trendingtechnology / adaptnlp Goto Github PK

from adaptnlp import EasyTokenTagger

## Example Text
example_text = "Novetta's headquarters is located in Mclean, Virginia."

## Load the token tagger module and tag text with the NER model 
tagger = EasyTokenTagger()
sentences = tagger.tag_text(text=example_text, model_name_or_path="ner")

## Output tagged token span results in Flair's Sentence object model
for sentence in sentences:
    for entity in sentence.get_spans("ner"):
        print(entity)

from adaptnlp import EasySequenceClassifier 

## Example Text
example_text = "Novetta is a great company that was chosen as one of top 50 great places to work!"

## Load the sequence classifier module and classify sequence of text with the english sentiment model 
classifier = EasySequenceClassifier()
sentences = classifier.tag_text(text=example_text, model_name_or_path="en-sentiment")

## Output labeled text results in Flair's Sentence object model
for sentence in sentences:
    print(sentence.labels)

from adaptnlp import EasyQuestionAnswering 

## Example Query and Context 
query = "What is the meaning of life?"
context = "Machine Learning is the meaning of life."
top_n = 5

## Load the QA module and run inference on results 
qa = EasyQuestionAnswering()
best_answer, best_n_answers = qa.predict_qa(query=query, context=context, n_best_size=top_n)

## Output top answer as well as top 5 answers
print(best_answer)
print(best_n_answers)

from adaptnlp import EasyDocumentEmbeddings, SequenceClassifierTrainer 

# Specify corpus data directory and model output directory
corpus = "Path/to/data/directory" 
OUTPUT_DIR = "Path/to/output/directory" 

# Instantiate AdaptNLP easy document embeddings module, which can take in a variable number of embeddings to make `Stacked Embeddings`.  
# You may also use custom Transformers LM models by specifying the path the the language model
doc_embeddings = EasyDocumentEmbeddings(model_name_or_path="bert-base-cased", methods = ["rnn"])

# Instantiate Sequence Classifier Trainer by loading in the data, data column map, and embeddings as an encoder
sc_trainer = SequenceClassifierTrainer(corpus=corpus, encoder=doc_embeddings, column_name_map={0: "text", 1:"label"})

# Find Learning Rate
learning_rate = sc_trainer.find_learning_rate(output_dir=OUTPUT_DIR)

# Train Using Flair's Sequence Classification Head
sc_trainer.train(output_dir=OUTPUT_DIR, learning_rate=learning_rate, max_epochs=150)


# Predict text labels with the trained model using `EasySequenceClassifier`
from adaptnlp import EasySequenceClassifier
example_text = '''Where was the Queen's wedding held? '''
classifier = EasySequenceClassifier()
sentences = classifier.tag_text(example_text, model_name_or_path=OUTPUT_DIR / "final-model.pt")
print("Label output:\n")
for sentence in sentences:
    print(sentence.labels)

from adaptnlp import LMFineTuner

# Specify Text Data File Paths
train_data_file = "Path/to/train.csv"
eval_data_file = "Path/to/test.csv"

# Instantiate Finetuner with Desired Language Model
finetuner = LMFineTuner(train_data_file=train_data_file, eval_data_file=eval_data_file, model_type="bert", model_name_or_path="bert-base-cased")
finetuner.freeze()

# Find Optimal Learning Rate
learning_rate = finetuner.find_learning_rate(base_path="Path/to/base/directory")
finetuner.freeze()

# Train and Save Fine Tuned Language Models
finetuner.train_one_cycle(output_dir="Path/to/output/directory", learning_rate=learning_rate)