Classy Classification

Have you every struggled with needing a Spacy TextCategorizer but didn't have the time to train one from scratch? Classy Classification is the way to go! For few-shot classification using sentence-transformers or spaCy models, provide a dictionary with labels and examples, or just provide a list of labels for zero shot-classification with Hugginface zero-shot classifiers.

Install

pip install classy-classification

or install with faster inference using onnx.

pip install classy-classification[onnx]

ONNX issues

pickling

ONNX does show some issues when pickling the data.

M1

Some installation issues might occur, which can be fixed by these commands.

brew install cmake
brew install protobuf
pip3 install onnx --no-use-pep517

Quickstart

SpaCy embeddings

import spacy
import classy_classification

data = {
    "furniture": ["This text is about chairs.",
               "Couches, benches and televisions.",
               "I really need to get a new sofa."],
    "kitchen": ["There also exist things like fridges.",
                "I hope to be getting a new stove today.",
                "Do you also have some ovens."]
}

nlp = spacy.load("en_core_web_md")
nlp.add_pipe(
    "text_categorizer",
    config={
        "data": data,
        "model": "spacy"
    }
)

print(nlp("I am looking for kitchen appliances.")._.cats)

# Output:
#
# [{"label": "furniture", "score": 0.21}, {"label": "kitchen", "score": 0.79}]

Multi-label classification

Sometimes multiple labels are necessary to fully describe the contents of a text. In that case, we want to make use of the multi-label implementation, here the sum of label scores is not limited to 1. Note that we use a multi-layer perceptron for this purpose instead of the default SVC implementation, requiring a few more training samples.

import spacy
import classy_classification

data = {
    "furniture": ["This text is about chairs.",
               "Couches, benches and televisions.",
               "I really need to get a new sofa.",
               "We have a new dinner table."],
    "kitchen": ["There also exist things like fridges.",
                "I hope to be getting a new stove today.",
                "Do you also have some ovens.",
                "We have a new dinner table."]
}

nlp = spacy.load("en_core_web_md")
nlp.add_pipe(
    "text_categorizer",
    config={
        "data": data,
        "model": "spacy",
        "multi_label": True,
        "config": {"hidden_layer_sizes": (64,), "seed": 42}
    }
)

print(nlp("texts about dinner tables have multiple labels.")._.cats)

# Output:
#
# [{"label": "furniture", "score": 0.94}, {"label": "kitchen", "score": 0.97}]

Sentence-transfomer embeddings

import spacy
import classy_classification

data = {
    "furniture": ["This text is about chairs.",
               "Couches, benches and televisions.",
               "I really need to get a new sofa."],
    "kitchen": ["There also exist things like fridges.",
                "I hope to be getting a new stove today.",
                "Do you also have some ovens."]
}

nlp = spacy.blank("en")
nlp.add_pipe(
    "text_categorizer",
    config={
        "data": data,
        "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
        "device": "gpu"
    }
)

print(nlp("I am looking for kitchen appliances.")._.cats)

# Output:
#
# [{"label": "furniture", "score": 0.21}, {"label": "kitchen", "score": 0.79}]

Hugginface zero-shot classifiers

import spacy
import classy_classification

data = ["furniture", "kitchen"]

nlp = spacy.blank("en")
nlp.add_pipe(
    "text_categorizer",
    config={
        "data": data,
        "model": "typeform/distilbert-base-uncased-mnli",
        "cat_type": "zero",
        "device": "gpu"
    }
)

print(nlp("I am looking for kitchen appliances.")._.cats)

# Output:
#
# [{"label": "furniture", "score": 0.21}, {"label": "kitchen", "score": 0.79}]

Credits

Inspiration Drawn From

Huggingface does offer some nice models for few/zero-shot classification, but these are not tailored to multi-lingual approaches. Rasa NLU has a nice approach for this, but its too embedded in their codebase for easy usage outside of Rasa/chatbots. Additionally, it made sense to integrate sentence-transformers and Hugginface zero-shot, instead of default word embeddings. Finally, I decided to integrate with Spacy, since training a custom Spacy TextCategorizer seems like a lot of hassle if you want something quick and dirty.

• Scikit-learn
• Rasa NLU
• Sentence Transformers
• Spacy

Or buy me a coffee

Standalone usage without spaCy

from classy_classification import classyClassifier

data = {
    "furniture": ["This text is about chairs.",
               "Couches, benches and televisions.",
               "I really need to get a new sofa."],
    "kitchen": ["There also exist things like fridges.",
                "I hope to be getting a new stove today.",
                "Do you also have some ovens."]
}

classifier = classyClassifier(data=data)
classifier("I am looking for kitchen appliances.")
classifier.pipe(["I am looking for kitchen appliances."])

# overwrite training data
classifier.set_training_data(data=data)
classifier("I am looking for kitchen appliances.")

# overwrite [embedding model](https://www.sbert.net/docs/pretrained_models.html)
classifier.set_embedding_model(model="paraphrase-MiniLM-L3-v2")
classifier("I am looking for kitchen appliances.")

# overwrite SVC config
classifier.set_classification_model(
    config={
        "C": [1, 2, 5, 10, 20, 100],
        "kernels": ["linear"],
        "max_cross_validation_folds": 5
    }
)
classifier("I am looking for kitchen appliances.")

Save and load models

data = {
    "furniture": ["This text is about chairs.",
               "Couches, benches and televisions.",
               "I really need to get a new sofa."],
    "kitchen": ["There also exist things like fridges.",
                "I hope to be getting a new stove today.",
                "Do you also have some ovens."]
}
classifier = classyClassifier(data=data)

with open("./classifier.pkl", "wb") as f:
    pickle.dump(classifier, f)

f = open("./classifier.pkl", "rb")
classifier = pickle.load(f)
classifier("I am looking for kitchen appliances.")

Todo

[ ] look into a way to integrate spacy trf models.