ins-pricing 0.4.4__py3-none-any.whl → 0.5.0__py3-none-any.whl

ins_pricing/modelling/__init__.py

@@ -1,95 +1,150 @@
-from __future__ import annotations
-
-from importlib import import_module
-from pathlib import Path
-import sys
-import types
-
-# Keep imports lazy to avoid hard dependencies when only using lightweight modules.
-
-__all__ = [
-    "BayesOptConfig",
-    "BayesOptModel",
-    "IOUtils",
-    "TrainingUtils",
-    "free_cuda",
-    "bayesopt",
-    "plotting",
-    "explain",
-]
-
-_LAZY_ATTRS = {
-    "bayesopt": "ins_pricing.modelling.core.bayesopt",
-    "plotting": "ins_pricing.modelling.plotting",
-    "explain": "ins_pricing.modelling.explain",
-    "BayesOptConfig": "ins_pricing.modelling.core.bayesopt.core",
-    "BayesOptModel": "ins_pricing.modelling.core.bayesopt.core",
-    "IOUtils": "ins_pricing.modelling.core.bayesopt.utils",
-    "TrainingUtils": "ins_pricing.modelling.core.bayesopt.utils",
-    "free_cuda": "ins_pricing.modelling.core.bayesopt.utils",
-}
-
+from __future__ import annotations
+
+from importlib import import_module
+from pathlib import Path
+import sys
+import types
+
+# Keep imports lazy to avoid hard dependencies when only using lightweight modules.
+
+__all__ = sorted(
+    {
+        "BayesOptConfig",
+        "BayesOptModel",
+        "bayesopt",
+        "plotting",
+        "explain",
+        "evaluation",
+        "cli",
+    }
+)
+
+_LAZY_ATTRS = {
+    "bayesopt": "ins_pricing.modelling.bayesopt",
+    "plotting": "ins_pricing.modelling.plotting",
+    "explain": "ins_pricing.modelling.explain",
+    "BayesOptConfig": "ins_pricing.modelling.bayesopt.core",
+    "BayesOptModel": "ins_pricing.modelling.bayesopt.core",
+}
+
+_BAYESOPT_EXPORTS = {
+    "BayesOptConfig",
+    "DatasetPreprocessor",
+    "OutputManager",
+    "VersionManager",
+    "BayesOptModel",
+    "FeatureTokenizer",
+    "FTTransformerCore",
+    "FTTransformerSklearn",
+    "GraphNeuralNetSklearn",
+    "MaskedTabularDataset",
+    "ResBlock",
+    "ResNetSequential",
+    "ResNetSklearn",
+    "ScaledTransformerEncoderLayer",
+    "SimpleGraphLayer",
+    "SimpleGNN",
+    "TabularDataset",
+    "FTTrainer",
+    "GLMTrainer",
+    "GNNTrainer",
+    "ResNetTrainer",
+    "TrainerBase",
+    "XGBTrainer",
+    "_xgb_cuda_available",
+}
+
+_LEGACY_EXPORTS = {
+    "IOUtils": "ins_pricing.utils",
+    "DeviceManager": "ins_pricing.utils",
+    "GPUMemoryManager": "ins_pricing.utils",
+    "MetricFactory": "ins_pricing.utils",
+    "EPS": "ins_pricing.utils",
+    "set_global_seed": "ins_pricing.utils",
+    "compute_batch_size": "ins_pricing.utils",
+    "tweedie_loss": "ins_pricing.utils",
+    "infer_factor_and_cate_list": "ins_pricing.utils",
+    "DistributedUtils": "ins_pricing.modelling.bayesopt.utils",
+    "TrainingUtils": "ins_pricing.modelling.bayesopt.utils",
+    "free_cuda": "ins_pricing.modelling.bayesopt.utils",
+    "TorchTrainerMixin": "ins_pricing.modelling.bayesopt.utils",
+}
+
+__all__ = sorted(set(__all__) | set(_BAYESOPT_EXPORTS) | set(_LEGACY_EXPORTS))
+
 _LAZY_SUBMODULES = {
-    "bayesopt": "ins_pricing.modelling.core.bayesopt",
-    "BayesOpt": "ins_pricing.modelling.core.BayesOpt",
-    "evaluation": "ins_pricing.modelling.core.evaluation",
+    "bayesopt": "ins_pricing.modelling.bayesopt",
+    "evaluation": "ins_pricing.modelling.evaluation",
     "cli": "ins_pricing.cli",
 }
-
-_PACKAGE_PATHS = {
-    "bayesopt": Path(__file__).resolve().parent / "core" / "bayesopt",
-    "cli": Path(__file__).resolve().parents[1] / "cli",
-}
-
-
-def _lazy_module(name: str, target: str, package_path: Path | None = None) -> types.ModuleType:
-    proxy = types.ModuleType(name)
