# FAISSKNN
`faissknn` contains implementations for both multiclass and multilabel K-Nearest Neighbors Classifier implementations. The classifiers follow the `scikit-learn`: `fit`, `predict`, and `predict_proba` methods.
### Install
The FAISS authors recommend to install `faiss` through conda e.g. `conda install -c pytorch faiss-gpu`. See [FAISS install page](https://github.com/facebookresearch/faiss/blob/main/INSTALL.md) for more info.
Once `faiss` is installed, `faissknn` can be install through pypi:
```
pip install faissknn
```
### Usage
Multiclass:
```python
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from faissknn import FaissKNNClassifier
x, y = make_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
model = FaissKNNClassifier(
n_neighbors=5,
n_classes=None,
device="cpu"
)
model.fit(x_train, y_train)
y_pred = model.predict(x_test) # (N,)
y_proba = model.predict_proba(x_test) # (N, C)
```
Multilabel:
```python
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from faissknn import FaissKNNMultilabelClassifier
x, y = make_multilabel_classification()
x_train, x_test, y_train, y_test = train_test_split(x, y)
model = FaissKNNClassifier(
n_neighbors=5,
device="cpu"
)
model.fit(x_train, y_train)
y_pred = model.predict(x_test) # (N, C)
y_proba = model.predict_proba(x_test) # (N, C)
```
GPU/CUDA: `faissknn` also supports running on the GPU to speed up computation. Simply change the device to `cuda` or a specific cuda device `cuda:0`
```python
model = FaissKNNClassifier(
n_neighbors=5,
device="cuda"
)
model = FaissKNNClassifier(
n_neighbors=5,
device="cuda:0"
)
```
Raw data
{
"_id": null,
"home_page": "https://github.com/isaaccorley/faissknn",
"name": "faissknn",
"maintainer": "",
"docs_url": null,
"requires_python": "<4,>=3.9",
"maintainer_email": "",
"keywords": "pytorch,machine learning,deep learning",
"author": "Isaac Corley",
"author_email": "isaac.corley@my.utsa.edu",
"download_url": "https://files.pythonhosted.org/packages/72/e0/5b2fd177311d93d259db16dc9b6d7afe32e1b45dd61a3f812c0bfd099530/faissknn-0.0.1.tar.gz",
"platform": null,
"description": "# FAISSKNN\n`faissknn` contains implementations for both multiclass and multilabel K-Nearest Neighbors Classifier implementations. The classifiers follow the `scikit-learn`: `fit`, `predict`, and `predict_proba` methods.\n\n### Install\n\nThe FAISS authors recommend to install `faiss` through conda e.g. `conda install -c pytorch faiss-gpu`. See [FAISS install page](https://github.com/facebookresearch/faiss/blob/main/INSTALL.md) for more info.\n\nOnce `faiss` is installed, `faissknn` can be install through pypi:\n\n```\npip install faissknn\n```\n\n### Usage\n\nMulticlass:\n\n```python\nfrom sklearn.datasets import make_classification\nfrom sklearn.model_selection import train_test_split\n\nfrom faissknn import FaissKNNClassifier\n\nx, y = make_classification()\nx_train, x_test, y_train, y_test = train_test_split(x, y)\nmodel = FaissKNNClassifier(\n n_neighbors=5,\n n_classes=None,\n device=\"cpu\"\n)\nmodel.fit(x_train, y_train)\n\ny_pred = model.predict(x_test) # (N,)\ny_proba = model.predict_proba(x_test) # (N, C)\n```\n\nMultilabel:\n\n```python\nfrom sklearn.datasets import make_classification\nfrom sklearn.model_selection import train_test_split\n\nfrom faissknn import FaissKNNMultilabelClassifier\n\nx, y = make_multilabel_classification()\nx_train, x_test, y_train, y_test = train_test_split(x, y)\nmodel = FaissKNNClassifier(\n n_neighbors=5,\n device=\"cpu\"\n)\nmodel.fit(x_train, y_train)\n\ny_pred = model.predict(x_test) # (N, C)\ny_proba = model.predict_proba(x_test) # (N, C)\n```\n\nGPU/CUDA: `faissknn` also supports running on the GPU to speed up computation. Simply change the device to `cuda` or a specific cuda device `cuda:0`\n\n```python\nmodel = FaissKNNClassifier(\n n_neighbors=5,\n device=\"cuda\"\n)\nmodel = FaissKNNClassifier(\n n_neighbors=5,\n device=\"cuda:0\"\n)\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "Faiss implementation of multiclass and multilabel K-Nearest Neighbors Classifiers",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://github.com/isaaccorley/faissknn"
},
"split_keywords": [
"pytorch",
"machine learning",
"deep learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "07433aa0fa6cef39134a51fa947dff793ee49402707bbdca0190e9ac728d4b02",
"md5": "dd657e2d765a66434b34c5dc581ab432",
"sha256": "e0ffd8aa5a33074d9d98f3cb7eaa6c3732d73bb9986c17ced93a17b157dd0303"
},
"downloads": -1,
"filename": "faissknn-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "dd657e2d765a66434b34c5dc581ab432",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4,>=3.9",
"size": 4516,
"upload_time": "2023-05-22T23:34:03",
"upload_time_iso_8601": "2023-05-22T23:34:03.137849Z",
"url": "https://files.pythonhosted.org/packages/07/43/3aa0fa6cef39134a51fa947dff793ee49402707bbdca0190e9ac728d4b02/faissknn-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "72e05b2fd177311d93d259db16dc9b6d7afe32e1b45dd61a3f812c0bfd099530",
"md5": "fa5b208f2932c4920345acd0b4608ba7",
"sha256": "d81a34949681c88a4bbce712102078ed8115b8402ca19966116a1a9ea81a2e87"
},
"downloads": -1,
"filename": "faissknn-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "fa5b208f2932c4920345acd0b4608ba7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4,>=3.9",
"size": 5000,
"upload_time": "2023-05-22T23:34:04",
"upload_time_iso_8601": "2023-05-22T23:34:04.954216Z",
"url": "https://files.pythonhosted.org/packages/72/e0/5b2fd177311d93d259db16dc9b6d7afe32e1b45dd61a3f812c0bfd099530/faissknn-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-22 23:34:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "isaaccorley",
"github_project": "faissknn",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "faissknn"
}
JSON
