haphazard 0.1.0__tar.gz

haphazard-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Arijit Das
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

haphazard-0.1.0/MANIFEST.in

@@ -0,0 +1,2 @@
+include README.md
+recursive-include haphazard *.py

haphazard-0.1.0/PKG-INFO

@@ -0,0 +1,255 @@
+Metadata-Version: 2.4
+Name: haphazard
+Version: 0.1.0
+Summary: A modular framework for registering and running haphazard datasets and models.
+Home-page: https://github.com/theArijitDas/Haphazard-Package/
+Author: Arijit Das
+Author-email: dasarijitjnv@gmail.com
+License: MIT
+Project-URL: Bug Tracker, https://github.com/theArijitDas/Haphazard-Package/issues
+Project-URL: Source Code, https://github.com/theArijitDas/Haphazard-Package/
+Keywords: machine-learning haphazard models datasets registration framework
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: tqdm
+Requires-Dist: scikit-learn
+Requires-Dist: torch
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Haphazard
+
+A Python package for **haphazard dataset and model management**.  
+Provides a standardized interface for loading datasets and models, running experiments, and extending with custom datasets or models.
+
+---
+
+## Table of Contents
+
+- [Installation](#installation)
+- [Quick Start](#quick-start)
+- [Datasets](#datasets)
+- [Models](#models)
+- [Contributing](#contributing)
+- [License](#license)
+
+---
+
+## Installation
+
+Install via pip (after packaging):
+
+```bash
+pip install haphazard
+````
+
+Or for local development:
+
+```bash
+git clone <repo_url>
+cd haphazard
+pip install -e .
+```
+
+---
+
+## Project Structure
+
+The Haphazard package has a modular layout:
+
+```
+haphazard/
+├── __init__.py                    # Top-level package
+├── data/                          # Dataset related modules
+│   ├── __init__.py
+│   ├── base_dataset.py            # Abstract BaseDataset class
+│   └── datasets/                  # All dataset implementations
+│       ├── __init__.py
+│       └── dummy_dataset/
+│           └── __init__.py
+├── models/                        # Model related modules
+│   ├── __init__.py
+│   ├── base_model.py              # Abstract BaseModel class
+│   └── model_zoo/                 # All model implementations
+│       ├── __init__.py
+│       └── dummy_model/
+│           └── __init__.py
+└── utils/                         # Optional helper functions
+    └── ...
+```
+
+**Notes:**
+
+* `data/base_dataset.py` defines `BaseDataset`.
+* `data/datasets/` contains registered datasets; each dataset is a submodule with `__init__.py`.
+* `models/base_model.py` defines `BaseModel`.
+* `models/model_zoo/` contains registered models; each model is a submodule with `__init__.py`.
+* `utils/` is optional, for shared helpers.
+
+This layout allows **dynamic registration** of datasets and models via decorators.
+
+---
+
+
+## Quick Start
+
+```python
+from haphazard import load_dataset, load_model
+
+# Load dataset
+dataset = load_dataset("dummy", n_samples=100, n_features=10)
+
+# Load model
+model = load_model("dummy")
+
+# Run model
+outputs = model(dataset)
+print(outputs)
+```
+
+---
+
+## Datasets
+
+* All datasets must inherit from `BaseDataset`.
+* Example dataset: `DummyDataset`.
+* Main interface:
+
+```python
+from haphazard import load_dataset
+
+dataset = load_dataset("dummy", base_path="./data")
+x, y = dataset.load_data()
+mask = dataset.load_mask(scheme="probabilistic", availability_prob=0.5)
+```
+
+### Dataset Attributes
+
+* `name` : str — Dataset name.
+* `task` : `"classification"` | `"regression"`.
+* `haphazard_type` : `"controlled"` | `"intrinsic"`.
+* `n_samples`, `n_features` : int.
+* `num_classes` : int (for classification).
+
+---
+
+## Models
+
+* All models must inherit from `BaseModel`.
+* Example model: `DummyModel`.
+* Main interface:
+
+```python
+from haphazard import load_model
+
+model = load_model("dummy")
+outputs = model(dataset)
+```
+
+### Output
+
+* **Classification**: `labels`, `preds`, `logits`, `time_taken`, `is_logit`.
+* **Regression**: `targets`, `preds`, `time_taken`.
+
+---
+
+## Contributing
+
+Haphazard is designed for **easy extensibility**. You can add new datasets and models.
+
+### Adding a new dataset
+
+1. Create a new folder under `haphazard/data/datasets/`, e.g., `my_dataset/`.
+2. Add `__init__.py`:
+
+```python
+from ...base_dataset import BaseDataset
+from ...datasets import register_dataset
+import numpy as np
+
+@register_dataset("my_dataset")
+class MyDataset(BaseDataset):
+    def __init__(self, base_path="./", **kwargs):
+        self.name = "my_dataset"
+        self.haphazard_type = "controlled"
+        self.task = "classification"
+        super().__init__(base_path=base_path, **kwargs)
+
+    def read_data(self, base_path="./"):
+        # Load or generate x, y
+        x = np.random.random((100, 10))
+        y = np.random.randint(0, 2, 100)
+        return x, y
+```
+
+3. The dataset is automatically registered and can be loaded with `load_dataset("my_dataset")`.
+
+### Adding a new model
+
+1. Create a new folder under `haphazard/models/model_zoo/`, e.g., `my_model/`.
+2. Add `__init__.py`:
+
+```python
+from ...base_model import BaseModel, BaseDataset
+from ...model_zoo import register_model
+import numpy as np
+
+@register_model("my_model")
+class MyModel(BaseModel):
+    def __init__(self, **kwargs):
+        self.name = "MyModel"
+        self.tasks = {"classification", "regression"}
+        self.deterministic = True
+        self.hyperparameters = set()
+        super().__init__(**kwargs)
+
+    def fit(self, dataset: BaseDataset, mask_params=None, model_params=None, seed=42):
+        # Dummy implementation
+        x, y = dataset.load_data()
+        mask = dataset.load_mask(**mask_params)
+        preds = np.random.randint(0, 2, size=y.shape[0])
+        if dataset.task == "classification":
+            return {
+                "labels": y,
+                "preds": preds,
+                "logits": preds.astype(float),
+                "time_taken": 0.0,
+                "is_logit": True
+            }
+        elif dataset.task == "regression":
+            return {
+                "targets": y,
+                "preds": preds,
+                "time_taken": 0.0,
+            }
+```
+
+3. The model is automatically registered and can be loaded with `load_model("my_model")`.
+
+---
+
+## License
+
+MIT License.