-    if package_path is not None:
-        proxy.__path__ = [str(package_path)]
-
-    def _load():
-        module = import_module(target)
-        sys.modules[name] = module
-        return module
-
-    def __getattr__(attr: str):
-        module = _load()
-        return getattr(module, attr)
-
-    def __dir__() -> list[str]:
-        module = _load()
-        return sorted(set(dir(module)))
-
-    proxy.__getattr__ = __getattr__  # type: ignore[attr-defined]
-    proxy.__dir__ = __dir__  # type: ignore[attr-defined]
-    return proxy
-
-
-def _install_proxy(alias: str, target: str) -> None:
-    module_name = f"{__name__}.{alias}"
-    if module_name in sys.modules:
-        return
-    proxy = _lazy_module(module_name, target, _PACKAGE_PATHS.get(alias))
-    sys.modules[module_name] = proxy
-    globals()[alias] = proxy
-
-
-for _alias, _target in _LAZY_SUBMODULES.items():
-    _install_proxy(_alias, _target)
-
-
-def __getattr__(name: str):
-    target = _LAZY_ATTRS.get(name)
-    if not target:
-        raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-    module = import_module(target)
-    if name in {"bayesopt", "plotting", "explain"}:
-        value = module
-    else:
-        value = getattr(module, name)
-    globals()[name] = value
-    return value
-
-
-def __dir__() -> list[str]:
-    return sorted(set(__all__) | set(globals().keys()))
+
+_PACKAGE_PATHS = {
+    "bayesopt": Path(__file__).resolve().parent / "bayesopt",
+    "cli": Path(__file__).resolve().parents[1] / "cli",
+}
+
+
+def _lazy_module(name: str, target: str, package_path: Path | None = None) -> types.ModuleType:
+    proxy = types.ModuleType(name)
+    if package_path is not None:
+        proxy.__path__ = [str(package_path)]
+
+    def _load():
+        module = import_module(target)
+        sys.modules[name] = module
+        return module
+
+    def __getattr__(attr: str):
+        module = _load()
+        return getattr(module, attr)
+
+    def __dir__() -> list[str]:
+        module = _load()
+        return sorted(set(dir(module)))
+
+    proxy.__getattr__ = __getattr__  # type: ignore[attr-defined]
+    proxy.__dir__ = __dir__  # type: ignore[attr-defined]
+    return proxy
+
+
+def _install_proxy(alias: str, target: str) -> None:
+    module_name = f"{__name__}.{alias}"
+    if module_name in sys.modules:
+        return
+    proxy = _lazy_module(module_name, target, _PACKAGE_PATHS.get(alias))
+    sys.modules[module_name] = proxy
+    globals()[alias] = proxy
+
+
+for _alias, _target in _LAZY_SUBMODULES.items():
+    _install_proxy(_alias, _target)
+
+
+def __getattr__(name: str):
+    target = _LAZY_ATTRS.get(name)
+    if target:
+        module = import_module(target)
+        if name in {"bayesopt", "plotting", "explain"}:
+            value = module
+        else:
+            value = getattr(module, name)
+        globals()[name] = value
+        return value
+
+    if name in _BAYESOPT_EXPORTS:
+        module = import_module("ins_pricing.modelling.bayesopt")
+        value = getattr(module, name)
+        globals()[name] = value
+        return value
+
+    legacy_module = _LEGACY_EXPORTS.get(name)
+    if legacy_module:
+        module = import_module(legacy_module)
+        value = getattr(module, name)
+        globals()[name] = value
+        return value
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+def __dir__() -> list[str]:
+    return sorted(set(__all__) | set(_BAYESOPT_EXPORTS) | set(_LEGACY_EXPORTS) | set(globals().keys()))

ins_pricing/modelling/bayesopt/README.md

@@ -0,0 +1,59 @@
+# BayesOpt
+
+BayesOpt is the training/tuning core for GLM, XGBoost, ResNet, FT-Transformer, and GNN workflows.
