def setUpClass(cls):
# Create a temporary directory to store the trained model
cls.model_dir = tempfile.TemporaryDirectory()
# Create an instance of the model
cls.model = XGBRegressorModel(
XGBRegressorModelConfig(
features=Features(Feature("Feature1", float, 1),
Feature("Feature2")),
predict=Feature("Target", float, 1),
directory=cls.model_dir.name,
))
# Generating data f(x1,x2) = 2*x1 + 3*x2
_n_data = 2000
_temp_data = np.random.rand(2, _n_data)
cls.records = [
Record(
"x" + str(random.random()),
data={
"features": {
"Feature1": float(_temp_data[0][i]),
"Feature2": float(_temp_data[1][i]),
"Target": 2 * _temp_data[0][i] + 3 * _temp_data[1][i],
}
},
) for i in range(0, _n_data)
]
cls.trainingsource = Sources(
MemorySource(MemorySourceConfig(records=cls.records[:1800])))
cls.testsource = Sources(
MemorySource(MemorySourceConfig(records=cls.records[1800:])))
def test_predict(self):
self.required_plugins("dffml-model-scikit")
# Import SciKit modules
dffml_model_scikit = importlib.import_module("dffml_model_scikit")
# Instantiate the model
model = dffml_model_scikit.LinearRegressionModel(
directory=self.mktempdir(),
predict=Feature("Salary", int, 1),
features=Features(
Feature("Years", int, 1),
Feature("Expertise", int, 1),
Feature("Trust", float, 1),
),
)
training_data = CSVSource(filename=self.train_filename)
test_data = CSVSource(filename=self.test_filename)
predict_data = CSVSource(filename=self.predict_filename)
# Train the model
train(model, training_data)
# Assess accuracy
accuracy(model, test_data)
# Make prediction
predictions = [
prediction for prediction in predict(model, predict_data)
]
self.assertEqual(round(predictions[0][2]["Salary"]["value"]), 70)
self.assertEqual(round(predictions[1][2]["Salary"]["value"]), 80)
def test_config_set(self):
config = FakeTesting.config(
parse_unknown(
"--test-fake-name",
"feedface",
"--test-num",
"-4.2",
"--test-fake-label",
"default-label",
"--test-fake-readonly",
"--test-files",
"a",
"b",
"c",
"--test-fake-source",
"csv",
"--test-source-filename",
"file.csv",
"--test-features",
"Year:int:1",
"Commits:int:10",
))
self.assertEqual(config.num, -4.2)
self.assertEqual(config.files, ["a", "b", "c"])
self.assertEqual(config.name, "feedface")
self.assertEqual(config.label, "default-label")
self.assertTrue(config.readonly)
self.assertTrue(isinstance(config.source, CSVSource))
self.assertEqual(config.source.config.filename, "file.csv")
self.assertEqual(
config.features,
Features(DefFeature("Year", int, 1),
DefFeature("Commits", int, 10)),
)
async def test_model(self):
with tempfile.TemporaryDirectory() as tempdir, patch.object(
Model, "load", new=model_load):
config = parse_unknown(
"--model-directory",
tempdir,
"--model-features",
"Years:int:1",
"Experiance:int:1",
"--model-predict",
"Salary:float:1",
)
async with self.post("/configure/model/fake/salary",
json=config) as r:
self.assertEqual(await r.json(), OK)
self.assertIn("salary", self.cli.app["models"])
self.assertEqual(
self.cli.app["models"]["salary"].config,
FakeModelConfig(
directory=pathlib.Path(tempdir),
features=Features(
Feature("Years", int, 1),
Feature("Experiance", int, 1),
),
predict=Feature("Salary", float, 1),
),
)
with self.subTest(context="salaryctx"):
# Create the context
async with self.get(
"/context/model/salary/salaryctx") as r:
self.assertEqual(await r.json(), OK)
self.assertIn("salaryctx",
self.cli.app["model_contexts"])
class FakeTestingConfig2:
name: str = field("Name of FakeTesting2")
num: float
features: Features = Features(
DefFeature("default", int, 1), DefFeature("features", int, 10)
)
label: str = "unlabeled"
def test_config_defaults(self):