haphazard-0.1.0/README.md

@@ -0,0 +1,214 @@
+# Haphazard
+
+A Python package for **haphazard dataset and model management**.  
+Provides a standardized interface for loading datasets and models, running experiments, and extending with custom datasets or models.
+
+---
+
+## Table of Contents
+
+- [Installation](#installation)
+- [Quick Start](#quick-start)
+- [Datasets](#datasets)
+- [Models](#models)
+- [Contributing](#contributing)
+- [License](#license)
+
+---
+
+## Installation
+
+Install via pip (after packaging):
+
+```bash
+pip install haphazard
+````
+
+Or for local development:
+
+```bash
+git clone <repo_url>
+cd haphazard
+pip install -e .
+```
+
+---
+
+## Project Structure
+
+The Haphazard package has a modular layout:
+
+```
+haphazard/
+├── __init__.py                    # Top-level package
+├── data/                          # Dataset related modules
+│   ├── __init__.py
+│   ├── base_dataset.py            # Abstract BaseDataset class
+│   └── datasets/                  # All dataset implementations
+│       ├── __init__.py
+│       └── dummy_dataset/
+│           └── __init__.py
+├── models/                        # Model related modules
+│   ├── __init__.py
+│   ├── base_model.py              # Abstract BaseModel class
+│   └── model_zoo/                 # All model implementations
+│       ├── __init__.py
+│       └── dummy_model/
+│           └── __init__.py
+└── utils/                         # Optional helper functions
+    └── ...
+```
+
+**Notes:**
+
+* `data/base_dataset.py` defines `BaseDataset`.
+* `data/datasets/` contains registered datasets; each dataset is a submodule with `__init__.py`.
+* `models/base_model.py` defines `BaseModel`.
+* `models/model_zoo/` contains registered models; each model is a submodule with `__init__.py`.
+* `utils/` is optional, for shared helpers.
+
+This layout allows **dynamic registration** of datasets and models via decorators.
+
+---
+
+
+## Quick Start
+
+```python
+from haphazard import load_dataset, load_model
+
+# Load dataset
+dataset = load_dataset("dummy", n_samples=100, n_features=10)
+
+# Load model
+model = load_model("dummy")
+
+# Run model
+outputs = model(dataset)
+print(outputs)
+```
+
+---
+
+## Datasets
+
+* All datasets must inherit from `BaseDataset`.
+* Example dataset: `DummyDataset`.
+* Main interface:
+
+```python
+from haphazard import load_dataset
+
+dataset = load_dataset("dummy", base_path="./data")
+x, y = dataset.load_data()
+mask = dataset.load_mask(scheme="probabilistic", availability_prob=0.5)
+```
+
+### Dataset Attributes
+
+* `name` : str — Dataset name.
+* `task` : `"classification"` | `"regression"`.
+* `haphazard_type` : `"controlled"` | `"intrinsic"`.
+* `n_samples`, `n_features` : int.
+* `num_classes` : int (for classification).
+
+---
+
+## Models
+
+* All models must inherit from `BaseModel`.
+* Example model: `DummyModel`.
+* Main interface:
+
+```python
+from haphazard import load_model
+
+model = load_model("dummy")
+outputs = model(dataset)
+```
+
+### Output
+
+* **Classification**: `labels`, `preds`, `logits`, `time_taken`, `is_logit`.
+* **Regression**: `targets`, `preds`, `time_taken`.
+
+---
+
+## Contributing
+
+Haphazard is designed for **easy extensibility**. You can add new datasets and models.
+
+### Adding a new dataset
+
+1. Create a new folder under `haphazard/data/datasets/`, e.g., `my_dataset/`.
+2. Add `__init__.py`:
+
+```python
+from ...base_dataset import BaseDataset