+It supports JSON-driven CLI runs and a Python API for notebooks/scripts.
+
+## Recommended API (config-based)
+
+```python
+from ins_pricing.modelling.bayesopt import BayesOptConfig
+from ins_pricing.modelling import BayesOptModel
+
+config = BayesOptConfig(
+    model_nme="my_model",
+    resp_nme="target",
+    weight_nme="weight",
+    factor_nmes=["f1", "f2"],
+    cate_list=["f2"],
+    task_type="regression",
+    epochs=50,
+    output_dir="./Results",
+)
+
+model = BayesOptModel(train_data, test_data, config=config)
+model.optimize_model("xgb", max_evals=50)
+```
+
+## Load config from file
+
+```python
+from ins_pricing.modelling.bayesopt import BayesOptConfig
+from ins_pricing.modelling import BayesOptModel
+
+config = BayesOptConfig.from_file("config.json")
+model = BayesOptModel(train_data, test_data, config=config)
+```
+
+## CLI entry
+
+```bash
+python ins_pricing/cli/BayesOpt_entry.py --config-json config_template.json
+```
+
+## FT roles
+
+- `model`: FT is a prediction model (writes `pred_ft`).
+- `embedding`: FT trains with labels but exports embeddings (`pred_<prefix>_*`).
+- `unsupervised_embedding`: FT trains without labels and exports embeddings.
+
+## Output layout
+
+`output_dir/` contains:
+- `plot/` plots and diagnostics
+- `Results/` metrics, params, and snapshots
+- `model/` saved models
+
+## Notes
+
+- Relative paths in config are resolved from the config file directory.
+- For multi-GPU, use `torchrun` and set `runner.nproc_per_node` in config.

ins_pricing/modelling/{core/bayesopt → bayesopt}/__init__.py

@@ -1,102 +1,64 @@
-"""BayesOpt subpackage (split from monolithic BayesOpt.py)."""
