def setUpClass(cls):
cls.features = Features()
cls.features.append(Feature("A", str, 1))
A, X = list(zip(*DATA))
cls.records = [
Record(str(i), data={"features": {
"A": A[i],
"X": X[i]
}}) for i in range(0, len(X))
]
cls.sources = Sources(
MemorySource(MemorySourceConfig(records=cls.records)))
cls.model_dir = tempfile.TemporaryDirectory()
cls.model = TextClassificationModel(
TextClassifierConfig(
directory=cls.model_dir.name,
classifications=[0, 1],
features=cls.features,
predict=Feature("X", int, 1),
add_layers=True,
layers=[
"Dense(units = 120, activation='relu')",
"Dense(units = 64, activation=relu)",
"Dense(units = 2, activation='softmax')",
],
model_path=
"https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim-with-oov/1",
epochs=30,
))
from dffml import CSVSource, Features, Feature
from dffml.noasync import train, accuracy, predict
from dffml_model_tensorflow_hub.text_classifier import TextClassificationModel
model = TextClassificationModel(
features=Features(Feature("sentence", str, 1)),
predict=Feature("sentiment", int, 1),
classifications=[0, 1, 2],
clstype=int,
directory="tempdir",
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="test.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{"sentence": "This track is horrible"},
):
features["sentiment"] = prediction["sentiment"]["value"]
print(features)