txtai-tfidf-logr.py

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

# Train the model
pipeline = Pipeline([
    ('tfidf', TfidfVectorizer()),
    ('lr', LogisticRegression(max_iter=250))
])

pipeline.fit(ds["train"]["text"], ds["train"]["label"])

# Determine accuracy on validation set
results = pipeline.predict(ds["validation"]["text"])
labels = ds["validation"]["label"]

results = [results[x] == label for x, label in enumerate(labels)]
print("Accuracy =", sum(results) / len(ds["validation"]))