-
-from __future__ import annotations
-
-import torch
-
-from ins_pricing.utils.torch_compat import disable_torch_dynamo_if_requested
-
-disable_torch_dynamo_if_requested()
-
-from .config_preprocess import (
-    BayesOptConfig,
-    DatasetPreprocessor,
-    OutputManager,
-    VersionManager,
-)
-from .core import BayesOptModel
-from .models import (
-    FeatureTokenizer,
-    FTTransformerCore,
-    FTTransformerSklearn,
-    GraphNeuralNetSklearn,
-    MaskedTabularDataset,
-    ResBlock,
-    ResNetSequential,
-    ResNetSklearn,
-    ScaledTransformerEncoderLayer,
-    SimpleGraphLayer,
-    SimpleGNN,
-    TabularDataset,
-)
-from .trainers import (
-    FTTrainer,
-    GLMTrainer,
-    GNNTrainer,
-    ResNetTrainer,
-    TrainerBase,
-    XGBTrainer,
-    _xgb_cuda_available,
-)
-from .utils import (
-    EPS,
-    DistributedUtils,
-    IOUtils,
-    PlotUtils,
-    TorchTrainerMixin,
-    TrainingUtils,
-    compute_batch_size,
-    csv_to_dict,
-    ensure_parent_dir,
-    free_cuda,
-    infer_factor_and_cate_list,
-    plot_dlift_list,
-    plot_lift_list,
-    set_global_seed,
-    split_data,
-    tweedie_loss,
-)
-
-__all__ = [
-    "BayesOptConfig",
-    "DatasetPreprocessor",
-    "OutputManager",
-    "VersionManager",
-    "BayesOptModel",
-    "FeatureTokenizer",
-    "FTTransformerCore",
-    "FTTransformerSklearn",
-    "GraphNeuralNetSklearn",
-    "MaskedTabularDataset",
-    "ResBlock",
-    "ResNetSequential",
-    "ResNetSklearn",
-    "ScaledTransformerEncoderLayer",
-    "SimpleGraphLayer",
-    "SimpleGNN",
-    "TabularDataset",
-    "FTTrainer",
-    "GLMTrainer",
-    "GNNTrainer",
-    "ResNetTrainer",
-    "TrainerBase",
-    "XGBTrainer",
-    "_xgb_cuda_available",
-    "EPS",
-    "DistributedUtils",
-    "IOUtils",
-    "PlotUtils",
-    "TorchTrainerMixin",
-    "TrainingUtils",
-    "compute_batch_size",
-    "csv_to_dict",
-    "ensure_parent_dir",
-    "free_cuda",
-    "infer_factor_and_cate_list",
-    "plot_dlift_list",
-    "plot_lift_list",
-    "set_global_seed",
-    "split_data",
-    "tweedie_loss",
-    "torch",
-]
+"""BayesOpt subpackage (split from monolithic BayesOpt.py)."""
+
+from __future__ import annotations
+
+from ins_pricing.utils.torch_compat import disable_torch_dynamo_if_requested
+
+disable_torch_dynamo_if_requested()
+
+from ins_pricing.modelling.bayesopt.config_preprocess import (
+    BayesOptConfig,
+    DatasetPreprocessor,
+    OutputManager,
+    VersionManager,
+)
+from ins_pricing.modelling.bayesopt.core import BayesOptModel
+from ins_pricing.modelling.bayesopt.models import (
+    FeatureTokenizer,
+    FTTransformerCore,
+    FTTransformerSklearn,
+    GraphNeuralNetSklearn,
+    MaskedTabularDataset,
+    ResBlock,
+    ResNetSequential,
+    ResNetSklearn,
+    ScaledTransformerEncoderLayer,
+    SimpleGraphLayer,
+    SimpleGNN,
+    TabularDataset,
+)
+from ins_pricing.modelling.bayesopt.trainers import (
+    FTTrainer,
+    GLMTrainer,
+    GNNTrainer,
+    ResNetTrainer,
+    TrainerBase,
+    XGBTrainer,
+    _xgb_cuda_available,
+)
+__all__ = [
+    "BayesOptConfig",
+    "DatasetPreprocessor",
+    "OutputManager",
+    "VersionManager",
+    "BayesOptModel",
+    "FeatureTokenizer",
+    "FTTransformerCore",
+    "FTTransformerSklearn",
+    "GraphNeuralNetSklearn",
+    "MaskedTabularDataset",
+    "ResBlock",
+    "ResNetSequential",
+    "ResNetSklearn",
+    "ScaledTransformerEncoderLayer",
+    "SimpleGraphLayer",
+    "SimpleGNN",
+    "TabularDataset",
+    "FTTrainer",
+    "GLMTrainer",
+    "GNNTrainer",
+    "ResNetTrainer",
+    "TrainerBase",
+    "XGBTrainer",
+    "_xgb_cuda_available",
+]