighborhood search)
    │   └─ .optimize([SolutionType], initial, objective, destroys, repairs, config)
    │   └─ Generic over solution type S - define your own struct
    │
    ├─ Scipy
    │   ├─ Optimization → .optimizeMinimize(), .optimizeMinimizeQuadratic(), .optimizeDualAnnealing()
    │   ├─ Statistics → .statsDescribe(), .statsPearsonr(), .statsSpearmanr(), .statsPercentile(), .statsIqr(), .statsMedian(), .statsMad(), .statsRobust()
    │   ├─ Curve Fitting → .curveFit()
    │   └─ Interpolation → .interpolate1dFit(), .interpolate1dPredict()
    │
    ├─ XGBoost (gradient boosting)
    │   ├─ Train → .trainRegressor(), .trainClassifier(), .trainQuantile()
    │   └─ Predict → .predict(), .predictClass(), .predictProba(), .predictQuantile()
    │
    ├─ LightGBM (fast gradient boosting)
    │   ├─ Train → .trainRegressor(), .trainClassifier()
    │   └─ Predict → .predict(), .predictClass(), .predictProba()
    │
    ├─ NGBoost (probabilistic gradient boosting)
    │   ├─ Train → .trainRegressor()
    │   └─ Predict → .predict(), .predictDist()
    │
    ├─ Torch (neural networks)
    │   ├─ Train → .mlpTrain(), .mlpTrainMulti()
    │   ├─ Predict → .mlpPredict(), .mlpPredictMulti()
    │   └─ Embeddings → .mlpEncode(), .mlpDecode()
    │
    ├─ Lightning (PyTorch Lightning neural networks)
    │   ├─ Train → .train(X, y, config, masks, group_weights, conditions)
    │   ├─ Predict → .predict(model, X, masks, conditions)
    │   ├─ Embeddings → .encode(), .decode(), .decodeConditional() (autoencoder only)
    │   ├─ Architectures:
    │   │   ├─ mlp: simple feedforward
    │   │   ├─ autoencoder: encoder → latent → decoder
    │   │   ├─ conv1d: 1D convolutional autoencoder (temporal)
    │   │   ├─ sequential: LSTM/GRU autoencoder (temporal)
    │   │   └─ transformer: attention-based autoencoder (temporal)
    │   ├─ Output modes:
    │   │   ├─ regression: MSE loss
    │   │   ├─ binary: BCE loss, per-position pos_weights (VectorType), masks
    │   │   └─ multi_head: N independent CE heads, per-head class_weights, masks
    │   ├─ Conditional generation: condition_dim in temporal architectures
    │   └─ Features: early stopping, gradient clipping, epoch callbacks, group_weights
    │
    ├─ GP (Gaussian Process regression)
    │   ├─ Train → .train()
    │   └─ Predict → .predict(), .predictStd()
    │
    ├─ MAPIE (conformal prediction intervals)
    │   ├─ Regression → .trainConformalRegressor(), .trainCQR()
    │   ├─ Classification → .trainConformalClassifier()
    │   ├─ Predict → .predictInterval(), .predictSet()
    │   └─ SHAP integration → .uncertaintyPredictorRegressor(), .uncertaintyPredictorClassifier()
    │
    ├─ Sklearn (preprocessing & metrics)
    │   ├─ Splitting (with stratification and rare class filtering) → .trainTestSplit(), .trainValTestSplit()
    │   ├─ Scaling → .standardScalerFit/Transform(), .minMaxScalerFit/Transform(), .robustScalerFit/Transform()
    │   ├─ Encoding → .labelEncoderFit/Transform/InverseTransform(), .ordinalEncoderFit/Transform()
    │   ├─ Class weights → .computeClassWeight()
    │   ├─ Regression metrics → .computeMetrics(), .computeMetricsMulti()
    │   ├─ Classification metrics → .computeClassificationMetrics(), .computeClassificationMetricsMulti()
    │   ├─ Probability metrics → .rocAucScore(), .logLoss(), .confusionMatrix()
    │   └─ Multi-target → .regressorChainTrain(), .regressorChainPredict()
    │
    └─ Shap (model explainability)
        ├─ Create → .treeExplainerCreate() (XGBoost only), .kernelExplainerCreate() (any model)
        ├─ Compute → .computeValues(), .featureImportance()
        └─ Supports → TreeExplainer: XGBoost; KernelExplainer: XGBoost, LightGBM, NGBoost, GP, Torch, RegressorChain, MAPIE

Common Types

Reference Documentation

• API Reference - Complete function signatures, types, and config options
• Examples - Working code examples by use case

Available Modules

Accessing Types

import { MADS, Optuna, Sklearn, XGBoost, ALNS } from "@elaraai/east-py-datascience";

// Access types via Module.Types.TypeName
MADS.Types.VectorType          // ArrayType(FloatType)
MADS.Types.BoundsType          // StructType({ lower, upper })
MADS.Types.ResultType          // StructType({ x_best, f_best, ... })

Optuna.Types.ParamSpaceType    // Parameter definition
Optuna.Types.StudyResultType   // Optimization result

ALNS.Types.ConfigType          // ALNS configuration
ALNS.Types.ResultType          // Result with "S" placeholder for solution type

Sklearn.Types.SplitConfigType  // Train/test split config
XGBoost.Types.ModelBlobType    // Trained model

Common Patterns

Train and Predict

// 1. Prepare data
const X = $.let([[...], [...], ...]);
const y = $.let([...]);

// 2. Configure and train
const config = $.let({ /* options with variant('some', value) or variant('none', null) */ });
const model = $.let(Module.train(X, y, config));

// 3. Predict
const predictions = $.let(Module.predict(model, X_test));

Optimization

// 1. Define objective function
const objective = East.function([VectorType], FloatType, ($, x) => {
    // compute and return objective value
});

// 2. Set bounds and config
const bounds = $.let({ lower: [...], upper: [...] });
const config = $.let({ /* options */ });

// 3. Optimize
const result = $.let(Module.optimize(objective, x0, bounds, config));
// result.x_best, result.f_best