+from ...datasets import register_dataset
+import numpy as np
+
+@register_dataset("my_dataset")
+class MyDataset(BaseDataset):
+    def __init__(self, base_path="./", **kwargs):
+        self.name = "my_dataset"
+        self.haphazard_type = "controlled"
+        self.task = "classification"
+        super().__init__(base_path=base_path, **kwargs)
+
+    def read_data(self, base_path="./"):
+        # Load or generate x, y
+        x = np.random.random((100, 10))
+        y = np.random.randint(0, 2, 100)
+        return x, y
+```
+
+3. The dataset is automatically registered and can be loaded with `load_dataset("my_dataset")`.
+
+### Adding a new model
+
+1. Create a new folder under `haphazard/models/model_zoo/`, e.g., `my_model/`.
+2. Add `__init__.py`:
+
+```python
+from ...base_model import BaseModel, BaseDataset
+from ...model_zoo import register_model
+import numpy as np
+
+@register_model("my_model")
+class MyModel(BaseModel):
+    def __init__(self, **kwargs):
+        self.name = "MyModel"
+        self.tasks = {"classification", "regression"}
+        self.deterministic = True
+        self.hyperparameters = set()
+        super().__init__(**kwargs)
+
+    def fit(self, dataset: BaseDataset, mask_params=None, model_params=None, seed=42):
+        # Dummy implementation
+        x, y = dataset.load_data()
+        mask = dataset.load_mask(**mask_params)
+        preds = np.random.randint(0, 2, size=y.shape[0])
+        if dataset.task == "classification":
+            return {
+                "labels": y,
+                "preds": preds,
+                "logits": preds.astype(float),
+                "time_taken": 0.0,
+                "is_logit": True
+            }
+        elif dataset.task == "regression":
+            return {
+                "targets": y,
+                "preds": preds,
+                "time_taken": 0.0,
+            }
+```
+
+3. The model is automatically registered and can be loaded with `load_model("my_model")`.
+
+---
+
+## License
+
+MIT License.

haphazard-0.1.0/haphazard/__init__.py

@@ -0,0 +1,25 @@
+"""
+haphazard
+---------
+Top-level imports for main API access.
+"""
+
+# User-facing APIs
+from .data import load_dataset
+from .models import load_model
+
+# Optional APIs for contributors
+from .data import BaseDataset, register_dataset
+from .models import BaseModel, register_model
+
+# -------------------------------------------------------------------------
+# Public exports
+# -------------------------------------------------------------------------
+__all__ = [
+    "load_dataset",
+    "load_model",
+    "BaseDataset",
+    "register_dataset",
+    "BaseModel",
+    "register_model",
+]

haphazard-0.1.0/haphazard/data/__init__.py

@@ -0,0 +1,26 @@
+"""
+haphazard.data
+--------------
+Dataset abstraction and registry subpackage.
+
+This subpackage provides:
+
+- The :class:`BaseDataset` abstract base class, which all datasets must inherit from.
+- Dataset registration and loading utilities via the `datasets` submodule.
+"""
+
+from .base_dataset import BaseDataset, TaskType, HaphazardType
+from .datasets import load_dataset, _DATASET_REGISTRY, register_dataset
+
+
+# -------------------------------------------------------------------------
+# Public exports
+# -------------------------------------------------------------------------
+__all__ = [
+    "BaseDataset",
+    "TaskType",
+    "HaphazardType",
+    "load_dataset",
+    "_DATASET_REGISTRY",
+    "register_dataset",
+]