config = FakeTesting.config(
parse_unknown(
"--test-fake-name",
"feedface",
"--test-num",
"-4.2",
"--test-files",
"a",
"b",
"c",
"--test-source-filename",
"file.json",
"--test-features",
"Year:int:1",
"Commits:int:10",
"--test-fake-nums",
"100",
))
self.assertEqual(config.num, -4.2)
self.assertEqual(config.files, ["a", "b", "c"])
self.assertEqual(config.name, "feedface")
self.assertEqual(config.label, "unlabeled")
self.assertFalse(config.readonly)
self.assertTrue(isinstance(config.source, JSONSource))
self.assertEqual(config.source.config.filename,
pathlib.Path("file.json"))
self.assertEqual(
config.features,
Features(Feature("Year", int, 1), Feature("Commits", int, 10)),
)
self.assertEqual(config.nums, (100, ))
def setUpClass(cls):
# Create a temporary directory to store the trained model
cls.model_dir = tempfile.TemporaryDirectory()
# Create an instance of the model
cls.model = AnomalyModel(
features=Features(
Feature("A", int, 1),
Feature("B", int, 2),
),
predict=Feature("Y", int, 1),
directory=cls.model_dir.name,
)
# Generating data
_n_data = 1800
_temp_data = np.random.normal(2, 1, size=(2, _n_data))
cls.records = [
Record(
"x" + str(random.random()),
data={
"features": {
"A": float(_temp_data[0][i]),
"B": float(_temp_data[1][i]),
"Y":
(_temp_data[0][i] > 1 - _temp_data[1][i]).astype(int),
}
},
) for i in range(0, _n_data)
]
cls.trainingsource = Sources(
MemorySource(MemorySourceConfig(records=cls.records[:1400])))
cls.testsource = Sources(
MemorySource(MemorySourceConfig(records=cls.records[1400:])))
async def test_predict(self):
self.required_plugins("dffml-model-scikit")
# Import SciKit modules
dffml_model_scikit = importlib.import_module("dffml_model_scikit")
# Instantiate the model
model = dffml_model_scikit.LinearRegressionModel(
location=self.mktempdir(),
predict=Feature("Salary", int, 1),
features=Features(
Feature("Years", int, 1),
Feature("Expertise", int, 1),
Feature("Trust", float, 1),
),
)
training_data = CSVSource(filename=self.train_filename)
test_data = CSVSource(filename=self.test_filename)
predict_data = CSVSource(filename=self.predict_filename)
# Train the model
await train(model, training_data)
# Assess accuracy
scorer = MeanSquaredErrorAccuracy()
await score(model, scorer, Feature("Salary", int, 1), test_data)
# Make prediction
predictions = [
prediction async for prediction in predict(model, predict_data)
]
self.assertEqual(round(predictions[0][2]["Salary"]["value"]), 70)
self.assertEqual(round(predictions[1][2]["Salary"]["value"]), 80)
# Test input data as list
await train(model, *self.train_data)
await score(model, scorer, Feature("Salary", int, 1), *self.test_data)
predictions = [
prediction
async for prediction in predict(model, *self.predict_data)
]
self.assertEqual(round(predictions[0][2]["Salary"]["value"]), 70)
self.assertEqual(round(predictions[1][2]["Salary"]["value"]), 80)
from dffml_model_tensorflow.dnnr import (
DNNRegressionModel,
DNNRegressionModelConfig,
)
training_data = CSVSource(
CSVSourceConfig(filename="training.csv", readonly=True))
test_data = CSVSource(CSVSourceConfig(filename="test.csv", readonly=True))
predict_data = CSVSource(CSVSourceConfig(filename="predict.csv",
readonly=True))
model = DNNRegressionModel(
DNNRegressionModelConfig(
features=Features(
DefFeature("Years", int, 1),
DefFeature("Expertise", int, 1),
DefFeature("Trust", float, 1),
),
predict="Salary",
))
Train(model=model, sources=[training_data])()
accuracy = Accuracy(model=model, sources=[test_data])()
row0, row1 = PredictAll(model=model, sources=[predict_data])()
print("Accuracy", accuracy)
print(row0)
print(row1)
