ClassifAIer
ClassifAIer is a Python library that combines scikit-learn classifiers with LangChain embedding libraries, enabling seamless text classification using embeddings from large language models. This library offers a user-friendly interface, allowing you to classify text data in a human-like manner.
Features
- Embedding Support: Ability to work with embeddings from large language models like OpenAI and compatible with embeddings supported by LangChain.
- Parametric Classifiers: Compatibility with a wide range of classifiers from
scikit-learn(e.g.,RandomForestClassifier,KNeighborsClassifier, etc.). - Easy to Use: Simplifies text classification tasks with a user-friendly API.
- Save and Load: Allows you to save and reload trained models for reuse.
Requirements
To use this library, you need Python 3.7 or higher. The required packages will be automatically installed when you install this library.
- scikit-learn
- langchain-core
- langchain
- numpy
Installation
You can install the required libraries using the following command:
pip install ClassifAIer
Usage
from classifaier import ClassifAIer
from langchain.embeddings import OpenAIEmbeddings
from sklearn.ensemble import RandomForestClassifier
# Initialize the embedding provider
embedding_provider = OpenAIEmbeddings(api_key='YOUR_API_KEY')
random_forest_classifier_params = {
"n_estimators": 100,
"max_depth": None,
"min_samples_split": 2,
"min_samples_leaf": 1,
"random_state": 42
}
random_forest_classifier = RandomForestClassifier(**random_forest_classifier_params)
# Create a classifier instance
classifier = ClassifAIer(embedding_provider=embedding_provider, classifier=random_forest_classifier)
# Prepare your data
texts = ["İspanya Birinci Futbol Ligi (La Liga) ekibi Athletic Bilbao, golcü oyuncusu Aritz Aduriz'in sözleşmesini bir yıllığına uzattı.", "Piyasalar ABD'nin enflasyon verilerine odaklandı."]
labels = ["spor", "ekonomi"]
# Train the model
classifier.fit(texts, labels)
# Make predictions
predictions = classifier.predict_all(["Fildişi Sahili Milli Takımı'nın Belçikalı teknik direktörü Marc Wilmots görevinden ayrıldı.", "Borsa, günü yükselişle tamamladı"])
print(predictions) # Output: ['spor', 'ekonomi']
# Save the model
classifier.save("my_classifier.pkl")
# Load the model
loaded_classifier = ClassifAIer.load("my_classifier.pkl", embedding_provider)
Contributing
Contributions are welcome! If you have suggestions or improvements, please create a pull request or open an issue.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Metadata
Release files for ClassifAIer 0.1.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ClassifAIer-0.1.6.tar.gz | 6.2 kB | Without provenance | Details for ClassifAIer-0.1.6.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ClassifAIer-0.1.6-py3-none-any.whl | Python 3 | none | any | Details for ClassifAIer-0.1.6-py3-none-any.whl |
Total release size: 13.1 kB
Release files / ClassifAIer-0.1.6.tar.gz
| Download URL | ClassifAIer-0.1.6.tar.gz |
|---|---|
| Size | 6.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
30ee36a9972aba9297070b5b05c8bfe6f21e77556e3d981da1d7ea43f2b79707
|
|
BLAKE2b-256 checksum How to use checksums |
5fe22d8e681ce52bcf32ae07594271aaed4441c7503741b47ce3dd71099e0fae
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.10.17
|
Release files / ClassifAIer-0.1.6-py3-none-any.whl
| Download URL | ClassifAIer-0.1.6-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
122df3c4e0a8a489131307b57b6393180048ec9e05ff7304c8b38b0c411e841d
|
|
BLAKE2b-256 checksum How to use checksums |
3600337ec3a7267f6749fe5c6a65a347d0049b43ce562b188dfcdd1de1961f89
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.10.17
|
Security for ClassifAIer 0.1.6
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.